DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This action is responsive to the Application filed on 06/10/2026
Claims 1, 3-4, 6-7, 9 and 11-17 are pending in the case. Claims 1, 4 and 9 are
independent claims. Claims 2, 5, 8, and 10 are cancelled claims.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3-4, 6-7, 9 and 11-17 are rejected under 35 U.S.C. 103 as being unpatentable over SULZER et al. (US Pub No.: 20200364468 A1), hereinafter referred to as SULZER, in view of Della et al. (US Pub No.: 20190220011 A1), hereinafter referred to as Della and further in view of Harel et al (US Pub No.: 20100245072 A1), hereinafter referred to as Harel.
With respect to claim 1, SULZER discloses:
A sensor platform comprising: a memory, the memory storing instructions for generating event detection models used to detect events in captured sensor data (In fig. 6 and paragraph [0105], SULZER discloses an Intelligent Video Surveillance (IVS) system that includes one or more microprocessors and memory. The IVS system analyzes real-time surveillance video and may also receive information from an environmental sensor indicating environmental conditions. Based on the detected condition, the microprocessor dynamically selects an appropriate situation-specific model (such as a neutral network) from a set of existing models and uses that selected model to perform inference, identification, or event detection on real-time surveillance video. In paragraph [0109], SALZER discloses that the process 200 and/or the functionality of the IVS System discussed above may be embodied in a non-transitory, machine-readable medium, having stored thereon a set of executable instructions to perform the process 200 and/or the functionality of the IVS System.).
A sensor interface communicatively coupled to the memory, the sensor interface configured to capture data received from sensors connected to the sensor interface and to store the captured sensor data in the memory (In fig. 6 and paragraph [0105], SULZER discloses that a processing system 600 may include one or more processors 610, memory 620, one or more input/output devices 630, one or more sensors 640, one or more user interfaces 650, and one or more actuators.)
Generate and train an event detection model from the instructions (In paragraph [0077], SULZER discloses collecting video data for training, testing, and verification of a machine learning model. The training data may be obtained from real security camera footage or simulated environments that replicate real-world conditions.)
Apply the trained event detection model to the captured sensor data, the trained event detection model configured to detect an event from within the captured sensor data (In paragraph [0106], SULZER discloses that the Intelligent Video Surveillance (IVS) system uses multiple separately trained machine-learning models for different operating conditions. One model is trained using daytime video and images, while another model is trained using nighttime infrared video and images. Before performing event detection, the system pre-processes the incoming video to determine whether it was captured during the day or night, either by using data from an environmental sensor or by analyzing characteristics of the incoming video itself.)
Transmit captured sensor data associated with the detected event in response to a request from the remote observer for sensor data corresponding to the detected event (In paragraph [0073], SULZER discloses a system storing the metadata output values generated during testing and uses those values to determine the minimum and maximum threshold for triggering alerts. In an embodiment, a compound weapon detection alert may be required in order to transmit an emergency signal to, e.g., a law enforcement authority, where a compound alert is a weapon detection alert triggered based on input from two or more separate input devices (e.g., video cameras).)
With respect to claim 1, SULZER does not explicitly disclose:
Retrieve the captured sensor data from memory
Associate portions of the captured sensor data with the detected event
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Della to disclose
Retrieve the captured sensor data from memory (In paragraph [0017], Della discloses an event recorder 156 that may be configured to receive data from multiple sources, whether internal or external to an autonomous vehicle 120, and further configured to identify an interval of time at which to store a subset of received data (e.g., event data) associated with an event)
Associate portions of the captured sensor data with the detected event (In paragraph [0017], Della discloses receiving and recording data from multiple sources. Identifies an event based on observed data deviating from expected values. Identifies an interval of time and stores a subset of the received data (event data) associated with an event.)
SULZER in view of Della are analogues pieces of art because both reference concern automated event detection system that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify SULZER, with a classification/annotation of data/labels relevant to the object of interest as taught by SULZER, with receiving event data via a communications network from an autonomous vehicle, identifying a computed vehicular drive parameter, extracting sensor data associated with the event, detecting application of control signals, analyzing the control signals, the sensor data, and the subset of computed vehicular drive parameters to identify a type of event as taught by Della. The motivation for doing so would have been to improve the performance of the detection model (See [0114] of SULZER.)
