Abstract: A pedestrian recognition method and device. The method comprises: acquiring image features of a target pedestrian image, the image features comprising facial features and body features (S101); acquiring from a feature database at least one target node of the image features, and using a pedestrian image that corresponds to the at least one target node as an image of a target pedestrian (S103); the feature database comprises multiple pedestrian feature nodes, and the pedestrian feature nodes comprise facial features and body features which correspond to a pedestrian image, as well as relationship features between other pedestrian feature nodes. The described method enables the amount of computation for pedestrian searching to be greatly reduced, which improves searching efficiency.

Abstract: The present disclosure relates to an information processing method and apparatus, an electronic device, and a storage medium. The method includes: inputting received input information into a neural network; processing the input information by means of the neural network, where in the case that convolution processing is executed by means of a convolution layer of the neural network, a convolution kernel of the convolution layer is updated by using a transformation matrix configured for the convolution layer, so that the convolution processing of the convolution layer is completed by means of the updated convolution kernel; and outputting a processing result of the processing of the neural network. According to embodiments of the present disclosure, group convolution of a neural network in any form can be implemented.

Abstract: Methods, apparatuses, devices, program products, and media can improve the accuracy rate of searching for a target person. The method includes: obtaining an image of the target person; searching a face image library by using the image of the target person to obtain a first face image template matching the image of the target person, where the face image library includes a plurality of face image templates; and obtaining, according to the first face image template and a pedestrian image library, at least one target pedestrian image template matching the image of the target person, where the pedestrian image library includes a plurality of pedestrian image templates.

Abstract: The present disclosure relates to a target object tracking method and apparatus, an electronic device, and a storage medium. The method includes: obtaining a first reference image of a target object; determining time information and location information of the target object in an image to be analyzed according to the first reference image, the image to be analyzed including the time information and the location information; determining a trajectory of the target object according to the time information and the location information of the target object; and generating tracking information for tracking the target object according to the trajectory of the target object. Embodiments of the present disclosure obtain highly-accurate tracking information of the target object according to the trajectory of the target object determined in the image to be analyzed by using the first reference image of the target object, such that the success rate of target object tracking is improved.

Abstract: The present disclosure relates to a distance measurement method, an intelligent control method and apparatus, an electronic device, and a storage medium. The method includes: obtaining a detection bounding box of a target object in an image photographed by a current object; determining at least one distance measurement point according to the shape of the detection bounding box; and determining a distance between the target object and the current object based on the distance measurement point.

Abstract: The present disclosure relates to a collision control method and apparatus, an electronic device, and a storage medium. The method includes: detecting a target object in an image photographed by a traveling object; determining a forward collision hazard region of the traveling object; and executing collision control on the traveling object based on a relative relationship between the target object and the forward collision hazard region, where the collision control includes collision warning and/or driving control.

Abstract: The present disclosure relates to a collision control method and apparatus, an electronic device, and a storage medium. The method includes: detecting a target object in an image photographed by a current object; determining a danger level of the target object; and executing collision control corresponding to the danger level.

Abstract: A face image retrieval method includes: obtaining to-be-retrieved face information corresponding to a to-be-retrieved image by a convolutional neural network, the convolutional neural network being configured with corresponding convolution calculation configuration information by a processor, the convolutional neural network including at least one convolutional layer, the convolution calculation configuration information including a data bit width value corresponding to each convolutional layer in the convolutional neural network, and the to-be-retrieved image including at least one face region; searching a database for matched preset face image information that matches the to-be-retrieved face information, the database storing at least one piece of preset face image information; and outputting the preset face image information that matches the to-be-retrieved face information.

Abstract: An image lighting method includes: determining a convolutional neural network corresponding to a lighting operation type of an initial image; obtaining local feature information and global feature information of initial image according to convolutional neural network; obtaining fusion feature information of initial image according to convolutional neural network based on local feature information and global feature information; obtaining a maximum pooling result map and a minimum pooling result map according to convolutional neural network based on a luminance component map of initial image; obtaining a bilateral grid matrix of initial image based on fusion feature information, maximum pooling result map, and minimum pooling result map; and performing affine transformation on initial image according to bilateral grid matrix to obtain a target image, the target image being an image obtained after lighting initial image according to lighting operation type.

