Patents by Inventor Zhizhen CHI
Zhizhen CHI 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: 11430265Abstract: The present application discloses a video-based human behavior recognition method, apparatus, device and storage medium, and relates to the technical field of human recognitions. The specific implementation scheme lies in: acquiring a human rectangle of each video frame of the video to be recognized, where each human rectangle includes a plurality of human key points, and each of the human key points has a key point feature; constructing a feature matrix according to the human rectangle of the each video frame; convolving the feature matrix with respect to a video frame quantity dimension to obtain a first convolution result and convolving the feature matrix with respect to a key point quantity dimension to obtain a second convolution result; inputting the first convolution result and the second convolution result into a preset classification model to obtain a human behavior category of the video to be recognized.Type: GrantFiled: September 16, 2020Date of Patent: August 30, 2022Inventors: Zhizhen Chi, Fu Li, Hao Sun, Dongliang He, Xiang Long, Zhichao Zhou, Ping Wang, Shilei Wen, Errui Ding
-
Patent number: 11354923Abstract: The present disclosure provides a human body recognition method and apparatus, and a storage medium, the method comprising: determining a coordinate of a target person in a three-dimensional space according to images containing the target person collected by at least two cameras; calculating back-projection errors of the target person under different cameras respectively according to the coordinate of the target person in the three-dimensional space; determining whether the cameras have a human body recognition error according to the back-projection errors of the cameras; when a camera has the human body recognition error, performing re-recognition of the target person under the camera by using person re-identification ReID, until the back-projection errors of all the cameras containing the target person are not greater than a preset threshold. The present disclosure can improve accuracy of the human body recognition result effectively.Type: GrantFiled: July 21, 2020Date of Patent: June 7, 2022Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Jian Wang, Xubin Li, Le Kang, Zeyu Liu, Zhizhen Chi, Chengyue Zhang, Xiao Liu, Hao Sun, Shilei Wen, Yingze Bao, Mingyu Chen, Errui Ding
-
Patent number: 11302104Abstract: A method, apparatus, device, and storage medium for predicting the number of people of a dense crowd, including: converting a first image, in which the number of people is to be determined, into a corresponding first thermodynamic chart according to a thermodynamic chart conversion model; and determining the number of people in the first image according to the first thermodynamic chart, wherein the thermodynamic chart conversion model is obtained by training according to a pre-marked second image and a thermodynamic chart corresponding to each second image, thereby achieving prediction of the number of people of a dense crowd, improving the accuracy in predicting the number of people of the dense crowd while improving management efficiency.Type: GrantFiled: July 1, 2019Date of Patent: April 12, 2022Inventors: Chengyue Zhang, Zeyu Liu, Zhizhen Chi, Le Kang, Mingyu Chen, Yingze Bao, Jian Wang, Xubin Li, Shilei Wen, Errui Ding, Xiao Liu, Hao Sun
-
Patent number: 11263445Abstract: A method, apparatus and a system for human body tracking processing, where an apparatus for video collection processing in the system has a built-in intelligent chip, and before uploading video data to a cloud server, the intelligent chip performs a pre-processing on the video data, retains a key image frame and performs a human body detection and a tracking processing on the key image frame by using human body detection tracking algorithm to acquire a first human body detection tracking result. Afterwards, the intelligent chip sends the first human body detection tracking result to the cloud server, so that the cloud server performs a human body re-identification algorithm processing and/or three-dimensional reconstruction algorithm processing on the first human body detection tracking result to acquire a second human body detection tracking result.Type: GrantFiled: July 2, 2019Date of Patent: March 1, 2022Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Zeyu Liu, Le Kang, Chengyue Zhang, Zhizhen Chi, Jian Wang, Xubin Li, Xiao Liu, Hao Sun, Shilei Wen, Errui Ding, Hongwu Zhang, Mingyu Chen, Yingze Bao
-
Patent number: 11259029Abstract: A method, device, apparatus for predicting a video coding complexity and a computer-readable storage medium are provided. The method includes: acquiring an attribute feature of a target video; extracting a plurality of first target image frames from the target video; performing a frame difference calculation on the plurality of the first target image frames, to acquire a plurality of first frame difference images; determining a histogram feature for frame difference images of the target video according to a statistical histogram of each first frame difference image; and inputting a plurality of features of the target video into a coding complexity prediction model to acquire a coding complexity prediction value of the target video. Through the above method, the BPP prediction value can be acquired intelligently.Type: GrantFiled: February 21, 2020Date of Patent: February 22, 2022Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.Inventors: Zhichao Zhou, Dongliang He, Fu Li, Xiang Zhao, Xin Li, Zhizhen Chi, Xiang Long, Hao Sun
-
