Canon Kabushiki Kaisha

Dongchao Wen

Tsewei Chen

Wei Tao

Xian Li

Hongxing Gao

Junjie Liu

Qi Hu

Weihong Deng

Jiani Hu

Dongyue Zhao

Shiting Wang

Kotaro Kitajima

Yong Jiang

Lifeng Xu

Naoko Watazawa

Fuguo Zhu

Deyu Wang

Qiao Wang

Donghui Sun

The present disclosure discloses an apparatus and a method for detecting a facial pose, an image processing system, and a storage medium. The apparatus comprises: an obtaining unit to obtain at least three keypoints of at least one face from an input image based on a pre-generated neural network, wherein coordinates of the keypoints obtained via a layer in the neural network for obtaining coordinates are three-dimensional coordinates; and a determining unit to determine, for the at least one face, a pose of the face based on the obtained keypoints, wherein the determined facial pose includes at least an angle. According to the present disclosure, the accuracy of the three-dimensional coordinates of the facial keypoints can be improved, thus the detection precision of a facial pose can be improved.

Apparatus and method for detecting facial pose, image processing system, and storage medium

The present disclosure relates to training method and apparatus for an object recognition model. There provides a training sample optimization apparatus for a neural network model for object recognition, comprising: for each training sample in a training sample database, a fluctuation determination unit configured to determine a fluctuation of model prediction of the training sample relative to a corresponding labeled identity of the training sample in a case of training the neural network model; and an optimization unit configured to determine whether the training sample can be used for training of the neural network model in the next training epoch, based on the fluctuation of the training sample.

Method and apparatus for training an object recognition model

The present disclosure provides a training and application method of a multi-layer neural network model, apparatus and a storage medium. In a forward propagation of the multi-layer neural network model, the number of input feature maps is expanded and a data computation is performed by using the expanded input feature maps.

Training and application method of a multi-layer neural network model, apparatus and storage medium

The present invention relates to method and apparatus for training a neural network for object recognition. A training method which includes inputting a training image set containing an object to be recognized, dividing the image samples in the training image set into simple samples and hard samples, for each kind of the image sample and the variation image sample, performing, a transitive transfer, calculating a distillation loss of the transferred student feature of the image sample relative to a teacher feature extracted from corresponding image sample of the other kind, classifying, the image sample, and calculating a classification loss of the image sample, calculating a total loss related to the training image set, and updating parameters of the neural network according to the calculated total loss.

Training method and training apparatus for a neural network for object recognition

The present disclosure provides a training and application method of a multi-layer neural network model, apparatus and storage medium. A number of channels of a filter in at least one convolutional layer in the multi-layer neural network model is expanded, and a convolution computation is performed by using the filter after expanding the number of channels, so that the performance of the network model does not degrade while simplifying the network model.

A method and an apparatus for optimizing and applying a multilayer neural network model, and a storage medium are provided. The optimization method includes, dividing out at least one sub-structure from the multilayer neural network model to be optimized, wherein a tail layer of the divided sub-structure is a quantization layer, and transferring operation parameters in layers other than the quantization layer to the quantization layer for each of the divided sub-structures and updating quantization threshold parameters in the quantization layer based on the transferred operation parameters. When a multilayer neural network model optimized based on the optimization method is operated, the necessary processor resources can be reduced.

Method and apparatus for optimizing and applying multilayer neural network model, and storage medium

An object tracking apparatus for a sequence of images, wherein a plurality of tracks have been obtained for the sequence of images, and each of the plurality of tracks is obtained by detecting an object in several images included in the sequence of images. The apparatus comprises matching track pair determining unit configured to determine a matching track pair from the plurality of tracks, wherein the matching track pair comprise a previous track and a subsequent track which correspond to the same object and are discontinuous, and combining unit configured to combine the previous track and the subsequent track included in the matching track pair.

Object tracking method and apparatus

A training and application method for a neural network model is provided. The training method determines the first network model to be trained and sets a downscaling layer for at least one layer in the first network model, wherein the number of filters and filter kernel of the downscaling layer are identical to those of layers to be trained in the second network model. Filter parameters of the downscaling layer are transmitted to the second network model as training information. By this training method, training can also be performed even when the scale of the layer for training in the first network model is different from that of the layers to be trained in the second network model, and the amount of lost data is small.

Training and application method of neural network model, apparatus, system and storage medium

The present invention relates to the fast multi-object detection and tracking system. According to the system of the present invention, only a few frames are to be detected and the other frames are split into different size of steady motion segments in a binary way, and then the system of the present invention can predicted accurately. The system can help to achieve high tracking speed with multi-persons in high-definition videos and gain high accuracy as well.

Fast multi-object detection and tracking system

One of the aspects of the present invention discloses an image processing apparatus and an image processing method. The image processing apparatus comprises: an image acquisition unit configured to acquire an image containing a face; a region location unit configured to locate at least one region which represents attributes of the face in the acquired image; a feature extraction unit configured to extract features from the located regions; and a feature integration unit configured to integrate the features of the located regions which are symmetrical with each other based on symmetry of the face. According to the present invention, the dimension of the features used for image processing could be reduced and the image processing accuracy could be maintained as much as possible.

Image processing apparatus and image processing method

An apparatus includes a unit configured to acquire an object shape regression model, which comprises an average object shape, a plurality of regression functions and a plurality of feature selection maps; a unit configured to set an initial object shape for the object image based on the average object shape; a unit configured to calculate at least one feature vector with respect to a plurality of feature points; a unit configured, for each coordinate of the plurality of feature points, to select feature fragments from the calculated feature vector based on a corresponding one of the plurality of feature selection maps and assemble the feature fragments into a sub feature vector; and a unit configured, for at least one coordinate of at least one feature point, to predict a coordinate increment based on the corresponding sub feature vector and a corresponding one of the plurality of regression functions.

Growing community of inventors

Beijing, China

Dongchao Wen