Chinese Academy of Sciences

Watrix Technology

Samsung Electronics Co., Ltd.

Yongzhen Huang

Liang Wang

Tieniu Tan

Zifeng Wu

Chang Kyu Choi

Jaejoon Han

Jungbae Kim

Byungin Yoo

Kaiqi Huang

A method of segmenting an object from an image includes receiving an input image including an object; generating an output image corresponding to the object from the input image using an image model; and extracting an object image from the output image.

Apparatus and method to segment object from image

The present disclosure relates to a gait recognition method based on deep learning, which comprises recognizing an identity of a person in a video according to the gait thereof through dual-channel convolutional neural networks sharing weights by means of the strong learning capability of the deep learning convolutional neural network. Said method is quite robust to gait changes across a large view, which can effectively solve the problem of low precision in cross-view gait recognition existing with the prior art gait recognition technology. Said method can be widely used in scenarios having video monitors, such as security monitoring in airports and supermarkets, person recognition, criminal detection, etc.

Gait recognition method based on deep learning

A human-shape image segmentation method comprising: extracting multi-scale context information for all first pixel points for training a human-shape image; sending image blocks of all scales of all the first pixel points into a same convolution neural network to form a multi-channel convolutional neural network group, wherein each channel corresponds to image blocks of one scale; training the neural network group using a back propagation algorithm to obtain human-shape image segmentation training model data; extracting multi-scale context information for all second pixels points for testing the human-shape image; sending image blocks of different scales of each of the second pixel points into a neural network channel corresponding to the human-shape image segmentation training model, wherein if said first probability is larger than said second probability, the second pixel points belong to the human-shape region, otherwise, the second pixel points are outside of the human-shape region. The human-shape image segmentation method is fast in image segmentation speed and high in accuracy.

Human-shape image segmentation method

A shape classification method based on the topological perceptual organization (TPO) theory, comprising steps of: extracting boundary points of shapes (S1); constructing topological space and computing the representation of extracted boundary points (S2); extracting global features of shapes from the representation of boundary points in topological space (S3); extracting local features of shapes from the representation of boundary points in Euclidean space (S4); combining global features and local features through adjusting the weight of local features according to the performance of global features (S5); classifying shapes using the combination of global features and local features (S6). The invention is applicable for intelligent video surveillance, e.g., objects classification and scene understanding. The invention can also be used for the automatic driving system wherein robust recognition of traffic signs plays an important role in enhancing the intelligence of the system.

Shape classification method based on the topological perceptual organization theory

A semiconductor laser with an equilateral triangle micro optical resonator has an output waveguide connected to the resonator for realizing directional emission, and the laser wafer structure is the slab waveguide constituted by lower cladding layer, active region and the upper cladding layer. The outer region of the equilateral triangle is etched to the lower cladding layer or substrate, while the unetched equilateral triangle region is used as the resonator, and the triangular sides serve as the reflecting mirrors. On one of the vertices or the sides of the triangle resonator connected or coupled an output waveguide can form an edge emission semiconductor laser and array having directive light emission. If the output waveguide is intersected with an incline, enabling the output light to deflect 90&deg; then surface emission output can be acquired, thereby a surface emission semiconductor laser and array is produced, and a multi-wavelength semiconductor laser or array can be made by the equilateral triangle micro optical resonators of various dimensions.

Growing community of inventors

Beijing, China

Yongzhen Huang