Search International and National Patent Collections

1. (WO2018076212) DE-CONVOLUTIONAL NEURAL NETWORK-BASED SCENE SEMANTIC SEGMENTATION METHOD

Pub. No.:    WO/2018/076212    International Application No.:    PCT/CN2016/103425
Publication Date: Fri May 04 01:59:59 CEST 2018 International Filing Date: Thu Oct 27 01:59:59 CEST 2016
IPC: G06T 7/00
Applicants: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES
中国科学院自动化研究所
Inventors: HUANG, Kaiqi
黄凯奇
ZHAO, Xin
赵鑫
CHENG, Yanhua
程衍华
Title: DE-CONVOLUTIONAL NEURAL NETWORK-BASED SCENE SEMANTIC SEGMENTATION METHOD
Abstract:
Disclosed is a de-convolutional neural network-based scene semantic segmentation method. The method comprises the following steps of: S1, extracting intensive feature expression for a scene picture by using a full-convolutional neural network; and S2, carrying out up-sampling learning and object edge optimization on the intensive feature expression obtained in the step S1 through utilizing a locally sensitive de-convolutional neural network by means of a local affinity matrix of the picture, so as to obtain a score map of the picture and then realize refined scene semantic segmentation. Through the locally sensitive de-convolutional neural network, the sensitivity, to the local edge, of the full-convolutional neural network is strengthened by utilizing local bottom layer information, so that scene segmentation with higher precision is obtained.