Patents by Inventor Zuoguan Wang
Zuoguan Wang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11972617Abstract: A method of hybrid lane modeling, including, receiving a roadway image, extracting a set of lane points from the roadway image, fitting a polynomial line to the set of lane points, determining a fitted error of the fitted polynomial line, outputting the polynomial line if the fitted error is less than a predetermined threshold, selecting a set of clean lane points from the set of lane points if the fitted error is greater than the predetermined threshold and interpolating a cubic spline line to the set of clean lane points.Type: GrantFiled: June 16, 2021Date of Patent: April 30, 2024Assignee: Sesame Technologies Inc.Inventors: Liying Liu, Zuoguan Wang, Qun Gu
-
Publication number: 20230267701Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.Type: ApplicationFiled: May 1, 2023Publication date: August 24, 2023Inventors: Yifang Xu, Xin Liu, Chia-Chin Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz
-
Patent number: 11676364Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.Type: GrantFiled: April 5, 2021Date of Patent: June 13, 2023Assignee: NVIDIA CorporationInventors: Yifang Xu, Xin Liu, Chia-Chih Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz
-
Patent number: 11625607Abstract: A method of pruning a convolutional neural network, comprising at least one of determining a number of channels (N) between a network input and a network output, constructing N lookup tables, each lookup table matched to a respective channel and pruning filters in the convolutional neural network to create a shortcut between the network input and the network output based on the N lookup tables.Type: GrantFiled: February 27, 2019Date of Patent: April 11, 2023Assignee: BLACK SESAME TECHNOLOGIES INC.Inventors: Zuoguan Wang, Yilin Song, Qun Gu
-
Publication number: 20220405515Abstract: A method of hybrid lane modeling, including, receiving a roadway image, extracting a set of lane points from the roadway image, fitting a polynomial line to the set of lane points, determining a fitted error of the fitted polynomial line, outputting the polynomial line if the fitted error is less than a predetermined threshold, selecting a set of clean lane points from the set of lane points if the fitted error is greater than the predetermined threshold and interpolating a cubic spline line to the set of clean lane points.Type: ApplicationFiled: June 16, 2021Publication date: December 22, 2022Inventors: Liying Liu, Zuoguan Wang, Qun Gu
-
Patent number: 11507823Abstract: A method of adaptive quantization for a convolutional neural network, includes at least one of receiving an acceptable model accuracy, determining a float value multiply accumulate for the layer based on a float value weight and a float value input, quantizing the float value weight at multiple weight quantization precisions, quantizing the float value input at multiple input quantization precisions, determining a multiply accumulate at multiple multiply accumulate quantization precisions based on the weight quantization precisions and the input quantization precisions, determining multiple quantization errors based on differences between the float value multiply accumulate and the multiple multiply accumulate quantization precisions and selecting one of the multiple weight quantization precisions, one of the multiple input quantization precisions and one of the multiple multiply accumulate quantization precisions based on the predetermined acceptable model accuracy and the multiple quantization errors.Type: GrantFiled: April 10, 2019Date of Patent: November 22, 2022Assignee: Black Sesame Technologies Inc.Inventors: Zuoguan Wang, Tian Zhou, Qun Gu
-
Patent number: 11490064Abstract: A method of depth estimation utilizing heterogeneous cameras, comprising, homogenizing a first camera image and a second camera image based on a first camera calibration dataset and a second camera calibration dataset respectively, wherein the first camera image and second camera image are distortion corrected and are zoom compensated, determining an initial image pair rectification transformation matrix of the homogenized first camera image and the homogenized second camera image, determining a delta image pair rectification transformation matrix based on the initial image pair rectification transformation matrix, determining, a final image pair rectification transformation matrix based on the initial image pair rectification transformation matrix and the delta image pair rectification transformation matrix resulting in a final rectified image pair and disparity mapping the final rectified image pair based on a depth net regression.Type: GrantFiled: June 8, 2021Date of Patent: November 1, 2022Assignee: Black Sesame Technologies Inc.Inventors: Zuoguan Wang, Jizhang Shan
-
