Abstract: The disclosure provides an object detection method and apparatus based on a Dynamic Vision Sensor (DVS). The method includes the following operations of: acquiring a plurality of image frames by a DVS; and, detecting the image frames by a recurrent coherent network to acquire a candidate box for objects to be detected, wherein the recurrent coherent network comprising a frame detection network model and a candidate graph model. By using a new recurrent coherent detection network, a bounding box for an object to be detected is fast detected from the data acquired by a DVS. The detection speed is improved greatly while ensuring the detection accuracy.

Abstract: An image processing apparatus includes a calculator configured to calculate a respective position offset for each of a plurality of candidate areas in a second frame based on a position of a basis image in a first frame and a determiner configured to determine a final selected area that includes a target in the second frame based on a respective weight allocated to each of the plurality of candidate areas and the calculated respective position offset.

Abstract: Exemplary embodiments provide an image vision processing method, device and equipment and relate to: determining parallax and depth information of event pixel points in a dual-camera frame image acquired by Dynamic Vision Sensors; determining multiple neighboring event pixel points of each non-event pixel point in the dual-camera frame image; determining, according to location information of each neighboring event pixel point of each non-event pixel point, depth information of the non-event pixel point; and performing processing according to the depth information of each pixel point in the dual-camera frame image. Since non-event pixel points are not required to participate in the matching of pixel points, even if it is difficult to distinguish between the non-event pixel points or the non-event pixel points are occluded, depth information of the non-event pixel points can be accurately determined according to the location information of neighboring event pixel points.

Abstract: A method to analyze a facial image includes: inputting a facial image to a residual network including residual blocks that are sequentially combined and arranged in a direction from an input to an output; processing the facial image using the residual network; and acquiring an analysis map from an output of an N-th residual block among the residual blocks using a residual deconvolution network, wherein the residual network transfers the output of the N-th residual block to the residual deconvolution network, and N is a natural number that is less than a number of all of the residual blocks, and wherein the residual deconvolution network includes residual deconvolution blocks that are sequentially combined, and the residual deconvolution blocks correspond to respective residual blocks from a first residual block among the residual blocks to the N-th residual block.

Abstract: A user trigger intent determining method and apparatus is disclosed. The user trigger intent determining apparatus may obtain a first face image, obtain a second face image after a visual stimuli object is displayed, and determine a final gaze location by correcting a first gaze location estimated from the first face image based on a second gaze location estimated from the second face image.

Abstract: A processor-implemented method includes acquiring, by a processor, a first undirected graph and a second undirected graph, generating, by the processor, a first lattice for the first undirected graph and a second lattice for the second undirected graph; matching, by the processor, the first lattice and the second lattice based on a first global structure of the first lattice and a second global structure of the second lattice, the first global structure corresponding to nodes of the first undirected graph and the second global structure corresponding to nodes of the second undirected graph, and processing the first undirected graph and the second undirected graph based on a result of the matching of the first lattice and the second lattice.

Abstract: A processor implemented method of processing a facial expression image, the method includes acquiring an expression feature of each of at least two reference facial expression images; generating a new expression feature based on an interpolation value of the expression feature; and adjusting a target facial expression image based on the new expression feature and creating a new facial expression image.

Abstract: An image processing apparatus, includes an image classifier configured to determine whether an input image is a low-quality image or a high-quality image; and an image evaluator configured to determine a first predetermined number of clearest images from a plurality of low-quality images determined by the image classifier.

Abstract: A method of detecting a target includes generating an image pyramid based on an image on which a detection is to be performed; classifying candidate areas in the image pyramid using a cascade neural network; and determining a target area corresponding to a target included in the image based on the plurality of candidate areas, wherein the cascade neural network includes a plurality of neural networks, and at least one neural network among the neural networks includes parallel sub-neural networks.

Abstract: A method of detecting a target includes determining a quality type of a target image captured using a camera, determining a convolutional neural network of a quality type corresponding to the quality type of the target image in a database comprising convolutional neural networks, determining a detection value of the target image based on the convolutional neural network of the corresponding quality type, and determining whether a target in the target image is a true target based on the detection value of the target image.

Abstract: The disclosure provides an object detection method and apparatus based on a Dynamic Vision Sensor (DVS). The method includes the following operations of: acquiring a plurality of image frames by a DVS; and, detecting the image frames by a recurrent coherent network to acquire a candidate box for objects to be detected, wherein the recurrent coherent network comprising a frame detection network model and a candidate graph model. By using a new recurrent coherent detection network, a bounding box for an object to be detected is fast detected from the data acquired by a DVS. The detection speed is improved greatly while ensuring the detection accuracy.

Abstract: A method to analyze a facial image includes: inputting a facial image to a residual network including residual blocks that are sequentially combined and arranged in a direction from an input to an output; processing the facial image using the residual network; and acquiring an analysis map from an output of an N-th residual block among the residual blocks using a residual deconvolution network, wherein the residual network transfers the output of the N-th residual block to the residual deconvolution network, and N is a natural number that is less than a number of all of the residual blocks, and wherein the residual deconvolution network includes residual deconvolution blocks that are sequentially combined, and the residual deconvolution blocks correspond to respective residual blocks from a first residual block among the residual blocks to the N-th residual block.

Abstract: Exemplary embodiments provide an image vision processing method, device and equipment and relate to: determining parallax and depth information of event pixel points in a dual-camera frame image acquired by Dynamic Vision Sensors; determining multiple neighboring event pixel points of each non-event pixel point in the dual-camera frame image; determining, according to location information of each neighboring event pixel point of each non-event pixel point, depth information of the non-event pixel point; and performing processing according to the depth information of each pixel point in the dual-camera frame image. Since non-event pixel points are not required to participate in the matching of pixel points, even if it is difficult to distinguish between the non-event pixel points or the non-event pixel points are occluded, depth information of the non-event pixel points can be accurately determined according to the location information of neighboring event pixel points.

Abstract: An image processing apparatus includes a calculator configured to calculate a respective position offset for each of a plurality of candidate areas in a second frame based on a position of a basis image in a first frame and a determiner configured to determine a final selected area that includes a target in the second frame based on a respective weight allocated to each of the plurality of candidate areas and the calculated respective position offset.