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 .
Priority
Receipt is acknowledged that application claims priority to foreign application with application number KR10-2023-0151054 dated 11/03/2023. Copies of certified papers required by 37 CFR 1.55 have been received. Priority is acknowledged under 35 USC 119(e) and 37 CFR 1.78.
Response to Amendment
The amendment filed 07/10/2026 has been entered. Applicant’s amendments to the specification and claims have overcome each and every objection and 35 U.S.C. 101 rejection previously set forth in the Non-Final Office Action mailed 04/16/2026. Claims 1-5, 8, 10-14, and 17-23 remain pending in the application, with claims 6, 7, 9, 15, and 16 having been cancelled and claims 21-23 being newly added.
Response to Arguments
Applicant's arguments, in the Remarks filed 07/10/2026, have been fully considered but they are not persuasive. Regarding independent claims 1, 10, and 18, Applicant argues “In Al Faruque, branch selection must occur before any results can start being generated…” Examiner agrees (i.e., para 76: “branches (where k is configurable) are selected for execution”). However, the amended claims still lack sufficient detail to exclude all possible scenarios executed by Al Faruque’s disclosed method.
In the invention disclosed by Al Faruque, in determining a target feature-type among a plurality of feature-types, the first, second, and third feature-types may be selected by the feature-type selection model (the gate module). In this case, the target feature-type is determined by multiple feature-types. For example, in the flowchart shown in Figure 2, if three branches including (1) A, (2) B, and (3) A+B are selected by the gate module, the three object detection models described in claim 1 are executed. In the last step, the final detection result of Al Faruque is based on the determination that all three object detection results are utilized as a final result based on the target feature-type determined by the gate module.
Applicant argues further that “In Al Faruque, only branches that contribute to a final fused object detection result are activated, and all of the activated branches contribute to the final fused object detection result.” Applicant agrees; however, the current claim language (claims 21-23) states that whichever of the object detection results are not selected as the final object detection result are discarded and not used. If all object detection results are selected, then no object detection results are discarded/not used, as demonstrated in Al Faruque’s example. Therefore, the example described above may still apply to claims 21-23.
In view of the foregoing, Applicant’s arguments are not persuasive and the amended claims do not overcome Al Faruque’s disclosed invention.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 3-5, 8, 10, 12-14, 17, and 21-22 are rejected under 35 U.S.C. 102(a)(1) and (a)(2) as being anticipated by Al Faruque et al. (U.S. Patent No. 2024/0062519 A1), hereinafter Al Faruque.
Regarding claim 1, Al Faruque teaches an object detection method comprising:
obtaining first-sensor data from a first sensor and obtaining second-sensor data from a second sensor, wherein the first sensor is a different type of sensor than the second sensor (Al Faruque, camera and lidar sensor data, para 59: “the plurality of sensors (100) may comprise a camera, a radar sensor, a lidar sensor, or a combination thereof”; para 75: “As shown in FIG. 2, the present invention accepts any number of sensors and sensing modalities as input”);
extracting a first feature from the first-sensor data and extracting a second feature from the second-sensor data (Al Faruque, features from each sensor, para 75: “Each stem is implemented as a CNN, which generates an initial set of spatial features for each sensor…Thus, there will be three stems if the implementation uses the camera, radar, and lidar sensors”; Features F in FIG. 2, attached below);
generating a third feature by synthesizing or combining the first feature with the second feature (Al Faruque, fusion (para 58) of camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations.”; see FIG. 2 wherein after target feature-types are determined, features may be fused, or combined);
inferring a first object detection result, by a first object detection model, from the first feature (Al Faruque, object detection results from a singular sensor input branch with no fusion, i.e., camera sensor branch, para 65: “Each branch can be configured to process either a single sensor or a set of sensors. Using the gate to select the branches, the model can dynamically choose between no fusion, early fusion, late fusion, and various combinations of the three”; para 58: “generating, based on each object detection model of the one or more branches, one or more detections corresponding to the one or more optimally-performing branches”; see para 81 and 128 regarding singular sensor input);
inferring a second object detection result, by a second object detection model, from the second feature (Al Faruque, object detection results from a singular sensor input branch with no fusion, i.e., lidar sensor branch; object detection results from all branches are options for selection, model may select more than one optimally performing branches (para 58), including those corresponding to singular sensor input (para 81 and 128));