Publication number: 20220114413Abstract: An example fused convolutional layer, comprising, a comparator capable of reception of a first zero point and a multiply-accumulation result, a first multiplexer coupled to the comparator, wherein the first multiplexer receives a plurality of power-of-two exponent values, a shift normalizer, coupled to the first multiplexer, wherein the shift normalizer is capable of receiving the multiply-accumulation result and the plurality of power-of-two exponent values, wherein the shift normalizer limits a quantization of the multiply-accumulation result to a power-of-two scale and a second multiplexer coupled to an output of the shift normalizer, the first multiplexer and receives a second zero point and outputs an activation.Type: ApplicationFiled: October 12, 2020Publication date: April 14, 2022Inventors: Zheng Qi, Qun Gu, Zheng Li, Chenghao Zhang, Tian Zhou, Zuoguan Wang
-
Patent number: 11281915Abstract: A method of partial frame perception, comprising receiving a bottom portion of an inverted image, detecting traffic areas of interest in the bottom portion of the inverted image, streaming the detected traffic areas of interest to a perception processor, receiving a top portion of the inverted image, detecting stationary areas of interest in the top portion of the inverted image and streaming the detected stationary areas of interest to the perception processor.Type: GrantFiled: December 6, 2019Date of Patent: March 22, 2022Assignee: BLACK SESAME TECHNOLOGIES INC.Inventors: Yuekun Zhang, Zuoguan Wang, Jizhang Shan, Ying Zhou
-
Publication number: 20220021861Abstract: A method of depth estimation utilizing heterogeneous cameras, comprising, homogenizing a first camera image and a second camera image based on a first camera calibration dataset and a second camera calibration dataset respectively, wherein the first camera image and second camera image are distortion corrected and are zoom compensated, determining an initial image pair rectification transformation matrix of the homogenized first camera image and the homogenized second camera image, determining a delta image pair rectification transformation matrix based on the initial image pair rectification transformation matrix, determining, a final image pair rectification transformation matrix based on the initial image pair rectification transformation matrix and the delta image pair rectification transformation matrix resulting in a final rectified image pair and disparity mapping the final rectified image pair based on a depth net regression.Type: ApplicationFiled: June 8, 2021Publication date: January 20, 2022Inventors: Zuoguan Wang, Jizhang Shan
-
Patent number: 11122248Abstract: A method of depth estimation utilizing heterogeneous cameras, comprising, homogenizing a first camera image and a second camera image based on a first camera calibration dataset and a second camera calibration dataset respectively, wherein the first camera image and second camera image are distortion corrected and are zoom compensated, determining an initial image pair rectification transformation matrix of the homogenized first camera image and the homogenized second camera image, determining a delta image pair rectification transformation matrix based on the initial image pair rectification transformation matrix, determining a final image pair rectification transformation matrix based on the initial image pair rectification transformation matrix and the delta image pair rectification transformation matrix resulting in a final rectified image pair and disparity mapping the final rectified image pair based on a depth net regression.Type: GrantFiled: July 20, 2020Date of Patent: September 14, 2021Assignee: Black Sesame International Holding LimitedInventors: Zuoguan Wang, Jizhang Shan
-
Publication number: 20210224556Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.Type: ApplicationFiled: April 5, 2021Publication date: July 22, 2021Inventors: Yifang Xu, Xin Liu, Chia-Chih Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz
-
Publication number: 20210174096Abstract: A method of partial frame perception, comprising receiving a bottom portion of an inverted image, detecting traffic areas of interest in the bottom portion of the inverted image, streaming the detected traffic areas of interest to a perception processor, receiving a top portion of the inverted image, detecting stationary areas of interest in the top portion of the inverted image and streaming the detected stationary areas of interest to the perception processor.Type: ApplicationFiled: December 6, 2019Publication date: June 10, 2021Inventors: Yuekun Zhang, Zuoguan Wang, Jizhang Shan, Ying Zhou
-
Patent number: 10997433Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.Type: GrantFiled: February 26, 2019Date of Patent: May 4, 2021Assignee: NVIDIA CorporationInventors: Yifang Xu, Xin Liu, Chia-Chih Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz
-
Publication number: 20210097393Abstract: A method of pruning a convolutional neural network, comprising at least one of determining a number of channels (N) between a network input and a network output, constructing N lookup tables, each lookup table matched to a respective channel and pruning filters in the convolutional neural network to create a shortcut between the network input and the network output based on the N lookup tables.Type: ApplicationFiled: February 27, 2019Publication date: April 1, 2021Inventors: Zuoguan Wang, Yilin Song, Qun Gu
-
Patent number: 10943132Abstract: A method of distant on-road object detection, comprising, capturing an initial frame of a roadway lane in a direction of travel, detecting lane edges in the initial frame, capturing a subsequent frame of the roadway lane, cropping the subsequent frame based on the detected lane edges of the initial frame resulting in an image patch, detecting an image patch object within the image patch, down-sampling the subsequent frame, detecting a down-sampled object within the down-sampled subsequent frame and merging the detections within the image patch and the detections within the down-sampled subsequent frame.Type: GrantFiled: April 10, 2019Date of Patent: March 9, 2021Assignee: Black Sesame International Holding LimitedInventors: Zuoguan Wang, Qun Gu, Jizhang Shan
-
Patent number: 10867192Abstract: A method of parking lot tracking including receiving a plurality of camera images from a plurality of cameras attached to a vehicle in motion, stitching the plurality of camera images to simulate a surround view of the vehicle, recognizing at least one potential parking space within the surround view of the vehicle, estimating a motion parameter by camera motion estimation of the plurality of cameras and tracking the at least one potential parking space based on the motion parameter.Type: GrantFiled: August 6, 2019Date of Patent: December 15, 2020Assignee: Black Sesame International Holding LimitedInventors: Yilin Song, Zuoguan Wang, Qun Gu
-
Publication number: 20200327339Abstract: A method of distant on-road object detection, comprising, capturing an initial frame of a roadway lane in a direction of travel, detecting lane edges in the initial frame, capturing a subsequent frame of the roadway lane, cropping the subsequent frame based on the detected lane edges of the initial frame resulting in an image patch, detecting an image patch object within the image patch, down-sampling the subsequent frame, detecting a down-sampled object within the down-sampled subsequent frame and merging the detections within the image patch and the detections within the down-sampled subsequent frame.Type: ApplicationFiled: April 10, 2019Publication date: October 15, 2020Inventors: Zuoguan Wang, Qun Gu, Jizhang Shan
-
Publication number: 20200234112Abstract: A method of adaptive quantization for a convolutional neural network, includes at least one of receiving an acceptable model accuracy, determining a float value multiply accumulate for the layer based on a float value weight and a float value input, quantizing the float value weight at multiple weight quantization precisions, quantizing the float value input at multiple input quantization precisions, determining a multiply accumulate at multiple multiply accumulate quantization precisions based on the weight quantization precisions and the input quantization precisions, determining multiple quantization errors based on differences between the float value multiply accumulate and the multiple multiply accumulate quantization precisions and selecting one of the multiple weight quantization precisions, one of the multiple input quantization precisions and one of the multiple multiply accumulate quantization precisions based on the predetermined acceptable model accuracy and the multiple quantization errors.Type: ApplicationFiled: April 10, 2019Publication date: July 23, 2020Inventors: Zuoguan Wang, Tian Zhou, Qun Gu
-
Publication number: 20190266418Abstract: In various examples, sensor data representative of an image of a field of view of a vehicle sensor may be received and the sensor data may be applied to a machine learning model. The machine learning model may compute a segmentation mask representative of portions of the image corresponding to lane markings of the driving surface of the vehicle. Analysis of the segmentation mask may be performed to determine lane marking types, and lane boundaries may be generated by performing curve fitting on the lane markings corresponding to each of the lane marking types. The data representative of the lane boundaries may then be sent to a component of the vehicle for use in navigating the vehicle through the driving surface.Type: ApplicationFiled: February 26, 2019Publication date: August 29, 2019Inventors: Yifang Xu, Xin Liu, Chia-Chih Chen, Carolina Parada, Davide Onofrio, Minwoo Park, Mehdi Sajjadi Mohammadabadi, Vijay Chintalapudi, Ozan Tonkal, John Zedlewski, Pekka Janis, Jan Nikolaus Fritsch, Gordon Grigor, Zuoguan Wang, I-Kuei Chen, Miguel Sainz