With respect to claim 1, SULZER and Della do not explicitly disclose:
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Harel to disclose:
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event (In paragraph [0254], Harel discloses generating and transmitting a lower-resolution version of a recorded video. Specifically, the system creates and stores a copy of a second video recording, compresses the copy to produce a lower-resolution version, and then streams the compressed video over a network, such as a cellular network, in real time or near real time.)
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event (In paragraph [0261], Harel discloses detecting an event, capturing high-resolution sensor data (video and optionally audio), and creating a compressed version of the high-resolution video for efficient handling or transmission.)
SULZER in view of Della and Harel are analogues pieces of art because both reference concern automated event detection system that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Harel, with receiving, in real time, data including a live recording of an environment surrounding the mobile vehicle and events occurring therein as taught by Harel. The motivation for doing so would have been to predict classification and types of objects as well as potential movements of dynamic objects (See [0073] of Della.)
Regarding claim 3, SULZER, in view of Della and Harel disclose the elements of claim 1. In addition, SULZER disclose:
The sensor platform of claim 1, wherein the processor is further configured to execute instructions stored in the memory that, when executed, cause the processors to: determine that one of the event detection models needs retraining; and retrain the event detection model (In paragraph [0085], SULZER discloses using feedback to improve an already trained model through retraining. Specifically, the system captures a video of a test situation and uses that video to retrain the existing model. The retraining may be performed using: (1) the new test video together with the existing training videos, (2) only the new test video, or (3) the new test video combined with a selected subset of the original training video. This allows the model to be refined and updated based on new data while providing flexibility in how much of the original training data is reused.)
With respect to claim 4, SULZER discloses:
A method, comprising: receiving captured sensor data at a remote location (In paragraph [0077], SULZER discloses collecting video data for training, testing, and verification of a machine learning model. The training data may be obtained from real security camera footage or simulated environments that replicate real-world conditions.)
Generating and training, at the remote location, an event detection model, the trained event detection model configured to detect an event from within the captured sensor data (In paragraph [0077], SULZER discloses collecting video data for training, testing, and verification of a machine learning model. The training data may be obtained from real security camera footage or simulated environments that replicate real-world conditions. In fig. 6 and paragraph [0105], SULZER discloses an Intelligent Video Surveillance (IVS) system that includes one or more microprocessors and memory. The IVS system analyzes real-time surveillance video and may also receive information from an environmental sensor indicating environmental conditions. Based on the detected condition, the microprocessor dynamically selects an appropriate situation-specific model (such as a neutral network) from a set of existing models and uses that selected model to perform inference, identification, or event detection on real-time surveillance video. In paragraph [0109], SALZER discloses that the process 200 and/or the functionality of the IVS System discussed above may be embodied in a non-transitory, machine-readable medium, having stored thereon a set of executable instructions to perform the process 200 and/or the functionality of the IVS System.
Applying the trained event detection model at the remote location to the captured sensor data to detect an event from within the captured sensor data (In paragraph [0106], SULZER discloses that the Intelligent Video Surveillance (IVS) system uses multiple separately trained machine-learning models for different operating conditions. One model is trained using daytime video and images, while another model is trained using nighttime infrared video and images. Before performing event detection, the system pre-processes the incoming video to determine whether it was captured during the day or night, either by using data from an environmental sensor or by analyzing characteristics of the incoming video itself.)
Transmitting captured sensor data associated with the detected event to the remote observer in response to a request from the remote observer for some or all of the sensor data associated with to the detected event (In paragraph [0073], SULZER discloses a system storing the metadata output values generated during testing and uses those values to determine the minimum and maximum threshold for triggering alerts. In an embodiment, a compound weapon detection alert may be required in order to transmit an emergency signal to, e.g., a law enforcement authority, where a compound alert is a weapon detection alert triggered based on input from two or more separate input devices (e.g., video cameras).)
With respect to claim 4, SULZER does not explicitly disclose:
Associating portions of the captured sensor data with the detected event
Transmitting notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Della to disclose
Associating portions of the captured sensor data with the detected event (In paragraph [0017], Della discloses receiving and recording data from multiple sources. Identifies an event based on observed data deviating from expected values. Identifies an interval of time and stores a subset of the received data (event data) associated with an event.)
SULZER in view of Della are analogues pieces of art because both reference concern automated event detection systems that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify SULZER, with a classification/annotation of data/labels relevant to the object of interest as taught by SULZER, with receiving event data via a communications network from an autonomous vehicle, identifying a computed vehicular drive parameter, extracting sensor data associated with the event, detecting application of control signals, analyzing the control signals, the sensor data, and the subset of computed vehicular drive parameters to identify a type of event as taught by Della. The motivation for doing so would have been to improve the performance of the detection model (See [0114] of SULZER.)
