Abstract: A license plate number recognition method includes: extracting license plate number features of an image to be recognized including a license plate number, through a pre-trained convolutional neural network; extracting an intermediate convolution result during extracting the license plate number features, and extracting a first verification feature and/or a second verification feature according to the intermediate convolution result; verifying whether the license plate number features are correct according to the first and/or second verification features; if correct, outputting a predicted license plate number result according to the license plate number features.

Abstract: The present application is applicable to the technical field of image processing, and provides a target object tracking method and an apparatus, and a terminal device. The target object tracking method includes: obtaining an image sequence including a target object, wherein the image sequence includes a plurality of image; analyzing the plurality of image, and determining a motion vector and a motion vector residual of the target object in a current image; and inputting the motion vector, the motion vector residual, and a known target region of the target object in a previous image into a first target detection network, and determining a predicted target region of the target object in the current image. The present application can reduce the calculation amount and thus improve the operation speed of target object tracking.

Abstract: A multi-target tracking method includes: obtaining a first image and a second image including N tracking targets from the same target video file, and obtaining N first tracking boxes of the first image that precedes a preset number of frames of the second image, the N first tracking boxes configured to frame the N tracking targets in the first image; superposing and synthesizing the first second images to obtain a target image; inputting the target image into an hourglass network model for feature extraction, to output a target feature map; inputting the target feature map into a prediction network to output a thermodynamic diagram, a width and height value set, a minor deviation value set, and a feature vector set; determining N second tracking boxes configured to frame N tracking targets in the second image, based on the thermodynamic diagram, the above three sets, and the N first tracking boxes.

Abstract: The present application is applicable to the technical field of image processing, and provides a target object tracking method and an apparatus, and a terminal device. The target object tracking method includes: obtaining an image sequence including a target object, wherein the image sequence includes a plurality of image; analyzing the plurality of image, and determining a motion vector and a motion vector residual of the target object in a current image; and inputting the motion vector, the motion vector residual , and a known target region of the target object in a previous image into a first target detection network, and determining a predicted target region of the target object in the current image. The present application can reduce the calculation amount and thus improve the operation speed of target object tracking.

Abstract: A license plate number recognition method includes: extracting license plate number features of an image to be recognized including a license plate number, through a pre-trained convolutional neural network; extracting an intermediate convolution result during extracting the license plate number features, and extracting a first verification feature and/or a second verification feature according to the intermediate convolution result; verifying whether the license plate number features are correct according to the first and/or second verification features; if correct, outputting a predicted license plate number result according to the license plate number features.

Abstract: A method and an apparatus for labeling human body completeness data, and a terminal device, are provided. The method includes: obtaining an image to be labeled (201); performing human body detection on the image to obtain a first human body frame (202); performing human body key point detection on the image, and determining human body part information according to the human body key points that have been detected (203); performing human body area detection on the image to obtain human body visible region labeling information (204); determining the human body part information associated with the first human body frame, and determining the human body visible region labeling information associated with the first human body frame, to complete the labeling of human body completeness data of the first human body frame (205). The described method can reduce a lot of manpower and material resources, shorten the time for labeling human completeness data, and are benefit rapid iteration of products.

Abstract: A multi-target tracking method includes: obtaining a first image and a second image including N tracking targets from the same target video file, and obtaining N first tracking boxes of the first image that precedes a preset number of frames of the second image, the N first tracking boxes configured to frame the N tracking targets in the first image; superposing and synthesizing the first second images to obtain a target image; inputting the target image into an hourglass network model for feature extraction, to output a target feature map; inputting the target feature map into a prediction network to output a thermodynamic diagram, a width and height value set, a minor deviation value set, and a feature vector set; determining N second tracking boxes configured to frame N tracking targets in the second image, based on the thermodynamic diagram, the above three sets, and the N first tracking boxes.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection and representation in images. In one aspect, a method includes detecting occurrences of objects of a particular type in images captured within a first duration of time, and iteratively training an image embedding function to produce as output representations of features of the input images depicting occurrences of objects of the particular type, where similar representations of features are generated for images that depict the same instance of an object of a particular type captured within a specified duration of time, and dissimilar representations of features are generated for images that depict different instances of objects of the particular type.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection and representation in images. In one aspect, a method includes detecting occurrences of objects of a particular type in images captured within a first duration of time, and iteratively training an image embedding function to produce as output representations of features of the input images depicting occurrences of objects of the particular type, where similar representations of features are generated for images that depict the same instance of an object of a particular type captured within a specified duration of time, and dissimilar representations of features are generated for images that depict different instances of objects of the particular type.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adjusting facial image search results. In one aspect, a method includes detecting, in images that are responsive to a query, faces in the images and building facial templates. The images are then clustered according to similarity measures of the facial templates. The cluster with the highest quantity is selected, and each image in the set of returned images is compared to each image in the selected cluster. The similarity of each face with the faces in the largest cluster, based on the facial templates, is determined as an inlier score for the image in which the face is depicted. The system then increases the rank of images with high inlier scores and decreases the rank of images with low inlier scores.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adjusting facial image search results. In one aspect, a method includes detecting, in images that are responsive to a query, faces in the images and building facial templates. The images are then clustered according to similarity measures of the facial templates. The cluster with the highest quantity is selected, and each image in the set of returned images is compared to each image in the selected cluster. The similarity of each face with the faces in the largest cluster, based on the facial templates, is determined as an inlier score for the image in which the face is depicted. The system then increases the rank of images with high inlier scores and decreases the rank of images with low inlier scores.