计算机应用与软件2017，Vol.34Issue(3)：127-130,4.DOI:10.3969/j.issn.1000-386x.2017.03.023
基于二进制光流描述子的运动目标提议
MOTION OBJECT PROPOSAL BASED ON BINARY OPTICAL FLOW DESCRIPTOR
摘要
Abstract
In order to reduce the redundance of proposal windows in video object detection, a novel binary optical flow descriptor is proposed to achieve separate proposals for connected objects.By analysing the local motion coherence of objects, we design the binary optical flow descriptor, construct the object proposal model and then use linear SVM classifier to solve motion object proposal parameters.To make full use of the speed advantage of binary and/or calculation, the motion object proposal parameters are represented approximately in binary to complete object proposal tasks quickly and efficiently.The experiment on the Caltech Pedestrians dataset is carried out, and a small number of high-quality motion object proposal windows are generated quickly.Experimental results show that the proposed method is superior to current object proposal methods.关键词
目标提议/局部运动一致性/光流/二进制描述子Key words
Object proposal/Local motion coherence/Optical flow/Binary descriptor分类
信息技术与安全科学引用本文复制引用
李洋,吴克伟,谢昭,孙永宣..基于二进制光流描述子的运动目标提议[J].计算机应用与软件,2017,34(3):127-130,4.基金项目
国家自然科学基金项目(61503111,61501467). （61503111,61501467）