inferring a third object detection result, by a third object detection model, from the third feature (Al Faruque, a fusion branch (para 58) of camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations. These pairings can enforce early fusion in the model by combining the stem features of heterogeneous sensor inputs”; see FIG. 2 wherein branches may include combinations of sensor features);
determining a target feature-type among a first feature-type, a second feature-type and a third feature-type by inputting the first feature and the second feature to a feature-type selection model (Al Faruque, gate module, para 75: “After the input from each sensor for a given modality is passed through the stem, the gate module uses the resulting features to identify the context and select which branches to execute”; para 86: “The model can: (i) adapt between using no fusion, early fusion, and late fusion, (ii) select from one or more radar, lidar, or camera sensor inputs”; see also para 68 and FIG. 2 wherein multiple branches representing the feature-types may be selected, including those representing fusions) which, based thereon, predicts the target feature-type (Al Faruque, feature types selected for execution and detection fusion, para 76: “The goal of the gate module is to rank the branches based on their expected performance for the input set of stem features. Next, the top-k branches (where k is configurable) are selected for execution and fusion to maximize object detection performance”); and
determining which of the first object detection result, the second object detection result and the third object detection result to use as a final object detection result based on the determined target feature-type (Al Faruque, use of all three object detection results in a case when at least k=3 branches are selected including the three object detection models inferred above – see para 76 citation above and final detections in FIG. 2).
PNG
media_image1.png
382
404
media_image1.png
Greyscale
Regarding claim 3 (dependent on claim 1), Al Faruque teaches wherein the first object detection model is configured for inputs of the first feature-type and not the second feature-type, the second object detection model is configured for inputs of the second feature-type and not the first feature-type (Al Faruque, object detection using only camera features or only lidar features – both scenarios described as “no fusion” (para 65) of one detection branch where the optimally-performing branch (para 58) is a singular sensor input (para 81); para 45: “The term “object detection model” is defined herein as a machine learning model configured to identify objects in a certain context based on sensor output”; para 128 also provides an example where no fusion involves one sensor type), and the third object detection model is configured for inputs of the third feature-type, which corresponds to a combination of the first feature-type and the second feature-type (Al Faruque, object detection using a branch (para 58) that combines, for example, camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations. These pairings can enforce early fusion in the model by combining the stem features of heterogeneous sensor inputs”; see para 45 citation above wherein the object detection models are configured for a certain sensor output, in this case, that of a sensor fusion combination).
Regarding claim 4 (dependent on claim 1), Al Faruque teaches wherein the feature-type selection model is configured to, based on the first feature that is input to the feature-type selection model and the second feature that is input to the feature-type selection model (Al Faruque, selection is based on the inputted features from sensors, see para 75 and FIG. 2), output probability values of the first feature-type, the second feature-type and the third feature-type, respectively (Al Faruque, expected performance for each feature type, or branch, para 68: the goal of the machine learning model is to model the expected performance of each branch configuration for a set of stem features… performance of each branch configuration is estimated”; see also para 76), the first feature-type corresponding to object detection corresponding to the first feature and not the second feature, and the second feature-type corresponding to object detection corresponding to the second feature and not the first feature, and the third feature-type corresponding to object detection corresponding to a fusion of the first feature and second feature (Al Faruque, see claim 1 rejection describing no fusion single sensor branches and fusion branches; para 45: “The term “object detection model” is defined herein as a machine learning model configured to identify objects in a certain context based on sensor output”).
Regarding claim 5 (dependent on claim 4), Al Faruque teaches further comprising selecting, as the target feature-type, from among the first feature-type, the second feature-type, and the third feature-type, whichever has the greatest among the probability values (Al Faruque, top ranked branches out of possible configurations, the first through third feature-types being among them, are selected, para 76: “The goal of the gate module is to rank the branches based on their expected performance for the input set of stem features. Next, the top-k branches (where k is configurable) are selected for execution and fusion to maximize object detection performance”).
