Beijing Jiaotong University

Taiyuan University of Science and Technoloy

Shanxi Zhishi Haotai Technology Co., Ltd

Huihui Bai

Yao Zhao

Jiapeng Jia

Yunchao Wei

Peihao Li

Anhong Wang

Disclosed is a multi-angle image semantic segmentation method for cadmium zinc telluride chips, belonging to the field of image quality augmentation. Firstly, construction of an n+1 dataset is performed by using acquire CZT images, and then pixel-level and latent-level knowledge representation is performed through a Pixel Aggregation Network PAN and a Latent Aggregation Network LAN in a Progressive Complementary Knowledge Aggregation network PCKA, which ultimately improves the quality and speed of CZT image segmentation. The method is suitable for applications that require multi-angle image acquisition and semantic segmentation, such as semiconductor material segmentation.

Multi-angle image semantic segmentation method for cadmium zinc telluride chips

A multi-description-based video encoding and decoding method, device and system, comprising the following steps: separating odd frames from even frames to generate and encode an initial description; utilizing the correlation of macro-block levels between different descriptions to generate and encode the side information of different modes; and transmitting via a channel. The present invention may be used in a real-time video transmission scenario.

Multi-description-based video encoding and decoding method, device and system

Growing community of inventors

Beijing, China

Huihui Bai