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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 05/15/2024 have been entered and considered. Initialed copies of the PTO-1449 by the Examiner are attached.
Election/Restrictions
Claims 1-4 withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected Group 1, there being no allowable generic or linking claim. Election was made without traverse in the reply filed on April 07, 2026.
Claim Objections
Claim 1 is objected to because of the following informalities: Please write out the words for the acronym ML and place ML in brackets.
Appropriate correction is required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 of this title, 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 5-8,10-11 and 13-20 are rejected under 35 U.S.C. 103 as being unpatentable over Suresh et al (Pub No.: US20200050893) in view of Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion).
Regarding independent claim 5, Suresh teaches a method of determining maritime compliance (detect states of operation of objects for purposes of compliance with the 1972 International Regulations for Preventing Collisions at Sea (COLREGS). For example, under COLREGS and object detection network can be used to recognize various types of vessels and objects around the vessel, which can enable navigation in accordance with COLREGS – see [p][0007][0067]) comprising:
acquiring, using one or more image capture devices ([t]he method 100 may include receiving a plurality of images from a sensor system. The plurality of images may be received via stereo feeds – see [p][0071]), a raw application image (first CNN layer takes the raw image as input -see [p][0179]);
processing the raw application image to produce a processed image (the images may be created by transforming frames or parts of the stereo feed into images. Images may be produced from the devices, such as other cameras or thermal cameras, and fused into a single or multiple output disparity maps – see [p][0071]);
inputting the processed image into a trained ML network ([a]t 103, the method may further include classifying objects in the images. Classification 103 may be performed in an offline mode. A dataset can be collected by capturing images using multiple cameras attached to the ships see [p][0072] and a CNN to interpret and adjust the map based on context in the scene. In this way, the stereoscopy can be used for depth estimation or distance estimation. Two or more cameras may be used to perform stereoscopy, with appropriate lensing and inter-focal length – see [p][0085]);
predicting one or more labeled features in the processed image using the trained ML network (the images are classified using labels including, inter alia, powered boat, sailing yacht, cargo ship, cruise ship, coast guard boat, naval vessel, lock bridge, normal bridge, static far object, moving far object, icebergs, and shore – see [p][0072]);
determining, with the trained ML network, a class of each of the one or more labeled features forming a set of determined classes (different categories into which the dataset is to be labeled are described above. Given any image, the image is classified into one of the above categories. In addition, if there is an overlap between categories, classifying an image into one of the two categories is sufficient – see [p][072]);
determining, with the trained ML network, maritime compliance based, at least in part, on whether a first feature of the one or more labeled features is non-compliant based on the determined class of the first feature ([t]he method may further include determining a route feasibility, which can provide a determination of whether a path to a destination is feasible, and the route feasibility may be determined in an offline mode. The route feasibility may be determined based on a heat map. The method may further include generating a navigation policy. The navigation policy may be part of the instructions generated at 104, or may be used to generate the instructions at 104. Alternatively, generating a navigation policy may be part of determining route feasibility, or a generated navigation policy may be used to determine a route feasibility. The navigation policy may be generated in an offline mode. In an instance, a navigation policy may make a map appear infeasible if navigation is not possible. A navigation policy can keep a vessel compliant with COLREGS or other national or local navigation requirements, where applicable. Alternatively, different navigational requirements or liberties may be embedded in the navigation policy for, inter alia, navy or coast guard vessels – see [p][0098-0099]); and
Suresh does not explicitly teach generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant.
Wang explicitly teaches discloses generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant ([d]etermine the Ringerman Blackness grade of the ship emission based on the scaled ratio. A higher Ringerman Blackness grade indicates a more severe level of pollution and effectively identify vessels emitting non-compliant exhaust plumes – see section 2.3.6, step 3 and section 4, [p][001] and a purple box for level 5 – see Fig 27).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Wang generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant.