Patent number: 11256920Abstract: A method and an apparatus for classifying a video are provided. The method may include: acquiring a to-be-classified video; extracting a set of multimodal features of the to-be-classified video; inputting the set of multimodal features into a post-fusion model corresponding to each modal respectively, to obtain multimodal category information of the to-be-classified video; and fusing the multimodal category information of the to-be-classified video, to obtain category information of the to-be-classified video. This embodiment improves the accuracy of video classification.Type: GrantFiled: March 26, 2020Date of Patent: February 22, 2022Assignee: Beijing Baidu Netcom Science and Technology Co., Ltd.Inventors: Xiang Long, Dongliang He, Fu Li, Zhizhen Chi, Zhichao Zhou, Xiang Zhao, Ping Wang, Hao Sun, Shilei Wen, Errui Ding
-
Patent number: 11074709Abstract: Embodiments of the present application provide an image-based position detection method, an apparatus, a device and a storage medium. Images captured at the same time by a plurality of photographing devices mounted in different orientations are acquired, where the plurality of photographing devices are synchronous in time; a two-dimensional position of a target object in each of the images is detected; and a three-dimensional position of the target object in an actual space is determined based on the two-dimensional position of the target object in each of the images and internal parameters and external parameters of the plurality of photographing devices. The embodiments of the present application implement a three-dimensional positioning solution based on a plurality of cameras, thereby improving the reliability and accuracy of object positioning.Type: GrantFiled: June 27, 2019Date of Patent: July 27, 2021Inventors: Xubin Li, Jian Wang, Shilei Wen, Errui Ding, Hao Sun, Le Kang, Yingze Bao, Mingyu Chen, Zhizhen Chi, Zeyu Liu, Chengyue Zhang
-
Publication number: 20210192194Abstract: The present application discloses a video-based human behavior recognition method, apparatus, device and storage medium, and relates to the technical field of human recognitions. The specific implementation scheme lies in: acquiring a human rectangle of each video frame of the video to be recognized, where each human rectangle includes a plurality of human key points, and each of the human key points has a key point feature; constructing a feature matrix according to the human rectangle of the each video frame; convolving the feature matrix with respect to a video frame quantity dimension to obtain a first convolution result and convolving the feature matrix with respect to a key point quantity dimension to obtain a second convolution result; inputting the first convolution result and the second convolution result into a preset classification model to obtain a human behavior category of the video to be recognized.Type: ApplicationFiled: September 16, 2020Publication date: June 24, 2021Inventors: Zhizhen Chi, Fu Li, Hao Sun, Dongliang He, Xiang Long, Zhichao Zhou, Ping Wang, Shilei Wen, Errui Ding
-
Patent number: 10970528Abstract: A method for human motion analysis, an apparatus for human motion analysis, a device, and a storage medium. The method includes: acquiring image information captured by a number of photographing devices, where at least one of the number of photographing devices is disposed above a shelf; performing human tracking according to the image information captured by the plurality of photographing devices, and determining position information in space of at least one human body and identification information of the at least one human body; acquiring, according to the position information in space of a target human body of the at least one human body, a target image captured by the photographing device above a shelf corresponding to the position information; and recognizing an action of the target human body according to the target image and detection data of a non-visual sensor corresponding to the position information.Type: GrantFiled: July 2, 2019Date of Patent: April 6, 2021Inventors: Jian Wang, Xubin Li, Le Kang, Zeyu Liu, Zhizhen Chi, Chengyue Zhang, Xiao Liu, Hao Sun, Shilei Wen, Yingze Bao, Mingyu Chen, Errui Ding
-
Publication number: 20210019531Abstract: a method and an apparatus for classifying a video are provided. The method may include: acquiring a to-be-classified video; extracting a set of multimodal features of the to-be-classified video; inputting the set of multimodal features into a post-fusion model corresponding to each modal respectively, to obtain multimodal category information of the to-be-classified video; and fusing the multimodal category information of the to-be-classified video, to obtain category information of the to-be-classified video. This embodiment improves the accuracy of video classification.Type: ApplicationFiled: March 26, 2020Publication date: January 21, 2021Inventors: Xiang Long, Dongliang He, Fu Li, Zhizhen Chi, Zhichao Zhou, Xiang Zhao, Ping Wang, Hao Sun, Shilei Wen, Errui Ding
-
Publication number: 20200374526Abstract: A method, device, apparatus for predicting a video coding complexity and a computer-readable storage medium are provided. The method includes: acquiring an attribute feature of a target video; extracting a plurality of first target image frames from the target video; performing a frame difference calculation on the plurality of the first target image frames, to acquire a plurality of first frame difference images; determining a histogram feature for frame difference images of the target video according to a statistical histogram of each first frame difference image; and inputting a plurality of features of the target video into a coding complexity prediction model to acquire a coding complexity prediction value of the target video. Through the above method, the BPP prediction value can be acquired intelligently.Type: ApplicationFiled: February 21, 2020Publication date: November 26, 2020Applicant: Beijing Baidu Netcom Science and Technology Co., LtdInventors: Zhichao Zhou, Dongliang He, Fu Li, Xiang Zhao, Xin Li, Zhizhen Chi, Xiang Long, Hao Sun