With respect to claim 4, SULZER and Della do not explicitly disclose:
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Harel to disclose:
Transmitting notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event (In paragraph [0254], Harel discloses generating and transmitting a lower-resolution version of a recorded video. Specifically, the system creates and stores a copy of a second video recording, compresses the copy to produce a lower-resolution version, and then streams the compressed video over a network, such as a cellular network, in real time or near real time.)
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event (In paragraph [0261], Harel discloses detecting an event, capturing high-resolution sensor data (video and optionally audio), and creating a compressed version of the high-resolution video for efficient handling or transmission.)
SULZER in view of Della and Harel are analogues pieces of art because both reference concern automated event detection system that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Harel, with receiving, in real time, data including a live recording of an environment surrounding the mobile vehicle and events occurring therein as taught by Harel. The motivation for doing so would have been to predict classification and types of objects as well as potential movements of dynamic objects (See [0073] of Della.)
Regarding claim 6, SULZER, in view of Della and Harel disclose the elements of claim 4. In addition, SULZER disclose:
The method of claim 4, wherein the method further comprises: determine that one of the event detection models needs retraining; and retrain the event detection model (In paragraph [0085], SULZER discloses using feedback to improve an already trained model through retraining. Specifically, the system captures a video of a test situation and uses that video to retrain the existing model. The retraining may be performed using: (1) the new test video together with the existing training videos, (2) only the new test video, or (3) the new test video combined with a selected subset of the original training video. This allows the model to be refined and updated based on new data while providing flexibility in how much of the original training data is reused.)
With respect to claim 7, SULZER discloses:
A non-transitory computer-readable storage medium comprising instructions that, when executed, cause one or more processors of a sensor platform to: receive captured sensor data (In paragraph [0077], SULZER discloses collecting video data for training, testing, and verification of a machine learning model. The training data may be obtained from real security camera footage or simulated environments that replicate real-world conditions.)
Generate and train an event detection model, the trained event detection model configured to detect an event from within the captured sensor data from the instructions (In paragraph [0077], SULZER discloses collecting video data for training, testing, and verification of a machine learning model. The training data may be obtained from real security camera footage or simulated environments that replicate real-world conditions. In fig. 6 and paragraph [0105], SULZER discloses an Intelligent Video Surveillance (IVS) system that includes one or more microprocessors and memory. The IVS system analyzes real-time surveillance video and may also receive information from an environmental sensor indicating environmental conditions. Based on the detected condition, the microprocessor dynamically selects an appropriate situation-specific model (such as a neutral network) from a set of existing models and uses that selected model to perform inference, identification, or event detection on real-time surveillance video. In paragraph [0109], SALZER discloses that the process 200 and/or the functionality of the IVS System discussed above may be embodied in a non-transitory, machine-readable medium, having stored thereon a set of executable instructions to perform the process 200 and/or the functionality of the IVS System.
Apply the trained event detection model to the captured sensor data to detect an event from within the captured sensor data (In paragraph [0106], SULZER discloses that the Intelligent Video Surveillance (IVS) system uses multiple separately trained machine-learning models for different operating conditions. One model is trained using daytime video and images, while another model is trained using nighttime infrared video and images. Before performing event detection, the system pre-processes the incoming video to determine whether it was captured during the day or night, either by using data from an environmental sensor or by analyzing characteristics of the incoming video itself.)
Transmit captured sensor data associated with the detected event to the remote observer in response to a request from the remote observer for some or all of the sensor data associated with to the detected event (In paragraph [0073], SULZER discloses a system storing the metadata output values generated during testing and uses those values to determine the minimum and maximum threshold for triggering alerts. In an embodiment, a compound weapon detection alert may be required in order to transmit an emergency signal to, e.g., a law enforcement authority, where a compound alert is a weapon detection alert triggered based on input from two or more separate input devices (e.g., video cameras).)
With respect to claim 7, SULZER does not explicitly disclose:
Associate portions of the captured sensor data with the detected event
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Della to disclose
Associate portions of the captured sensor data with the detected event (In paragraph [0017], Della discloses receiving and recording data from multiple sources. Identifies an event based on observed data deviating from expected values. Identifies an interval of time and stores a subset of the received data (event data) associated with an event.)