Regarding claim 8 (dependent on claim 1), Al Faruque teaches wherein the determining which of the first object detection result, the second object detection result and the third object detection result to use as the final object detection result comprises determining which of the first object detection result, the second object detection result and the third object detection result has a feature-type that matches the target feature-type (Al Faruque, see input of gate-selected branches to the final detection in FIG. 2, para 56: “generate a final fusion of the one or more detections corresponding to the one or more optimally-performing branches and determining, based on the final fusion, one or more objects relative to the multi-sensor computer system”).
Regarding claim 10, Al Faruque teaches an object detection apparatus comprising:
one or more processors (Al Faruque, processor of para 55); and
a memory storing instructions configured to cause the one or more processors (Al Faruque, memory component and computer readable instructions of para 55) to:
obtain first-sensor data from a first sensor and obtain second-sensor data from a second sensor that is a different type of sensor than the first sensor (Al Faruque, camera and lidar sensor data, para 59: “the plurality of sensors (100) may comprise a camera, a radar sensor, a lidar sensor, or a combination thereof”; para 75: “As shown in FIG. 2, the present invention accepts any number of sensors and sensing modalities as input”);
extract a first feature from the first-sensor data but not from the second-sensor data, and extract a second feature from the second-sensor data but not from the first-sensor data (Al Faruque, features from each individual sensor, para 75: “Each stem is implemented as a CNN, which generates an initial set of spatial features for each sensor…Thus, there will be three stems if the implementation uses the camera, radar, and lidar sensors”; Features F in FIG. 2 stem from each type of sensor data and not from another sensor);
generate a third feature by synthesizing or combining the first feature with the second feature (Al Faruque, fusion (para 58) of camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations.”; see FIG. 2 wherein after target feature-types are determined, features may be fused, or combined);
infer a first object detection result, by a first object detection model, from the first feature (Al Faruque, object detection results from a singular sensor input branch with no fusion, i.e., camera sensor branch, para 65: “Each branch can be configured to process either a single sensor or a set of sensors. Using the gate to select the branches, the model can dynamically choose between no fusion, early fusion, late fusion, and various combinations of the three”; para 58: “generating, based on each object detection model of the one or more branches, one or more detections corresponding to the one or more optimally-performing branches”; see para 81 and 128 regarding singular sensor input);
infer a second object detection result, by a second object detection model, from the second feature (Al Faruque, object detection results from a singular sensor input branch with no fusion, i.e., lidar sensor branch; object detection results from all branches are options for selection, model may select more than one optimally performing branches (para 58), including those corresponding to singular sensor input (para 81 and 128));
infer a third object detection result, by a third object detection model, from the third feature (Al Faruque, a fusion branch (para 58) of camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations. These pairings can enforce early fusion in the model by combining the stem features of heterogeneous sensor inputs”; see FIG. 2 wherein branches may include combinations of sensor features and claim 18 rejection wherein each branch comprises an object detection model);
determine a target feature-type among a first feature-type, a second feature-type and a third feature-type by inputting the first feature and the second feature to a feature-type selection model (Al Faruque, gate module, para 75: “After the input from each sensor for a given modality is passed through the stem, the gate module uses the resulting features to identify the context and select which branches to execute”; para 86: “The model can: (i) adapt between using no fusion, early fusion, and late fusion, (ii) select from one or more radar, lidar, or camera sensor inputs”; see also para 68 and FIG. 2 wherein multiple branches representing the feature-types may be selected, including those representing fusions) which, based thereon, predicts the target feature-type (Al Faruque, feature types selected for execution and detection fusion, para 76: “The goal of the gate module is to rank the branches based on their expected performance for the input set of stem features. Next, the top-k branches (where k is configurable) are selected for execution and fusion to maximize object detection performance”); and
determine which of the first object detection result, the second object detection result and the third object detection result to use as a final object detection result based on the determined target feature-type (Al Faruque, use of all three object detection results in a case when at least k=3 branches are selected including the three object detection models inferred above – see para 76 citation above and final detections in FIG. 2).
