PETS2021: Through-foliage detection and tracking challenge and evaluation

Luis Patino, Jonathan Boyle, James M. Ferryman, Jonas Auer, Julian Pegoraro, Roman P. Pflugfelder, Mertcan Cokbas, Janusz Konrad, Prakash Ishwar, Giulia Slavic, Lucio Marcenaro, Yifan Jiang, Youngsaeng Jin, Hanseok Ko, Guangliang Zhao, Guy Ben-Yosef, Jianwei Qiu

Abstract: This paper presents the outcomes of the PETS2021 challenge held in conjunction with AVSS2021 and sponsored by the EU FOLDOUT project. The challenge comprises the publication of a novel video surveillance dataset on through-foliage detection, the defined challenges addressing person detection and tracking in fragmented occlusion scenarios, and quantitative and qualitative performance evaluation of challenge results submitted by six worldwide participants. The results show that while several detection and tracking methods achieve overall good results, through-foliage detection and tracking remains a challenging task for surveillance systems especially as it serves as the input to behaviour (threat) recognition.