SULZER in view of Della are analogues pieces of art because both reference concern automated event detection systems that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify SULZER, with a classification/annotation of data/labels relevant to the object of interest as taught by SULZER, with receiving event data via a communications network from an autonomous vehicle, identifying a computed vehicular drive parameter, extracting sensor data associated with the event, detecting application of control signals, analyzing the control signals, the sensor data, and the subset of computed vehicular drive parameters to identify a type of event as taught by Della. The motivation for doing so would have been to improve the performance of the detection model (See [0114] of SULZER.)
With respect to claim 7, SULZER and Della do not explicitly disclose:
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Harel to disclose:
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event (In paragraph [0254], Harel discloses generating and transmitting a lower-resolution version of a recorded video. Specifically, the system creates and stores a copy of a second video recording, compresses the copy to produce a lower-resolution version, and then streams the compressed video over a network, such as a cellular network, in real time or near real time.)
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event (In paragraph [0261], Harel discloses detecting an event, capturing high-resolution sensor data (video and optionally audio), and creating a compressed version of the high-resolution video for efficient handling or transmission.)
SULZER in view of Della and Harel are analogues pieces of art because both reference concern automated event detection system that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Harel, with receiving, in real time, data including a live recording of an environment surrounding the mobile vehicle and events occurring therein as taught by Harel. The motivation for doing so would have been to predict classification and types of objects as well as potential movements of dynamic objects (See [0073] of Della.)
With respect to claim 9, SULZER discloses:
A sensor system, comprising: a sensor platform (In paragraph [0089], SULZER disclose the process may run on an intelligent video surveillance system (IVS System), which includes one or more microprocessors and/or a memory device. In an embodiment, the IVS System can analyze and/or detect differing environmental conditions/characteristics in real-time surveillance video. This may be accomplished, in an embodiment, by a dedicated environmental sensor that sends a signal to the microprocessor.)
An observer station remote from the sensor platform (In paragraph [0089], disclose an embodiment, the IVS System can analyze and/or detect differing environmental conditions/characteristics in real-time surveillance video.)
A communications channel connected to the sensor platform and the observer station, wherein the sensor platform includes: a memory, the memory storing instructions for generating event detection models used to detect events in the captured sensor data (In fig. 6 and paragraph [0105], SULZER discloses an Intelligent Video Surveillance (IVS) system that includes one or more microprocessors and memory. The IVS system analyzes real-time surveillance video and may also receive information from an environmental sensor indicating environmental conditions. Based on the detected condition, the microprocessor dynamically selects an appropriate situation-specific model (such as a neutral network) from a set of existing models and uses that selected model to perform inference, identification, or event detection on real-time surveillance video. In paragraph [0109], SALZER discloses that the process 200 and/or the functionality of the IVS System discussed above may be embodied in a non-transitory, machine-readable medium, having stored thereon a set of executable instructions to perform the process 200 and/or the functionality of the IVS System.)
An interface, the interface configured to receive captured sensor data and store the captured sensor data to memory (In fig. 6 and paragraph [0105], SULZER discloses that a processing system 600 may include one or more processors 610, memory 620, one or more input/output devices 630, one or more sensors 640, one or more user interfaces 650, and one or more actuators.)
One or more processors communicatively coupled to the memory, the processors configured to execute instructions stored in the memory, the instructions when executed causing the one or more processors to: generate and train an event detection model from the instructions (In paragraph [0077], SULZER discloses collecting video data for training, testing, and verification of a machine learning model. The training data may be obtained from real security camera footage or simulated environments that replicate real-world conditions.)
Apply the trained event detection model to the captured sensor data, the trained event detection model configured to detect an event from within the captured sensor data (In paragraph [0106], SULZER discloses that the Intelligent Video Surveillance (IVS) system uses multiple separately trained machine-learning models for different operating conditions. One model is trained using daytime video and images, while another model is trained using nighttime infrared video and images. Before performing event detection, the system pre-processes the incoming video to determine whether it was captured during the day or night, either by using data from an environmental sensor or by analyzing characteristics of the incoming video itself.)
Transmit captured sensor data associated with the detected event to the remote observer in response to a request from the remote observer for some or all of the sensor data associated with to the detected event (In paragraph [0073], SULZER discloses a system storing the metadata output values generated during testing and uses those values to determine the minimum and maximum threshold for triggering alerts. In an embodiment, a compound weapon detection alert may be required in order to transmit an emergency signal to, e.g., a law enforcement authority, where a compound alert is a weapon detection alert triggered based on input from two or more separate input devices (e.g., video cameras).)