Regarding claim 12 (dependent on claim 10), Al Faruque teaches wherein the first object detection model is configured for inputs of the first feature-type and not the second feature-type, the second object detection model is configured for inputs of the second feature-type and not the first feature-type (Al Faruque, object detection using only camera features or only lidar features – both scenarios described as “no fusion” (para 65) of one detection branch where the optimally-performing branch (para 58) is a singular sensor input (para 81); para 45: “The term “object detection model” is defined herein as a machine learning model configured to identify objects in a certain context based on sensor output”; para 128 also provides an example where no fusion involves one sensor type), and the third object detection model is configured for inputs of the third feature-type, which corresponds to a combination of the first feature-type and the second feature-type (Al Faruque, object detection using a branch (para 58) that combines, for example, camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations. These pairings can enforce early fusion in the model by combining the stem features of heterogeneous sensor inputs”; see para 45 citation above wherein the object detection models are configured for a certain sensor output, in this case, that of a sensor fusion combination).
Regarding claim 13 (dependent on claim 10), Al Faruque teaches wherein the feature-type selection model is configured to, based on the first feature that is input to the feature-type selection model and the second feature that is input to the feature-type selection model (Al Faruque, selection is based on the inputted features from sensors, see para 75 and FIG. 2), output probability values of the first feature-type, the second feature-type and the third feature-type, respectively (Al Faruque, expected performance for each feature type, or branch, para 68: the goal of the machine learning model is to model the expected performance of each branch configuration for a set of stem features… performance of each branch configuration is estimated”; see also para 76), the first feature-type corresponding to object detection corresponding to the first feature and not the second feature, and the second feature-type corresponding to object detection corresponding to the second feature and not the first feature, and the third feature-type corresponding to object detection corresponding to a fusion of the first feature and second feature (Al Faruque, see claim 1 rejection describing no fusion single sensor branches and fusion branches; para 45: “The term “object detection model” is defined herein as a machine learning model configured to identify objects in a certain context based on sensor output”).
Regarding claim 14 (dependent on claim 13), Al Faruque teaches wherein the instructions are further configured to cause the one or more processors to select, as the target feature-type, from among the first feature-type, the second feature-type and the third feature-type, whichever has the greatest among the probability values (Al Faruque, top ranked branches out of possible configurations, the first through third feature-types being among them, are selected, para 76: “The goal of the gate module is to rank the branches based on their expected performance for the input set of stem features. Next, the top-k branches (where k is configurable) are selected for execution and fusion to maximize object detection performance”).
Regarding claim 17 (dependent on claim 10), Al Faruque teaches wherein the determining which of the first object detection result, the second object detection result and the third object detection result to use as the final object detection result comprises determining which of the first object detection result, the second object detection result and the third object detection result has a feature-type that matches the target feature-type (Al Faruque, see input of gate-selected branches to the final detection in FIG. 2, para 56: “generate a final fusion of the one or more detections corresponding to the one or more optimally-performing branches and determining, based on the final fusion, one or more objects relative to the multi-sensor computer system”).
Regarding claim 21 (dependent on claim 1), Al Faruque teaches wherein whichever of the first object detection result, the second object detection result and the third object detection result are not selected as the final object detection result are discarded and not used for the final object detection result (In the example described by Al Faruque in claim 1, all object detection results are selected.).
Regarding claim 22 (dependent on claim 10), Al Faruque teaches wherein whichever of the first object detection result, the second object detection result and the third object detection result are not selected as the final object detection result are discarded and not used for the final object detection result (In the example described by Al Faruque in claim 10, all object detection results are selected.).
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 2, 11, 18-20, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Al Faruque in view of Tian et al. (CN Patent No. 117975436 A), hereinafter Tian.
Regarding claim 2 (dependent on claim 1), Al Faruque teaches wherein the first sensor is an image capturing device configured to output image data as the first-sensor data (Al Faruque, camera of para 59), and the second sensor is a light detection and ranging (LiDAR) or RADAR sensor (Al Faruque, lidar of para 59), but fails to explicitly teach wherein the second sensor is configured to output point cloud data as the second-sensor data.