-
Publication number: 20200349349Abstract: The present disclosure provides a human body recognition method and apparatus, and a storage medium, the method comprising: determining a coordinate of a target person in a three-dimensional space according to images containing the target person collected by at least two cameras; calculating back-projection errors of the target person under different cameras respectively according to the coordinate of the target person in the three-dimensional space; determining whether the cameras have a human body recognition error according to the back-projection errors of the cameras; when a camera has the human body recognition error, performing re-recognition of the target person under the camera by using person re-identification ReID, until the back-projection errors of all the cameras containing the target person are not greater than a preset threshold. The present disclosure can improve accuracy of the human body recognition result effectively.Type: ApplicationFiled: July 21, 2020Publication date: November 5, 2020Applicant: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Jian WANG, Xubin LI, Le KANG, Zeyu LIU, Zhizhen CHI, Chengyue ZHANG, Xiao LIU, Hao SUN, Shilei WEN, Yingze BAO, Mingyu CHEN, Errui DING
-
Publication number: 20190325209Abstract: A method, apparatus and a system for human body tracking processing, where an apparatus for video collection processing in the system has a built-in intelligent chip, and before uploading video data to a cloud server, the intelligent chip performs a pre-processing on the video data, retains a key image frame and performs a human body detection and a tracking processing on the key image frame by using human body detection tracking algorithm to acquire a first human body detection tracking result. Afterwards, the intelligent chip sends the first human body detection tracking result to the cloud server, so that the cloud server performs a human body re-identification algorithm processing and/or three-dimensional reconstruction algorithm processing on the first human body detection tracking result to acquire a second human body detection tracking result.Type: ApplicationFiled: July 2, 2019Publication date: October 24, 2019Applicant: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Zeyu LIU, Le KANG, Chengyue ZHANG, Zhizhen CHI, Jian WANG, Xubin LI, Xiao LIU, Hao SUN, Shilei WEN, Errui DING, Hongwu ZHANG, Mingyu CHEN, Yingze BAO
-
Publication number: 20190325207Abstract: A method for human motion analysis, an apparatus for human motion analysis, a device, and a storage medium. The method includes: acquiring image information captured by a number of photographing devices, where at least one of the number of photographing devices is disposed above a shelf; performing human tracking according to the image information captured by the plurality of photographing devices, and determining position information in space of at least one human body and identification information of the at least one human body; acquiring, according to the position information in space of a target human body of the at least one human body, a target image captured by the photographing device above a shelf corresponding to the position information; and recognizing an action of the target human body according to the target image and detection data of a non-visual sensor corresponding to the position information.Type: ApplicationFiled: July 2, 2019Publication date: October 24, 2019Applicant: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Jian WANG, Xubin LI, Le KANG, Zeyu LIU, Zhizhen CHI, Chengyue ZHANG, Xiao LIU, Hao SUN, Shilei WEN, Yingze BAO, Mingyu CHEN, Errui DING
-
Publication number: 20190325231Abstract: A method, apparatus, device, and storage medium for predicting the number of people of a dense crowd, including: converting a first image, in which the number of people is to be determined, into a corresponding first thermodynamic chart according to a thermodynamic chart conversion model; and determining the number of people in the first image according to the first thermodynamic chart, wherein the thermodynamic chart conversion model is obtained by training according to a pre-marked second image and a thermodynamic chart corresponding to each second image, thereby achieving prediction of the number of people of a dense crowd, improving the accuracy in predicting the number of people of the dense crowd while improving management efficiency.Type: ApplicationFiled: July 1, 2019Publication date: October 24, 2019Applicant: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Chengyue ZHANG, Zeyu LIU, Zhizhen CHI, Le KANG, Mingyu CHEN, Yingze BAO, Jian WANG, Xubin LI, Shilei WEN, Errui DING, Xiao LIU, Hao SUN
-
Publication number: 20190318499Abstract: Embodiments of the present application provide an image-based position detection method, an apparatus, a device and a storage medium. Images captured at the same time by a plurality of photographing devices mounted in different orientations are acquired, where the plurality of photographing devices are synchronous in time; a two-dimensional position of a target object in each of the images is detected; and a three-dimensional position of the target object in an actual space is determined based on the two-dimensional position of the target object in each of the images and internal parameters and external parameters of the plurality of photographing devices. The embodiments of the present application implement a three-dimensional positioning solution based on a plurality of cameras, thereby improving the reliability and accuracy of object positioning.Type: ApplicationFiled: June 27, 2019Publication date: October 17, 2019Inventors: Xubin LI, Jian WANG, Shilei WEN, Errui DING, Hao SUN, Le KANG, Yingze BAO, Mingyu CHEN, Zhizhen CHI, Zeyu LIU, Chengyue ZHANG