Abstract: An access control includes: performing, by a camera device, video data collection to obtain video data; performing, by the camera device, face image detection on the video data; in response to a face image being detected, performing, by the camera device, authentication on the face image; and outputting, by the camera device according to whether extracted feature data passes the authentication, a corresponding access control signal, so that an access control linkage apparatus opens or closes a door. Based on the embodiments of the present disclosure, the convenience and safety when a user passes through an access control are improved, the detection time is short, the detection efficiency is high, and the security of user data is improved.

Abstract: An image style transform method includes: acquiring an initial image to be subjected to style transform; inputting a gradient of the initial image to an image style transform model, and obtaining a feature map of the initial image in a gradient domain from the image style transform model, where the image style transform model is obtained by being trained in the gradient domain based on a pixel-wise loss and a perceptual loss; and performing image reconstruction according to the feature map of the initial image in the gradient domain to obtain a style image.

Abstract: An image retrieval method includes: respectively performing a dimension reduction operation on convolutional layer features of an image to be retrieved to obtain dimension-reduced features; clustering the dimension-reduced features to obtain a plurality of clustering features; performing feature fusion on the plurality of clustering features to obtain a global feature; and retrieving, on the basis of the global feature, the image to be retrieved from a database.

Abstract: An image processing method includes: obtaining a facial skin tone area in an image to be processed; filtering the image to be processed to obtain a filtered smooth image; obtaining a high-frequency image based on the smooth image and the image to be processed; obtaining a facial skin tone high-frequency image based on the high-frequency image and a facial skin tone mask; and superimposing the high-frequency image and the image to be processed based on the facial skin tone mask and preset first superimposition strength in a luma channel, and superimposing a luma channel signal of the facial skin tone high-frequency image onto a luma channel signal of the image to be processed, to obtain a first image.

Abstract: A content data recommendation method based on an identity verification apparatus includes: in response to an operation for identity verification, obtaining a first image of a user, and obtaining attribute information of the user from the first image; sending the attribute information to a content server, so that the content server determines first recommendation content data of the user according to the attribute information; and receiving the first recommendation content data fed back by the content server, and displaying recommendation content corresponding to the first recommendation content data.

Abstract: A dual-view angle image calibration method includes: performing feature matching on a first image pair to obtain a first feature point pair set, the first image pair including two images respectively photographed corresponding to two different view angles of a same scene; obtaining multiple different first fundamental matrices of the first image pair at least according to the first feature point pair set, and obtaining first image deformation information indicating relative deformation between the first image pair after mapping transformation is performed through the first fundamental matrices and the first image pair before the mapping transformation is performed; determining a first optimization fundamental matrix from the multiple first fundamental matrices at least according to the first image deformation information; and calibrating the first image pair according to the first optimization fundamental matrix.

Abstract: A method for recommending collocating dress includes: obtaining a first dress image from an input image; obtaining a first dress feature of the first dress image; obtaining, based on the first dress feature, a second dress feature matching the first dress feature from a collocation database, the second dress feature being a dress feature of a second dress image; and obtaining, based on the second dress feature, a dress image identical to and/or similar to the second dress image from a recommendation database as a collocating dress image. Based on the method in the embodiments, at least one collocation recommendation is provided for a dress image, and the recommendation result is more objective and is more in accordance with user demands.

Abstract: An access control method, an access control apparatus, a system, and a storage medium are disclosed. The method includes: acquiring a scene image, and recognizing one or more face images in the scene image; determining an attribute of the face image, the attribute including a registered user and an unregistered user; and if multiple face images are recognized, determining whether attributes corresponding to the multiple face images include the registered user, and responsive to determining that the attributes corresponding to the multiple face images comprise the registered user, controlling an access control device to be opened; responsive to determining that the attributes corresponding to the multiple face images does not comprise the registered user, in condition that an access control verification request instruction is received and verification for the access control verification request instruction succeeds, controlling the access control device to be opened.

Abstract: A methods for determining face image quality includes: obtaining pose angle information and/or size information of a face in an image; and obtaining quality information of the face in the image on the basis of the pose angle information and/or the size information of the face.

Abstract: A face image processing method includes: performing face detection on an image to be processed, and obtaining at least one face region image included in the image to be processed and face attribute information in the at least one face region image; and for the at least one face region image, processing an image corresponding to a first region and/or an image corresponding to a second region in the face region image at least according to the face attribute information in the face region image, wherein the first region is a skin region, and the second region includes at least a non-skin region.