Detection of the movements of persons from a sparse sequence of TV images
作者:
Highlights:
•
摘要
This paper describes a method for detecting persons walking in a passageway from two consecutive TV images at long intervals. The method consists of the following steps: (1) extracting candidate areas for persons from TV images by image processing; (2) detecting persons in the areas on the basis of their shapes and sizes, and locating them in a passageway; (3) finding the correspondence of persons between two images on the basis of their locations. Special hardware called DIP was employed for high speed image processing.
论文关键词:Motion estimation,Robot vision,Movement of persons,Autonomous vehicle,High speed image processing,Consecutive TV image,Inverse perspective transformation,Occlusion problem
论文评审过程:Received 17 February 1984, Accepted 2 May 1984, Available online 19 May 2003.
论文官网地址:https://doi.org/10.1016/0031-3203(85)90046-9