With respect to claim 9, SULZER does not explicitly disclose:
Retrieve the captured sensor data from memory
Associate portions of the captured sensor data with the detected event
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Della to disclose
Retrieve the captured sensor data from memory (In paragraph [0017], Della discloses an event recorder 156 that may be configured to receive data from multiple sources, whether internal or external to an autonomous vehicle 120, and further configured to identify an interval of time at which to store a subset of received data (e.g., event data) associated with an event.)
Associate portions of the captured sensor data with the detected event (In paragraph [0017], Della discloses receiving and recording data from multiple sources. Identifies an event based on observed data deviating from expected values. Identifies an interval of time and stores a subset of the received data (event data) associated with an event.)
SULZER in view of Della are analogues pieces of art because both reference concern automated event detection systems that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify SULZER, with a classification/annotation of data/labels relevant to the object of interest as taught by SULZER, with receiving event data via a communications network from an autonomous vehicle, identifying a computed vehicular drive parameter, extracting sensor data associated with the event, detecting application of control signals, analyzing the control signals, the sensor data, and the subset of computed vehicular drive parameters to identify a type of event as taught by Della. The motivation for doing so would have been to improve the performance of the detection model (See [0114] of SULZER.)
With respect to claim 9, SULZER and Della do not explicitly disclose:
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event
However, it is known by Harel to disclose:
Transmit notice of the detected event to a remote observer, including transmitting a lower resolution version of the portions of captured sensor data associated the detected event (In paragraph [0254], Harel discloses generating and transmitting a lower-resolution version of a recorded video. Specifically, the system creates and stores a copy of a second video recording, compresses the copy to produce a lower-resolution version, and then streams the compressed video over a network, such as a cellular network, in real time or near real time.)
Wherein the captured sensor data include a higher resolution version of the portions of the captured sensor data associated with the detected event (In paragraph [0261], Harel discloses detecting an event, capturing high-resolution sensor data (video and optionally audio), and creating a compressed version of the high-resolution video for efficient handling or transmission.)
SULZER in view of Della and Harel are analogues pieces of art because both reference concern automated event detection system that analyze captured sensor data, identify events, preserve or process event related information. Accordingly, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify Harel, with receiving, in real time, data including a live recording of an environment surrounding the mobile vehicle and events occurring therein as taught by Harel. The motivation for doing so would have been to predict classification and types of objects as well as potential movements of dynamic objects (See [0073] of Della.)
Regarding claim 11, SULZER, in view of Della and Harel disclose the elements of claim 9. In addition, SULZER disclose:
The system of claim 9, wherein the one or more of the processors are further configured to execute instructions stored in the memory that, when executed, cause the processors to: determine that one of the event detection models needs retraining; and retrain the event detection model (In paragraph [0085], SULZER discloses using feedback to improve an already trained model through retraining. Specifically, the system captures a video of a test situation and uses that video to retrain the existing model. The retraining may be performed using: (1) the new test video together with the existing training videos, (2) only the new test video, or (3) the new test video combined with a selected subset of the original training video. This allows the model to be refined and updated based on new data while providing flexibility in how much of the original training data is reused.)
Regarding claim 12, SULZER, in view of Della and Harel disclose the elements of claim 9. In addition, SULZER disclose:
The system of claim 9, wherein the observer station comprises: a memory, the memory storing instructions for generating event detection models used to detect events in the captured sensor data (In fig. 6 and paragraph [0105], SULZER discloses an Intelligent Video Surveillance (IVS) system that includes one or more microprocessors and memory. The IVS system analyzes real-time surveillance video and may also receive information from an environmental sensor indicating environmental conditions. Based on the detected condition, the microprocessor dynamically selects an appropriate situation-specific model (such as a neutral network) from a set of existing models and uses that selected model to perform inference, identification, or event detection on real-time surveillance video. In paragraph [0109], SALZER discloses that the process 200 and/or the functionality of the IVS System discussed above may be embodied in a non-transitory, machine-readable medium, having stored thereon a set of executable instructions to perform the process 200 and/or the functionality of the IVS System.)
One or more processors communicatively coupled to the memory, the processors configured to execute instructions stored in the memory, the instructions when executed causing the one or more processors to: receive the notices of detected events from the sensor platform (In paragraph [0077], SULZER discloses collecting video data for training, testing, and verification of a machine learning model. The training data may be obtained from real security camera footage or simulated environments that replicate real-world conditions.)