Wherein having Suresh generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel for the purposes of performing the real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness , since both Suresh and Wang relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Wang performs real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion), see Abstract).
Regarding claim 6, Suresh in view of Wang teach the method of claim 5, Suresh explicitly teaches wherein the raw application image comprises a plurality of raw application images (stereo images from sensor before stereopsis is performed – see [p][0113]).
Regarding claim 7, Suresh in view of Wang teach the method of claim 5, Suresh does explicitly teach wherein at least one of the one or more alerts comprises a visual warning.
Wang explicitly teaches wherein at least one of the one or more alerts comprises a visual warning (a purple box for level 5 – see Fig 27).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Wang wherein at least one of the one or more alerts comprises a visual warning.
Wherein having Suresh wherein at least one of the one or more alerts comprises a visual warning.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel for the purposes of performing the real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness , since both Suresh and Wang relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Wang performs real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion), see Abstract).
Regarding claim 7, Suresh in view of Wang teach the method of claim 5, Suresh does explicitly teach wherein the one or more labeled features comprises one or more maritime compliance elements.
Wang explicitly teaches wherein the one or more labeled features comprises one or more maritime compliance elements (The process of ship emission detection in this study is illustrated in Figure1.The initial step involves data augmentation and mitigation of environmental interferences for the collected raw dataset. In the second step, an enhanced YOLOv5s-CMBI network model is utilized to extract and compare the smoke regions in the data set through experimentation. The third step involves preprocessing of the processed data and image segmentation, followed by the application of the Ringelmann Blackness scale for grading the opacity levels of the smoke emissions – see section 2.1).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Wang wherein the one or more labeled features comprises one or more maritime compliance elements.
Wherein having Suresh wherein the one or more labeled features comprises one or more maritime compliance elements.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel for the purposes of performing the real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness , since both Suresh and Wang relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Wang performs real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion), see Abstract).
Regarding claim 10, Suresh in view of Wang teach teaches the method of claim 5, Suresh explicitly teaches wherein the image capture device comprises a digital still camera or a digital video camera (the image feed received from cameras – see [p][0066]).
Regarding claim 11, Suresh in view of Wang teach the method of claim 5, Suresh explicitly teaches wherein the one or more image capture devices are communicatively coupled to a trigger device (processor 202 can be configured to perform stereoscopy, generate heat maps, and/or estimate object depth – see [p][0123]), wherein an image storage component stores the processed image in response to a trigger signal (determining a route feasibility, which can provide a determination of whether a path to a destination is feasible, and the route feasibility may be determined in an offline mode. The route feasibility may be determined based on a heat map and generating a navigation policy. The navigation policy may be part of the instructions generated at 104, or may be used to generate the instructions at 104. Alternatively, generating a navigation policy may be part of determining route feasibility, or a generated navigation policy may be used to determine a route feasibility. The navigation policy may be generated in an offline mode. In an instance, a navigation policy may make a map appear infeasible if navigation is not possible. A navigation policy can keep a vessel compliant with COLREGS or other national or local navigation requirements, where applicable – see [p][0098-0099]), and
Suresh does not explicitly teach wherein the trigger signal is generated by the trigger device in response to a non-compliant feature.
Wang explicitly teaches wherein the trigger signal is generated by the trigger device in response to a non-compliant feature (for e.g purple bounding box for level 5 – see Fig 27).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Wang wherein the trigger signal is generated by the trigger device in response to a non-compliant feature.
Wherein having Suresh wherein, the trigger signal is generated by the trigger device in response to a non-compliant feature.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel for the purposes of performing the real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness , since both Suresh and Wang relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Wang performs real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion), see Abstract)
Regarding claim 13, Suresh in view of Wang teach the method of claim 5, Suresh explicitly teaches further comprising determining a closest point of approach between two or more labeled features based, at least in part, on the processed image ([t]he results that are produced by each one or more trained models for the validation data that is input to the one or more trained models may be compared to the labels assigned to the validation data to determine which of the models is the best model. For example, the model that produces results that most closely match the validation data labels may be selected as the best model. Test data may then be used for model evaluation of the model that is selected (e.g., the best model) – see [p][0151]).
