Multicamera pedestrian detection using logic minimization
作者：
Highlights：
• The first work of using logic minimization method in multi-camera pedestrian detection.
• It greatly reduces the search space for an optimized solution and can be applied in the general data association problem.
• Its efficiency benefits real-time video surveillance applications.
• The 2D template matching is decomposed into 1D operations and the contribution of background pixels is rewarded.
• It outperforms benchmark non-deep or deep multicamera/monocular algorithms for pedestrian detection.
摘要
•The first work of using logic minimization method in multi-camera pedestrian detection.•It greatly reduces the search space for an optimized solution and can be applied in the general data association problem.•Its efficiency benefits real-time video surveillance applications.•The 2D template matching is decomposed into 1D operations and the contribution of background pixels is rewarded.•It outperforms benchmark non-deep or deep multicamera/monocular algorithms for pedestrian detection.
论文关键词：Pedestrian detection,Multicamera,Homography,Logic minimization,Video surveillance
论文评审过程：Received 4 May 2020, Revised 26 August 2020, Accepted 13 October 2020, Available online 14 October 2020, Version of Record 30 January 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107703
