Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

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

Symantec Corporation

The Procter Gamble Company

Southwest Petroleum University

Baidu Online Network Technology Co., Ltd.

Crsc Research & Design Institute Group Co., Ltd.

Xiao Tan

Hao Sun

Xiaoqing Ye

Errui Ding

Shilei Wen

Hongwu Zhang

Feng Zhou

Wei Zhang

Minyue Jiang

Xipeng Yang

Yingying Li

Zhikang Zou

Hang Li

Yi Bu Li

Nigel Patrick Somerville Roberts

Wei Li

Qingyou Liu

Dongliang He

Yue Yu

Xingming Wang

Chao Sun

Yongfeng Zhong

Yuan Zhong

James Song

Derek Dasong Liu

Jiangfan Deng

Hongxiang Lei

Shihong Xiao

Xu Si

Tieshan Zhang

Qing Tu

Fanyao Jin

Shichao Zhao

Jianchuan Wu

Dengwei Li

Kai Xiao

Fan Bai

Yin Ming Mei

Feng Ye

Han Qi

Xu Luo

A method for training an image depth estimation model. A sample environmental image, sample environmental point cloud data and sample edge information of the sample environmental image are input into a to-be-trained model; initial depth information of each of pixel points in the sample environmental image and a feature relationship between each of the pixel points and a corresponding neighboring pixel point of each of the pixel points are determined through the to-be-trained model, the initial depth information of each of the pixel points is optimized according to the feature relationship to obtain optimized depth information of each of the pixel points, and a parameter of the to-be-trained model is adjusted according to the optimized depth information to obtain the image depth estimation model.

Method for training image depth estimation model and method for processing image depth information

Embodiments of the present disclosure disclose a method and apparatus for determining a target anchor, a device and a storage medium. The method may include: extracting a plurality of feature maps of an original image using a feature extraction network; inputting the plurality of feature maps into a feature pyramid network to perform feature fusion, to obtain a plurality of fused feature maps; and using a region proposal network to implement operations as follows: determining an initial anchor of a network head using the fused feature map, based on a size of each fused feature map, and determining an offset parameter of the initial anchor, based on a ratio of the size of the fused feature map to the original image, and generating a plurality of candidate anchors in different directions, based on the offset parameter of the initial anchor.

Method and apparatus for determining target anchor, device and storage medium

The present disclosure provides an object pose obtaining method, and an electronic device, relates to technology fields of image processing, computer vision, and deep learning. A detailed implementation is: extracting an image block of an object from an image, and generating a local coordinate system corresponding to the image block; obtaining 2D projection key points in an image coordinate system corresponding to a plurality of 3D key points on a 3D model of the object; converting the 2D projection key points into the local coordinate system to generate corresponding 2D prediction key points; obtaining direction vectors between each pixel point in the image block and each 2D prediction key point, and obtaining a 2D target key point corresponding to each 2D predication key point based on the direction vectors; and determining a pose of the object according to the 3D key points and the 2D target key points.

Object pose obtaining method, and electronic device

A method and an apparatus for calibrating an external parameter of a camera are provided. The method may include: acquiring a time-synchronized data set of three-dimensional point clouds and two-dimensional image of a calibration reference object, the two-dimensional image being acquired by a camera with a to-be-calibrated external parameter; establishing a transformation relationship between a point cloud coordinate system and an image coordinate system, the transformation relationship including a transformation parameter; back-projecting the data set of the three-dimensional point clouds onto a plane where the two-dimensional image is located through the transformation relationship to obtain a set of projection points of the three-dimensional point clouds; adjusting the transformation parameter to map the set of the projection points onto the two-dimensional image; and obtaining an external parameter of the camera based on the adjusted transformation parameter and the data set of the three-dimensional point clouds.

Method, apparatus, electronic device and computer readable medium for calibrating external parameter of camera

A vehicle information detection method, a method for training a detection model, an electronic device and a storage medium are provided, and relates to the technical field of artificial intelligence, in particular to the technical field of computer vision and deep learning. The method includes: performing a first target detection operation based on an image of a target vehicle, to obtain a first detection result for target information of the target vehicle; performing an error detection operation based on the first detection result, to obtain error information; and performing a second target detection operation based on the first detection result and the error information, to obtain a second detection result for the target information.

Vehicle information detection method, method for training detection model, electronic device and storage medium

A method for generating a license plate defacement classification model, a license plate defacement classification method an electronic device and a storage medium, and related to the technical field of artificial intelligence, and specifically, to the technical field of computer vision and the technical field of intelligent transportation are provided. The method for generating a license plate defacement classification model includes: acquiring training data, wherein the training data includes a plurality of annotated vehicle images, annotated content includes information indicating that a license plate is defaced or is not defaced, and the annotated content further includes location information of a license plate area; and training a first neural network by using the training data, to obtain the license plate defacement classification model for predicting whether the license plate in a target vehicle image is defaced. A robust license plate defacement classification model can be obtained by using embodiments.

Method for generating a license plate defacement classification model, license plate defacement classification method, electronic device and storage medium

The present disclosure provides a target detection and model training method and apparatus, a device and a storage medium, and relates to the field of artificial intelligence, and in particular, to computer vision and deep learning technologies, which may be applied to smart city and intelligent transportation scenarios. The target detection method includes: performing feature extraction processing on an image to obtain image features of a plurality of stages of the image; performing position coding processing on the image to obtain a position code of the image; obtaining detection results of the plurality of stages of a target in the image based on the image features of the plurality of stages and the position code; and obtaining a target detection result based on the detection results of the plurality of stages.

