An inexpensive monocular vision system for tracking humans in industrial environments
Robotics and Automation（2013）
摘要
We report on a novel vision-based method for reliable human detection from vehicles operating in industrial environments in the vicinity of workers. By exploiting the fact that reflective vests represent a standard safety equipment on most industrial worksites, we use a single camera system and active IR illumination to detect humans by identifying the reflective vest markers. Adopting a sparse feature based approach, we classify vest markers against other reflective material and perform supervised learning of the object distance based on local image descriptors. The integration of the resulting per-feature 3D position estimates in a particle filter finally allows to perform human tracking in conditions ranging from broad daylight to complete darkness.
更多查看译文
关键词
cameras,computer vision,feature extraction,image classification,infrared imaging,learning (artificial intelligence),object detection,object tracking,occupational safety,particle filtering (numerical methods),pose estimation,active IR illumination,human detection,human tracking,industrial environments,industrial worksites,local image descriptors,monocular vision system,object distance,particle filter,per-feature 3D position estimates,reflective material,reflective vest marker identification,single camera system,sparse feature-based approach,standard safety equipment,supervised learning,vest marker classification,vision-based method
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要