However, Tian teaches a similar method (Tian, pg. 6, para n0005: “This method employs heterogeneous data from multiple sensors to achieve feature-level fusion in a 3D target detection algorithm”) in a vehicle (Tian, FIG. 9, pg. 44-45) wherein lidar point cloud data is collected and used in the method (Tian, pg. 15, para n0022). Al Faruque discloses a base method for collecting lidar data for object detection, but does not specify outputting point cloud data. Tian teaches a method for collecting lidar data for object detection, further teaching a known technique of outputting point cloud data from a lidar sensor. A person having ordinary skill in the art, before the effective filing date of the claimed invention, could have applied the known technique, as taught by Tian, in the same way to the method of Al Faruque and achieved predictable results of capturing 3D data of the environment surrounding a vehicle to improve object detection results.
Regarding claim 11 (dependent on claim 10), Al Faruque teaches wherein the first sensor is an image capturing device configured to output image data as the first sensor data (Al Faruque, camera of para 59), and the second sensor is a light detection and ranging (LiDAR) or RADAR sensor (Al Faruque, lidar of para 59), but fails to explicitly teach wherein the second sensor is configured to output point cloud data as the second sensor data.
However, Tian teaches a similar method (Tian, pg. 6, para n0005: “This method employs heterogeneous data from multiple sensors to achieve feature-level fusion in a 3D target detection algorithm”) in a vehicle apparatus (Tian, FIG. 9, pg. 44-45) wherein lidar point cloud data is collected and used in the method (Tian, pg. 15, para n0022). Al Faruque discloses a base method for collecting lidar data for object detection, but does not specify outputting point cloud data. Tian teaches a method for collecting lidar data for object detection, further teaching a known technique of outputting point cloud data from a lidar sensor. A person having ordinary skill in the art, before the effective filing date of the claimed invention, could have applied the known technique, as taught by Tian, in the same way to the method of the apparatus of Al Faruque and achieved predictable results of capturing 3D data of the environment surrounding a vehicle to improve object detection results.
Regarding claim 18, Al Faruque teaches a vehicle system (Al Faruque, autonomous car example described in para 53-54) comprising:
a first sensor configured to obtain image data capturing an area near a vehicle (Al Faruque, camera of para 59);
a second sensor configured to radiate electromagnetic energy in the area near the vehicle and obtain data based on a reflection of the electromagnetic energy from an object in the area (Al Faruque, lidar sensor of para 59); and
one or more processors (Al Faruque, processor of para 55) configured to detect the object based on the image data and the data by:
extracting a first feature from the image data and extracting a second feature from the data (Al Faruque, features from each sensor, para 75: “Each stem is implemented as a CNN, which generates an initial set of spatial features for each sensor…Thus, there will be three stems if the implementation uses the camera, radar, and lidar sensors”; Features F in FIG. 2, attached below);
generating a third feature by synthesizing or combining the first feature with the second feature (Al Faruque, fusion (para 58) of camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations.”; see FIG. 2 wherein after target feature-types are determined, features may be fused, or combined);
performing a first inference, by a first object detection model, on the first feature but not on the second feature, to generate a first object detection result (Al Faruque, object detection results from a singular sensor input branch with no fusion, i.e., camera sensor branch, para 65: “Each branch can be configured to process either a single sensor or a set of sensors. Using the gate to select the branches, the model can dynamically choose between no fusion, early fusion, late fusion, and various combinations of the three”; para 58: “generating, based on each object detection model of the one or more branches, one or more detections corresponding to the one or more optimally-performing branches”; see para 81 and 128 regarding singular sensor input);
performing a second inference, by a second object detection model, on the second feature but not the first feature, to generate a second object detection result (Al Faruque, object detection results from a singular sensor input branch with no fusion, i.e., lidar sensor branch; object detection results from all branches are options for selection, model may select more than one optimally performing branches (para 58), including those corresponding to singular sensor input (para 81 and 128));
performing a third inference, by a third object detection model, on a fusion of the first feature and second feature, to generate a third object detection result (Al Faruque, a fusion branch (para 58) of camera and lidar features, para 81: “The branches of the proposed framework are designed to be specific to different sensor fusion combinations. These pairings can enforce early fusion in the model by combining the stem features of heterogeneous sensor inputs”; see FIG. 2 wherein branches may include combinations of sensor features and claim 18 rejection wherein each branch comprises an object detection model);