Request sensor data corresponding to one or more of the detected events (In paragraph [0073], SULZER discloses a system storing the metadata output values generated during testing and uses those values to determine the minimum and maximum threshold for triggering alerts. In an embodiment, a compound weapon detection alert may be required in order to transmit an emergency signal to, e.g., a law enforcement authority, where a compound alert is a weapon detection alert triggered based on input from two or more separate input devices (e.g., video cameras).)
Regarding claim 13, SULZER, in view of Della and Harel disclose the elements of claim 12. In addition, Harel disclose:
The system of claim 12, wherein the observer station further comprises a user interface, the user interface configured to receive the notices of detected events and to select one or more of the detected events for review of the sensor data corresponding to the event (In paragraph [0173-0174], Harel discloses that the surveillance device 710 may also include a location sensor (e.g., a GPS receiver) that can determine the location data of the surveillance device 710 and the vehicle 702 it is installed on/with. From determining the location data of the surveillance device 710 and the vehicle 702, a location map (e.g., GPS map) of the surrounding environment/events captured in the recordings can be generated by the surveillance device and stored in local storage.)
Regarding claim 14, SULZER, in view of Della and Harel, disclose the elements of claim 13. In addition, SULZER disclose:
The system of claim 13, wherein the user interface is further configured to notify the sensor platform of the selected events (In paragraph [0073], SULZER discloses determining the minimum and maximum parameters for triggering alerts. This allows the presently disclosed systems and methods to greatly reduce false positives while also triggering real-time weapon detection alerts.)
Regarding claim 15, SULZER, in view of Della and Harel, disclose the elements of claim 13. In addition, SULZER disclose:
The system of claim 13, wherein the observer station further comprises a model tracker, the model tracker configured to enable a user to detect false positives in detected events and to notify the sensor platform of the false positives (In paragraph [0143], SULZER discloses the testing and evaluation phase for the trained weapon detection model. The trained model is provided with a standardized testing process that may also receive input from a false-positive reinforcement model.)
Regarding claim 16, SULZER, in view of Della and Harel disclose the elements of claim 13. In addition, SULZER disclose:
The system of claim 13, wherein the observer station further comprises an event prototype, wherein the event prototype is configured to enable a user to prototype new event detection models (In paragraph [0085], SALZER teaches using new test videos to retrain an existing event detection model. The retraining can use only the new test or combine it with existing training video, allowing iterative development of improved event detection models. In paragraph [0143], SALZER teaches a standardized model performance testing and evaluation process, where a trained model is tested using annotated videos, live testing, and numerous performance metrics such as true positives, false positives, false negatives. In paragraph [0072-0074], SALZER discloses teaching exporting metadata, filtering results, determining the optimal threshold, evaluating performance, and selecting the best model configuration before deployment.)
Regarding claim 17, SULZER, in view of Della and Harel disclose the elements of claim 13. In addition, SULZER disclose:
The system of claim 13, wherein the observer station further comprises a model tracker, the model tracker configured to: identify new types of interesting events in captured sensor data (In paragraph [0084], SULZER disclose the output of a video inference testing job replicates the output of real-time inference with metadata including object size, object speed, event duration, and confidence score, among other parameters.)
Label relevant time intervals as an example of the event (In paragraph [0084], SULZER discloses the output of a video inference testing job that replicates the output of real-time inference with metadata including object size, object speed, event duration, and confidence score, among other parameters.)
Wherein the sensor platform further comprises an event modeling application, the event modeling application configured to receive the labeled time intervals from the observer station and to train a new detection model based on the captured sensor data from the labeled time intervals (In paragraph [0085], SULZER discloses using a new testing video or retraining an existing model. It's focused on updating the model with new examples of the same data modality (video) rather than introducing a new form of data.)
Response to Arguments
Applicant's arguments filed on 06/10/2026 have been fully considered, and in part are persuasive.
Pertaining to Rejection under 103
Applicant’s arguments in regard to the examiner’s rejections under 35 USC 103 are moot in view of the new grounds of rejection
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EVEL HONORE whose telephone number is (703)756-1179. The examiner can normally be reached Monday-Friday 8 a.m. -5:30 p.m.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Mariela D Reyes can be reached at (571) 270-1006. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
EVEL HONORE
Examiner
Art Unit 2142
/Mariela Reyes/Supervisory Patent Examiner, Art Unit 2142
Prosecution Insights