Baidu Online Network Technology (beijing) Co., Ltd.

Baidu Online Network Technology Co., Ltd.

Xubin Li

Shilei Wen

Xiao Xi Liu

Errui Ding

Hao Sun

Jian Wang

Mingyu Chen

Yingze Bao

Le Kang

Zeyu Liu

Zhizhen Chi

Chengyue Zhang

Xin Li

Fan Yang

Xin Zhang

Feng Li

Fu Li

Xiang Zhao

Haiping Wang

Shijia Chen

Xi Zeng

Baoyu Zhang

Rongrong Han

Fantian Meng

Chenghao Chang

Xinwei Yu

Jiaqi Jiang

Meng Qi

Lixing Gong

Yueyang Song

Yang Hu

Hui Shen

Yuan Gao

Yan Jiang

Zhigang Wang

Hongwu Zhang

Dongliang He

Xiaohua Cheng

You Han

Shouke Qin

Peizhi Xu

Yinan Yu

Zeming Zhang

Xiaolin Ma

Zhiyang Chen

Ti Bai

Yi Fu

Xiao Liu

Embodiments of the present disclosure disclose a method and apparatus for recognizing a body movement. A specific embodiment of the method includes: sampling an input to-be-recognized video to obtain a sampled image frame sequence of the to-be-recognized video; performing key point detection on the sampled image frame sequence by using a trained body key point detection model, to obtain a body key point position heat map of each sampled image frame in the sampled image frame sequence, the body key point position heat map being used to represent a probability feature of a position of a preset body key point; and inputting body key point position heat maps of the sampled image frame sequence into a trained movement classification model to perform classification, to obtain a body movement recognition result corresponding to the to-be-recognized video.

Method and apparatus for recognizing body movement

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.

Human body recognition method and apparatus, and storage medium

A human body tracking method, apparatus, and device, and a storage medium. The method includes: obtaining a current frame image captured by a target photographing device at a current moment; detecting each human body in the current frame image to obtain first position information of the each human body in the current frame image; calculating second position information of a first human body in the current frame image; determining target position information of the each human body in the current frame image according to the second position information of the first human body in the current frame image, the first position information of the each human body in the current frame image, and pedestrian features of all tracked pedestrians stored in a preset list.

Human body tracing method, apparatus and device, and storage medium

A method and an apparatus for human behavior recognition, and a storage medium, the method includes: obtaining a human behavior video captured by a camera; extracting a start point and an end point of a human motion from the human behavior video, where the human motion between the start point and the end point corresponds to a sliding window; determining whether the sliding window is a motion section; and if the sliding window is a motion section, anticipating a motion category of the motion section using a pre-trained motion classifying model. Thus, accurate anticipation of a motion in a human behavior video captured by a camera is realized without human intervention.

Method and apparatus for human behavior recognition, and storage medium

The present disclosure provides a method and apparatus for extracting a video preview, a device and a computer storage medium. The method comprises: inputting a video into a video classification model obtained by pre-training; obtaining weights of respective video frames output by an attention module in the video classification model; extracting continuous N video frames whose total weight value satisfies a preset requirement, as the video preview of the target video, N being a preset positive integer. It is possible to, in the manner provided by the present disclosure, automatically extract continuous video frames from the video as the video preview, without requiring manual clipping, and with manpower costs being reduced.

Method and apparatus for extracting video preview, device and computer storage medium

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.

Method, apparatus, device, and storage medium for predicting the number of people of dense crowd

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.

Method, apparatus and system for human body tracking processing

A method and an apparatus for processing an image are provided. A method may include: acquiring a to-be-processed foggy image, and performing minimum value filtering on the to-be-processed foggy image to obtain a grayscale image of the to-be-processed foggy image; selecting, in a descending order of pixel values, a target number of pixel points from the grayscale image, and determining an image area corresponding to the selected pixel points from the to-be-processed foggy image; acquiring pixel values of the pixel points included in the image area, and determining an atmospheric light value based on the acquired pixel values; and performing image defogging processing on the to-be-processed foggy image based on the grayscale image and the atmospheric light value to obtain a processed image. The effect of image display and the efficiency of image processing can be improved.

Method and apparatus for processing image

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.

Image-based position detection method, image based position detection apparatus, device and storage medium

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.

Method for human motion analysis, apparatus for human motion analysis, device and storage medium

The present disclosure provides a method and apparatus for evaluating image definition, a computer device and a storage medium, wherein the method comprises: obtaining an image to be processed; inputting the image to be processed to a pre-trained evaluation model; obtaining an comprehensive image definition score outputted by the evaluation model, the comprehensive image definition score being obtained by the evaluation model by obtaining N image definition scores based on N different scales respectively, and then integrating the N image definition scores, N being a positive integer greater than one. The solution of the present invention can be applied to improve the accuracy of the evaluation result.

Method and apparatus for evaluating image definition, computer device and storage medium

Embodiments of the present disclosure disclose a method and apparatus for adding a digital watermark in a video. A specific embodiment of the method includes: performing target detection on each frame of image in a target video; determining, based on a target detection result, whether the target video includes at least one carrier, the carrier referring to an object for adding a digital watermark in the each frame of image; and determining a target carrier from the at least one carrier, and adding the digital watermark to an area of the target carrier in the each frame of image including the target carrier in the target video, in response to determining the target video including the at least one carrier.

Method and apparatus for adding digital watermark to video

The present disclosure provides a video displaying method and apparatus, a device and a computer storage medium, wherein the method comprises: positioning a target video; displaying a video preview of the target video, the video preview being a video segment extracted from the target video. This displaying manner exhibits a stronger capability of expressing the video content. The user can better know whether the video is the desired content. The present disclosure may reduce a probability of the user missing desired video resources and reduce a probability that the user finds that the video content does not meet an expectation after he views the video content, thereby helping the user to conveniently and effectively view the desired video resources.

Video displaying method and apparatus, device and computer storage medium

A method for tracking a target profile in a video includes: determining position information of corner points of the target profile and parameter information of a first edge formed by adjacent corner points in a previous image frame adjacent to a current image frame; tracking corner points of the target profile in the previous image frame to acquire position information of the corner points of the target profile in the current image frame to determine parameter information of a second edge; predicting to acquire predicted parameter information, and generating candidate target profiles based on the predicted parameter information, in response to determining that a similarity between the first edge and a second edge corresponding to the first edge being less than a first preset threshold; and determining a final position of the target profile in the current image frame based on the candidate target profiles.

Method and apparatus for tracking target profile in video

Embodiments of the present disclosure disclose a method and an apparatus for processing an image. A specific embodiment of the method includes: acquiring a target image including a polygon image; inputting the target image into a pre-trained convolutional neural network to obtain a characteristic vector of the target image, the convolutional neural network being used to represent a correspondence relationship between an image and a characteristic vector, and the characteristic vector being a vector including a category feature, a position feature, and a keypoint feature of the polygon image; and recognizing an image area of the polygon image based on the category feature, the position feature, and the keypoint feature. This embodiment improves the accuracy of polygon image recognition.

Growing community of inventors

Beijing, China

Xubin Li