inputting the first feature with the second feature to a selection model (Al Faruque, gate module, para 75: “After the input from each sensor for a given modality is passed through the stem, the gate module uses the resulting features to identify the context and select which branches to execute”; para 86: “The model can: (i) adapt between using no fusion, early fusion, and late fusion, (ii) select from one or more radar, lidar, or camera sensor inputs”; see also para 68 and FIG. 2 wherein multiple branches representing the feature-types may be selected, including those representing fusions), the selection model inferring a target feature-type from the first feature and the second feature (Al Faruque, feature types selected for execution and detection fusion, para 76: “The goal of the gate module is to rank the branches based on their expected performance for the input set of stem features. Next, the top-k branches (where k is configurable) are selected for execution and fusion to maximize object detection performance”); and
determining which of the first object detection result, the second object detection result and the third object detection result to use as a final object detection result corresponding to the object based on the inferred target feature-type (Al Faruque, use of all three object detection results in a case when at least k=3 branches are selected including the three object detection models inferred above – see para 76 citation above and final detections in FIG. 2).
However, Al Faruque fails to explicitly teach wherein the second sensor data is point cloud data. Tian teaches a similar method (Tian, pg. 6, para n0005: “This method employs heterogeneous data from multiple sensors to achieve feature-level fusion in a 3D target detection algorithm”) in a vehicle system (Tian, FIG. 9, pg. 44-45) wherein lidar point cloud data is collected and used in the method (Tian, pg. 15, para n0022). Al Faruque discloses a base method for collecting lidar data for object detection, but does not specify outputting point cloud data. Tian teaches a method for collecting lidar data for object detection, further teaching a known technique of outputting point cloud data from a lidar sensor. A person having ordinary skill in the art, before the effective filing date of the claimed invention, could have applied the known technique, as taught by Tian, in the same way to the method of the system of Al Faruque and achieved predictable results of capturing 3D data of the environment surrounding a vehicle to improve object detection results.
Regarding claim 19 (dependent on claim 18), Al Faruque in view of Tian teaches wherein an output of the selection model comprises a first probability value corresponding to the first object detection model, a second probability value corresponding to the second object detection model and a third probability value corresponding to the third object detection model (Al Faruque, expected object detection performance for each feature type, or branch, para 68: the goal of the machine learning model is to model the expected performance of each branch configuration for a set of stem features… performance of each branch configuration is estimated”; see also para 76), and wherein whichever of the first, the second and the third object detection results' object detection model has the higher probability value is selected as the final object detection result (Al Faruque, top ranked branches out of possible configurations, the first through third feature-types being among them, are selected, para 76: “The goal of the gate module is to rank the branches based on their expected performance for the input set of stem features. Next, the top-k branches (where k is configurable) are selected for execution and fusion to maximize object detection performance”).
Regarding claim 20 (dependent on claim 18), Al Faruque in view of Tian teaches wherein determining which of the first object detection result, the second object detection result and the third object detection result to use as the final object detection result comprises determining which of the first object detection result, the second object detection result and the third object detection result has a feature-type that matches the target feature-type (Al Faruque, see input of gate-selected branches to the final detection in FIG. 2, para 56: “generate a final fusion of the one or more detections corresponding to the one or more optimally-performing branches and determining, based on the final fusion, one or more objects relative to the multi-sensor computer system”).
Regarding claim 23 (dependent on claim 18), Al Faruque in view of Tian teaches wherein whichever of the first object detection result, the second object detection result and the third object detection result are not selected as the final object detection result are discarded and not used for the final object detection result (In the example described by Al Faruque in claim 18, all object detection results are selected.).
Conclusion
THIS ACTION IS MADE FINAL. 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 EMMA E DRYDEN whose telephone number is (571)272-1179. The examiner can normally be reached M-F 9-5 EST.
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, ANDREW BEE can be reached at (571) 270-5183. 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.
/EMMA E DRYDEN/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights