Patents by Inventor Qun Gu

Qun Gu 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).

  • Publication number: 20250054315
    Abstract: The present invention discloses a system for detecting poses of people around a vehicle. An electronic sensor such as a camera is associated with a vehicle for the generation of consecutive frames within a video. The system generates a boundary box around a person within each frame and optimizes a tracker for each person in consecutive frames. The system detects people on the road through pose estimation. The system performs a confidence pre-processing procedure before sending the trackers to a pose estimator to extract their poses.
    Type: Application
    Filed: August 10, 2023
    Publication date: February 13, 2025
    Inventors: Xiaomin Liu, Wenyi Wang, Lei Zhang, Qun Gu
  • Publication number: 20250029392
    Abstract: The present invention discloses a system and a method for real-time image based traffic detection for self-driving and advanced driver-assistance systems (ADAS). The system and method include conversion of a resized image by an image reducer with resolution smaller than the image generated. The resized image is used for further analysis and uses less computing resources to provide real-time traffic assistance to the vehicle.
    Type: Application
    Filed: July 19, 2023
    Publication date: January 23, 2025
    Inventors: Zhenhui Jiang, Zuoguan Wang, Qun Gu
  • Patent number: 12205397
    Abstract: A method of human pose estimation, including, receiving an image frame, extracting in at least a first stage a first stage image feature based on the image frame, extracting in at least a second stage a second stage image feature based on the first stage image feature, extracting in at least a subsequent stage a subsequent stage image feature based on the second stage image feature, up-sampling the subsequent stage image feature, up-sampling the second stage image feature, concatenating the first stage image feature, the up-sampled second stage image feature and the up-sampled subsequent stage image feature and outputting a feature map based on an output of the concatenation.
    Type: Grant
    Filed: August 31, 2021
    Date of Patent: January 21, 2025
    Assignee: Black Sesame Technologies Inc.
    Inventors: Xiaomin Liu, Lei Zhang, Qun Gu
  • Publication number: 20240378413
    Abstract: 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: Application
    Filed: July 22, 2024
    Publication date: November 14, 2024
    Inventors: Zheng Qi, Qun Gu, Zheng Li, Chenghao Zhang, Tian Zhou, Zuoguan Wang
  • Publication number: 20240371014
    Abstract: The present invention discloses a new solution for training depth estimation net to improve prediction performance using kinematics and a self-attention module. The present invention not only helps to recover depth scale, but also simplifies the training stage and solves the dynamic object issue using the attention module.
    Type: Application
    Filed: May 2, 2023
    Publication date: November 7, 2024
    Inventors: Wenwen Tu, Zuoguan Wang, Qun Gu
  • Publication number: 20240361462
    Abstract: An example method of converting lidar points to a three-dimensional image, including receiving a set of irregular lidar points forming a lidar point cloud, assigning the set of irregular lidar points to a 3D or 2D grid resulting in a set of assigned points, determining a pseudo image based on the set of assigned points resulting in a set of regular pseudo image points, encoding the set of regular pseudo image points including a reflection channel normalization, at least one point decoration and a point feature of the at least one point decoration resulting in a set of high dimension regular features and predicting at least one three-dimensional object utilizing the set of high dimension regular features.
    Type: Application
    Filed: April 27, 2023
    Publication date: October 31, 2024
    Inventors: Xinrui Zhang, Lei Zhang, Qun Gu
  • Publication number: 20240357362
    Abstract: The present disclosure provides a network element selection method, and apparatus, and network elements. The method includes: selecting, by a first network element, a network slice-specific authentication and authorization function (NSSAAF) network element according to first information; wherein the first information includes at least one of the following: S-NSSAI for a network slice; a home network identifier in a subscription permanent identifier (SUPI); a data network name (DNN); a generic public subscription identifier (GPSI); a subscription permanent identifier (SUPI); an external group ID; an internal group ID; and a routing identifier.
    Type: Application
    Filed: July 28, 2022
    Publication date: October 24, 2024
    Inventors: Qun GU, Aihua LI, Zhenning HUANG
  • Patent number: 12124936
    Abstract: 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: Grant
    Filed: October 12, 2020
    Date of Patent: October 22, 2024
    Assignee: Black Sesame Technologies Inc.
    Inventors: Zheng Qi, Qun Gu, Zheng Li, Chenghao Zhang, Tian Zhou, Zuoguan Wang
  • Patent number: 12002294
    Abstract: A method of face anti-spoofing, comprising, receiving a near infra-red facial image, having a near infrared channel, receiving a red-green-blue facial image, having a red channel, a green channel and a blue channel, generating a synthetic three channel image based on the near infrared channel, the red channel, the green channel and the blue channel and training a deep neural network based on the synthetic three channel image.
    Type: Grant
    Filed: March 4, 2021
    Date of Patent: June 4, 2024
    Assignee: Black Sesame Technologies Inc.
    Inventors: Xiaomin Liu, Lei Zhang, Qun Gu, Zilong Hu
  • Patent number: 11989973
    Abstract: A method of age and gender estimation, comprising receiving an input image, detecting a facial image within the input image, estimating a head pose based on a set of facial image intensities of the facial image, wherein the head pose is expressed as a yaw, a pitch and a roll, determining whether the yaw, the pitch and the roll of the head pose is less than a predetermined threshold, aligning the facial image if the yaw, the pitch and the roll of the head pose are less than the predetermined threshold and predicting an age and a gender of the aligned facial image.
    Type: Grant
    Filed: August 31, 2021
    Date of Patent: May 21, 2024
    Assignee: Black Sesame Technologies Inc.
    Inventors: Meng Meng, Lei Zhang, Qun Gu
  • Patent number: 11972617
    Abstract: 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: Grant
    Filed: June 16, 2021
    Date of Patent: April 30, 2024
    Assignee: Sesame Technologies Inc.
    Inventors: Liying Liu, Zuoguan Wang, Qun Gu
  • Patent number: 11887384
    Abstract: A method of describing a temporal event, including receiving a video sequence of the temporal event, extracting at least one physical characteristic of an at least one occupant within the video sequence, extracting at least one action of the at least one occupant within the video sequence, extracting at least one interaction of the at least one occupant with a secondary occupant within the video sequence, determining a safety level of the temporal event within a vehicle based on at least one of the at least one action and the at least one interaction and describing the at least one physical characteristic of the at least one occupant and at least one of the at least one action and the at least one interaction of the at least one occupant.
    Type: Grant
    Filed: February 2, 2021
    Date of Patent: January 30, 2024
    Assignee: Black Sesame Technologies Inc.
    Inventors: Zilong Hu, Lei Zhang, Qun Gu
  • Publication number: 20230230636
    Abstract: The present disclosure relates to methods of writing data in nucleic acid chains and methods of reading data written in nucleic acid chains. The present disclosure also relates to a kit for writing and reading data in nucleic acid chains.
    Type: Application
    Filed: May 14, 2021
    Publication date: July 20, 2023
    Inventors: Li-Qun GU, Kai TIAN
  • Patent number: 11625607
    Abstract: 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: Grant
    Filed: February 27, 2019
    Date of Patent: April 11, 2023
    Assignee: BLACK SESAME TECHNOLOGIES INC.
    Inventors: Zuoguan Wang, Yilin Song, Qun Gu
  • Publication number: 20230069436
    Abstract: A method of age and gender estimation, comprising receiving an input image, detecting a facial image within the input image, estimating a head pose based on a set of facial image intensities of the facial image, wherein the head pose is expressed as a yaw, a pitch and a roll, determining whether the yaw, the pitch and the roll of the head pose is less than a predetermined threshold, aligning the facial image if the yaw, the pitch and the roll of the head pose are less than the predetermined threshold and predicting an age and a gender of the aligned facial image.
    Type: Application
    Filed: August 31, 2021
    Publication date: March 2, 2023
    Inventors: Meng Meng, Lei Zhang, Qun Gu
  • Publication number: 20230067442
    Abstract: A method of human pose estimation, including, receiving an image frame, extracting in at least a first stage a first stage image feature based on the image frame, extracting in at least a second stage a second stage image feature based on the first stage image feature, extracting in at least a subsequent stage a subsequent stage image feature based on the second stage image feature, up-sampling the subsequent stage image feature, up-sampling the second stage image feature, concatenating the first stage image feature, the up-sampled second stage image feature and the up-sampled subsequent stage image feature and outputting a feature map based on an output of the concatenation.
    Type: Application
    Filed: August 31, 2021
    Publication date: March 2, 2023
    Inventors: Xiaomin Liu, Lei Zhang, Qun Gu
  • Patent number: 11544009
    Abstract: A system on a chip, including a first domain having a first processor, a first local memory coupled to the first processor, wherein the first local memory having a first memory format and a first sub-network coupled to the first processor, a second domain having a second processor, a second local memory coupled to the second processor and a second sub-network coupled to the second processor, wherein the second local memory having a second memory format which differs from the first memory format, a multi-tier network coupled to the first sub-network and the second sub-network, a global memory coupled to the multi-tier network and a multi-port DDR controller coupled to the global memory to receive, transmit and share the first local memory having the first memory format and the second local memory having the second memory format based on a predetermined criteria.
    Type: Grant
    Filed: May 10, 2021
    Date of Patent: January 3, 2023
    Assignee: Black Sesame Technologies Inc.
    Inventors: Zheng Qi, Qun Gu, Chengyu Xiong
  • Publication number: 20220405515
    Abstract: 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: Application
    Filed: June 16, 2021
    Publication date: December 22, 2022
    Inventors: Liying Liu, Zuoguan Wang, Qun Gu
  • Patent number: 11507823
    Abstract: 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: Grant
    Filed: April 10, 2019
    Date of Patent: November 22, 2022
    Assignee: Black Sesame Technologies Inc.
    Inventors: Zuoguan Wang, Tian Zhou, Qun Gu
  • Publication number: 20220333164
    Abstract: Provided herein are probes in which an Ap site of a probe strand can selectively cross-link with a 2?-deoxyguanosine (dG) of a target strand. Also provided for are methods of using such probes to generate and detect crosslinked molecules and methods of detecting disease associated genetic mutations.
    Type: Application
    Filed: August 10, 2020
    Publication date: October 20, 2022
    Inventors: Kent Gates, Li-Qun Gu, Maryam Imani Nejad, Xu Guo