Regarding claim 14, Suresh in view of Wang teach teaches the method of claim 5, Suresh explicitly teaches wherein the ML network comprises a convolutional neural network ([a]n object detection network (ODN), which can include a convolutional neural network (CNN), can be trained to identify and classify objects in a real-time offline environment – see [p][0066]).
Regarding claim 15, Suresh in view of Wang teach teaches the method of claim 5, Suresh explicitly teaches further comprising obtaining a plurality of videos from the one or more image capture devices ([t]he method 100 may include receiving a plurality of images from a sensor system. The plurality of images may be received via stereo feeds – see [p][0071] and Fig 10), wherein the image capture device comprises a time-lapse camera, a video camera (see Fig 10), or a combination thereof.
Regarding independent claim 16, Suresh a system for maritime compliance detection (detect states of operation of objects for purposes of compliance with the 1972 International Regulations for Preventing Collisions at Sea (COLREGS). For example, under COLREGS and object detection network can be used to recognize various types of vessels and objects around the vessel, which can enable navigation in accordance with COLREGS – see [p][0007][0067]), the system comprising: one or more image capture devices (the plurality of images may be received via stereo feeds – see [p][0071]) configured to acquire a raw application image (first CNN layer takes the raw image as input -see [p][0179]); and a maritime compliance detection system (processor 202 can be configured to perform stereoscopy – see [p][0123]) in communication with the image capture device (processor 202 can be configured to perform stereoscopy, generate heat maps, and/or estimate object depth – see [p][0123])), the maritime compliance detection system comprising a processor (processor 202 – see [p][0123]) and a memory (non-transitory computer readable medium – see [p][0033]), the memory storing instructions (a program – see [p][0033]) that, when executed by the processor, cause the processor to: receive a raw application image (first CNN layer takes the raw image as input -see [p][0179]);
process the raw application image to produce a processed image (the images may be created by transforming frames or parts of the stereo feed into images. Images may be produced from the devices, such as other cameras or thermal cameras, and fused into a single or multiple output disparity maps – see [p][0071]);
input the processed image into a trained ML network ([a]t 103, the method may further include classifying objects in the images. Classification 103 may be performed in an offline mode. A dataset can be collected by capturing images using multiple cameras attached to the ships see [p][0072] and a CNN to interpret and adjust the map based on context in the scene. In this way, the stereoscopy can be used for depth estimation or distance estimation. Two or more cameras may be used to perform stereoscopy, with appropriate lensing and inter-focal length – see [p][0085]);
predict one or more labeled features in the processed image using the trained ML network (the images are classified using labels including, inter alia, powered boat, sailing yacht, cargo ship, cruise ship, coast guard boat, naval vessel, lock bridge, normal bridge, static far object, moving far object, icebergs, and shore – see [p][0072]);
determine, with the trained ML network, a class of each of the one or more labeled features forming a set of determined classes (different categories into which the dataset is to be labeled are described above. Given any image, the image is classified into one of the above categories. In addition, if there is an overlap between categories, classifying an image into one of the two categories is sufficient – see [p][072]);
determine, with the trained ML network, maritime compliance based, at least in part, on whether a first feature of the one or more labeled features is non-compliant based on the determined class of the first feature ([t]he method may further include determining a route feasibility, which can provide a determination of whether a path to a destination is feasible, and the route feasibility may be determined in an offline mode. The route feasibility may be determined based on a heat map. The method may further include generating a navigation policy. The navigation policy may be part of the instructions generated at 104, or may be used to generate the instructions at 104. Alternatively, generating a navigation policy may be part of determining route feasibility, or a generated navigation policy may be used to determine a route feasibility. The navigation policy may be generated in an offline mode. In an instance, a navigation policy may make a map appear infeasible if navigation is not possible. A navigation policy can keep a vessel compliant with COLREGS or other national or local navigation requirements, where applicable. Alternatively, different navigational requirements or liberties may be embedded in the navigation policy for, inter alia, navy or coast guard vessels – see [p][0098-0099]); and
Suresh does not explicitly teach generate one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant.
Wang explicitly teaches discloses generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant ([d]etermine the Ringerman Blackness grade of the ship emission based on the scaled ratio. A higher Ringerman Blackness grade indicates a more severe level of pollution and effectively identify vessels emitting non-compliant exhaust plumes – see section 2.3.6, step 3 and section 4, [p][001] and a purple box for level 5 – see Fig 27).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Wang generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant.
Wherein having Suresh generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel for the purposes of performing the real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness , since both Suresh and Wang relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Wang performs real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion), see Abstract).
Regarding claim 17, which corresponds to claim 6 except for reciting a different statutory category of a system. Therefore, the rejection analysis of claim 6 is fully applicable to claim 17.
Regarding claim 18, which corresponds to claim 8 except for reciting a different statutory category of a system. Therefore, the rejection analysis of claim 8 is fully applicable to claim 18.
Regarding claim 19, which corresponds to claim 10 except for reciting a different statutory category of a system. Therefore, the rejection analysis of claim 10 is fully applicable to claim 19.
Regarding claim 20, which corresponds to claim 11 except for reciting a different statutory category of a non-transitory computer-readable medium. Therefore, the rejection analysis of claim 11 is fully applicable to claim 20.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Suresh et al (Pub No.: US20200050893) in view of Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion) as applied to claim 5 further in view of Guo et al (NPL titled: Low-Light Maritime Image Enhancement with Regularized Illumination Optimization and Deep Noise Suppression).
Regarding claim 9, Suresh in view of Wang teach, the method of claim 5, Suresh in view of Wang does not explicitly teach, wherein processing the raw application image comprises denoising and filtering the raw application image.
Guo explicitly teaches wherein processing the raw application image comprises denoising (blind denoising network to blindly remove the unwanted noise existed in enhanced images – see IV, subsection C, [p][001]) and filtering (guided filter – see section IV, subsection B, [p][001]) the raw application image.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh as modified by Wang of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Guo wherein processing the raw application image comprises denoising.
Wherein having Suresh wherein processing the raw application image comprises denoising.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel by enhancing the low-light images through regularized illumination optimization and deep noise suppression, since both Suresh and Wang relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Guo enhance the low-light images through regularized illumination optimization and deep noise suppression while effectively boost the details existed in reflection map by effectively boosting the details existed in reflection map (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Guo et al (NPL titled: Low-Light Maritime Image Enhancement with Regularized Illumination Optimization and Deep Noise Suppression), see Abstract and section IV, subsection B, [p][001]).
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Suresh et al (Pub No.: US20200050893) in view of Wang et al (NPL titled: Research on Black Smoke Detection and Class Evaluation Method for Ships Based on YOLOv5s-CMBI Multi-Feature Fusion) as applied to claim 5 further in view of Miller et al (Pub No.: 20210248776) in view of Zhao (NPL titled: Infrared maritime target detection based on edge dilation segmentation and multiscale local saliency of image details).
Regarding claim 12, Suresh in view of Wang teach the method of claim 5, Suresh teaches wherein processing comprises: obtaining, from the one or more image capture devices, at least one background image (receiving a background image with the water conditions, the sky conditions, and/or the light conditions – see [p][0024]);
Suresh in view of Wang does not explicitly teach subtracting the at least one background image from the raw application image to produce at least one background-subtracted image; detecting pixels where the background-subtracted image changed from the raw application image; identifying one or more object edges in the background-subtracted image.
Miller explicitly teaches subtracting the at least one background image from the raw application image to produce at least one background-subtracted image ( process the geospatial image to convert the geospatial image map 310 into an array 310 by removing background noise (e.g., using a background subtraction algorithm for image processing) – see [p][0038]); detecting pixels where the background-subtracted image changed from the raw application image (detecting the edges or boundaries 315 of the physical structure of interest 320 -see [p][0038]); identifying one or more object edges in the background-subtracted image (the edges or boundaries 315 of the physical structure of interest 320 may establish the initial or first boundary outline of the physical structure – see [p][0038]);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh in view of Wang of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Miller subtracting the at least one background image from the raw application image to produce at least one background-subtracted image; detecting pixels where the background-subtracted image changed from the raw application image; identifying one or more object edges in the background-subtracted image; and combining the one or more object edges to obtain a region of interest (ROI) in the background-subtracted image.
Wherein having Suresh subtracting the at least one background image from the raw application image to produce at least one background-subtracted image; detecting pixels where the background-subtracted image changed from the raw application image; identifying one or more object edges in the background-subtracted image; and combining the one or more object edges to obtain a region of interest (ROI) in the background-subtracted image.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel for the purposes of analyzing a geospatial image of a geographic area in order to identify locations of interest within the geospatial image, since both Suresh and Miller relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Wang performs real-time detection accuracy of ship exhaust plumes and further quantify the degree of darkness (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Miller et al (Pub No.: 20210248776), see Abstract).
Suresh in view of Wang and Miller does not explicitly teach combining the one or more object edges to obtain a region of interest (ROI) in the background-subtracted image.
Zhao explicitly teaches combining the one or more object edges to obtain a region of interest (ROI) in the background-subtracted image ([a]ccording to this feature, to obtain the complete target region and calculate the features of the target more accurately, a change rate of the dilated edge is proposed in this paper. The edge area of each suspected target is obtained by iterative dilation. The change of average intensity of the two adjacent edge area is calculated as the condition for stopping iteration. Then the whole target can be obtained – see section 3.3).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Suresh in view of Wang and Miller of a method/system of training a machine learning (ML) network comprising: obtaining a plurality of training images with the teachings of Zhao combining the one or more object edges to obtain a region of interest (ROI) in the background-subtracted image.
Wherein having Suresh combining the one or more object edges to obtain a region of interest (ROI) in the background-subtracted image.
The motivation behind the modification would have been for identifying and classifying objects in images from a sensor system disposed on a maritime vessel by performing edge dilation segmentation to obtain complete suspected target, since both Suresh and Zhao relates object detection, wherein Suresh identify and classify objects in images from a sensor system disposed on a maritime vessel while Zhao performs edge dilation segmentation to obtain complete suspected target, (Please see Suresh et al (Pub No.: US20200050893), see [p][0014] and Zhao et al (NPL titled: Infrared maritime target detection based on edge dilation segmentation and multiscale local saliency of image details), see Abstract).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Rodriguez et al (US Patent No.: 12555370) discloses a systems and methods for range estimation in autonomous maritime vehicles through use of an image processing model. The model comprises a neural network that informs the vehicle as to the ranges of real-world objects based on a diversified set of synthetic and real-world training data. During training, the model estimates the ranges of objects and/or subcomponents extracted from the training data and compares the estimated ranges with the corresponding ground truths. The system then uses the results of the comparisons to update the weights and biases in the neural network and improve the accuracy and performance of the image processing model deployed to the vehicle.
Lu et al (US Patent No.: 12482340) discloses a large ship safety supervision system, configured to realize shipmen monitoring and ship safety supervision, wherein shipmen monitoring comprising monitoring of real time positions of shipmen in cabins and shipmen health data, and ship safety supervision comprises oceanic condition warning, on board devices running condition monitoring, ship navigation/construction monitoring and ship remote guidance. Data transmission in between ships and shores is realized by the hybrid self-adaptive compression technology based on model classification and the data transmission link intelligent selection technology based on fuzzy neural network creatively, in the meanwhile, real time safety management and supervision and ship remote work analysis and guidance can be realized.
Anazi et al (Pub No.: 20250356613) discloses a method may include acquiring, using one or more image capture devices, a raw application image and processing the raw application image to produce a processed image. Using a trained machine learning network, the method further includes predicting one or more labeled features in the processed image and determining a class of each of the one or more labeled features forming a set of determined classes. The method further includes determining, with the trained machine learning network, maritime compliance based, at least in part, on whether a first feature of the one or more labeled features is non-compliant based on the determined class of the first feature, and generating one or more alerts regarding maritime compliance based on a determination that the first feature is non-compliant.
Patterson et al (US Patent No.: 12345833) discloses a field of awareness (FOA) system provides an operator of a vessel with intuitive object detection and positioning information. The system may comprise an FOA cloud server and an FOA unit. The FOA cloud server may be configured to perform a machine learning training operation to modify an FOA model based on a location-based relationship between training radar data and truth data. The FOA unit may be disposed on the vessel and may comprise processing circuitry configured to apply radar data to the FOA model to perform a comparison to determine a matched model signature, an associated matched object type, and an icon representation for the object of interest. The processing circuitry also be configured to control the display device to render the icon representation of the object at a position relative to a representation of the vessel based on the relative object position.
Park et al (US Patent No.: 12057018 ) discloses a method by which a computing means monitors a harbor, and a harbor monitoring method, according to one aspect of the present invention, comprises the steps of: acquiring a harbor image; generating a segmentation image corresponding to the harbor image; generating a display image corresponding to the harbor image and having a first view attribute; generating a conversion segmentation image, which corresponds to the segmentation image and has a second view attribute different from the first view attribute; matching the display image so as to generate a panoramic image; matching the conversion segmentation image so as to generate a matching segmentation image; calculating ship mooring guide information on the basis of the matching segmentation image; and outputting the mooring guide information together with the panoramic image.
Im et al (US Patent No.: 11521497) discloses a method and a system for recognition of objects near a ship by using a deep neural network to prevent a collision with the object by recognizing a neighboring object that may be risky to the ship sailing in a restricted condition such as a foggy environment. All object movements within a predetermined radius are detected and recognized so that collision accidents with objects on the sea in an environment such as fog caused by bad weather at sea can be prevented, and a risk alarm is notified to a captain when the object is detected so that collision accidents can be remarkably reduced. In addition, peripheral environments are detected by only installing a CCTV camera so that expenses can be reduced, human negligence can be prevented, and the system can be easily constructed to prevent collisions.
Park et al (US Patent No.: 11314990) discloses a method for acquiring an object information, the method comprising: obtaining an input image acquired by capturing a sea; obtaining a noise level of the input image; when the noise level indicates a noise lower than a predetermined level, acquiring an object information related to an obstacle included in the input image from the input image by using a first artificial neural network, and when the noise level indicates a noise higher than the predetermined level, obtaining a noise-reduced image of which the environmental noise is reduced from the input image by using a second artificial neural network, and acquiring an object information related to an obstacle included in the sea from the noise-reduced image by using the first artificial neural network.
SURESH et al (Pub No.: 20200050202) discloses systems, methods, and apparatuses for deep learning and intelligent sensing system integrations. A processor may be configured to receive a plurality of images from the sensor system, identify objects in the images in an offline mode, classify the objects in the images in the offline mode, generate heat maps in the offline mode, and send instructions regarding operation of the maritime vessel based on the objects that are identified. The visual sensor may be a stereoscopic camera. The processor may be further configured to perform stereoscopy. The instructions may include a speed or a heading of, for example, a maritime vessel.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDRAE S ALLISON whose telephone number is (571)270-1052. The examiner can normally be reached on Monday-Friday 9am-5pm 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, Chineyere Wills-Burns, can be reached on (571) 272-9752. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ANDRAE S ALLISON/Primary Examiner, Art Unit 2673
June 5, 2026
Prosecution Insights