Target detection and model training method and apparatus, device and storage medium

Embodiments of the present disclosure provide a method and apparatus for detecting a target object in an image. The method includes: performing following prediction operations using a pre-trained neural network: detecting a target object in a two-dimensional image to determine a two-dimensional bounding box of the target object; and determining a relative position constraint relationship between the two-dimensional bounding box of the target object and a three-dimensional projection bounding box obtained by projecting a three-dimensional bounding box of the target object into the two-dimensional image; and the method further including: determining the three-dimensional projection bounding box of the target object, based on the two-dimensional bounding box of the target object and the relative position constraint relationship between the two-dimensional bounding box of the target object and the three-dimensional projection bounding box.

Method and apparatus for detecting target object in image

A lane line detection method, an electronic device, and a storage medium, related to the field of artificial intelligence, and particularly related to computer vision and deep learning technologies, which can be applied to intelligent traffic scenes, are provided. The method includes: dividing an image into a foreground region and a background region; determining a solid line and a dotted line included in the foreground region; determining, according to the solid line and the dotted line comprised in the foreground region, whether a dotted-and-solid line is included in the foreground region; and determining a lane line detection result according to the solid line, the dotted line, and whether a dotted-and-solid line is comprised in the foreground region. According to the technical solution, the accuracy of lane line detection can be improved.

Lane line detection method, electronic device, and computer storage medium

The present disclosure provides an image processing method. An image to be classified is input into a feature extraction model to generate N dimensional features. Dimension fusion is performed on M features of the N dimensional features to obtain M dimension fusion features. The image to be classified is processed based on M dimension fusion features and remaining features of the N dimensional features other than the M features.

Feature fusion method and apparatus for image processing, electronic device and storage medium

The present application discloses a vehicle re-identification method and apparatus, a device and a storage medium, which relates to the field of computer vision, intelligent search, deep learning and intelligent transportation. The specific implementation scheme is: receiving a re-identification request from a terminal device, the re-identification request including a first image of a first vehicle shot by a first camera and information of the first camera; acquiring a first feature of the first vehicle and a first head orientation of the first vehicle according to the first image; determining a second image of the first vehicle from images of multiple vehicles according to the first feature, multiple second features extracted based on the images of the multiple vehicles in an image database, the first head orientation of the first vehicle, and the information of the first camera; and transmitting the second image to the terminal device.

Vehicle re-identification method, apparatus, device and storage medium

Embodiments of the present disclosure disclose a method and apparatus for identifying a video. A specific embodiment of the method includes: acquiring a predetermined number of video frames from a video to be identified to obtain a video frame sequence; performing the following processing step: importing the video frame sequence into a pre-trained video identification model to obtain a classification tag probability corresponding to the video frame sequence, wherein the classification tag probability is used to characterize a probability of identifying a corresponding tag category of the video to be identified; and setting, in response to the classification tag probability being greater than or equal to a preset identification accuracy threshold, a video tag for the video to be identified according to the classification tag probability, or else increasing the number of video frames in the video frame sequence and continuing to perform the above processing step.

Method and apparatus for identifying video

A vehicle information detection method, an electronic device and a storage medium are provided, and relates to the technical field of artificial intelligence, in particular to the technical field of computer vision and deep learning. The method includes: determining a bird's-eye view of a target vehicle based on an image of the target vehicle; performing feature extraction on the image of the target vehicle and the bird's-eye view respectively, to obtain first feature information corresponding to the image of the target vehicle and second feature information corresponding to the bird's-eye view of the target vehicle; and determining three-dimensional information of the target vehicle based on the first feature information and the second feature information. According to embodiments of the disclosure, accurate detection of vehicle information can be realized based on a monocular image.

Vehicle information detection method, electronic device and storage medium

The present disclosure provides a three-dimensional (3D) object detection method, a 3D object detection apparatus, an electronic device, and a readable storage medium, belonging to a field of computer vision technologies. Two-dimensional (2D) image parameters and initial 3D image parameters are determined for a target object. Candidate 3D image parameters are determined for the target object based on a disturbance range of 3D parameters and the initial 3D image parameters determined for the target object. Target 3D image parameters are selected for the target object from the candidate 3D image parameters determined for the target object based on the 2D image parameters. A 3D detection result of the target object is determined based on the target 3D image parameters.

Three-dimensional object detection method, electronic device and readable storage medium

Embodiments of the present disclosure provide a method and apparatus for processing a video frame, and relates to the field of computer vision technology. The method may include: acquiring a plurality of candidate first-order radial distortion parameters preset for a to-be-processed video frame, and acquiring a specified value of a specified radial distortion parameter; performing radial distortion correction on the to-be-processed video frame to obtain a first initial corrected video frame; selecting a first initial corrected video frame in which a local region except for a center region after distortion correction includes a largest number of straight line segments; and determining a candidate first-order radial distortion parameter corresponding to the selected first initial corrected video frame for use as a target first-order radial distortion parameter of the to-be-processed video frame.

Method and apparatus for processing video frame

Growing community of inventors

Beijing, China

Xiao Tan