Unified multi-spectral pedestrian detection based on probabilistic fusion networks
作者：
Highlights：
• We propose a unified CNN architecture for the task of multispectral pedestrian detection and formulate the entire network to be learned in an end-to-end manner.
• Unlike existing multispectral fusion techniques, we comprehensively utilize color, thermal, color-thermal fusion features to maximize detection performance by synergistically using their detection probabilities with channel weighting fusion (CWF) and accumulated probability fusion (APF).
• The proposed system significantly reduces the missing rate of baseline method by 5.60%, yielding a 31.36% overall missing rate on the KAIST multispectral pedestrian benchmark
摘要
•We propose a unified CNN architecture for the task of multispectral pedestrian detection and formulate the entire network to be learned in an end-to-end manner.•Unlike existing multispectral fusion techniques, we comprehensively utilize color, thermal, color-thermal fusion features to maximize detection performance by synergistically using their detection probabilities with channel weighting fusion (CWF) and accumulated probability fusion (APF).•The proposed system significantly reduces the missing rate of baseline method by 5.60%, yielding a 31.36% overall missing rate on the KAIST multispectral pedestrian benchmark
论文关键词：Multi-spectral sensor fusion,Pedestrian detection,Channel weighting fusion,Probabilistic fusion
论文评审过程：Received 10 May 2017, Revised 19 January 2018, Accepted 4 March 2018, Available online 13 March 2018, Version of Record 21 March 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.03.007
