KIT | KIT-Bibliothek | Impressum | Datenschutz

VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results

Du, Dawei; Wen, Longyin; Zhu, Pengfei; Fan, Heng; Hu, Qinghua; Ling, Haibin; Shah, Mubarak; Pan, Junwen; Al-Ali, Ali; Mohamed, Amr; Imene, Bakour; Dong, Bin; Zhang, Binyu; Nesma, Bouchali Hadia; Xu, Chenfeng; Duan, Chenzhen; Castiello, Ciro; Mencar, Corrado; Liang, Dingkang; Krüger, Florian; ... mehr

Abstract:
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by 3, 360 images, including 2, 460 images for training, and 900 images for testing. Specifically, we manually annotate persons with points in each video frame. There are 14 algorithms from 15 institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: http://www.aiskyeye.com/.



Originalveröffentlichung
DOI: 10.1007/978-3-030-66823-5_41
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Buchaufsatz
Publikationsdatum 03.01.2020
Sprache Englisch
Identifikator ISBN: 978-3-030-66822-8
ISSN: 0302-9743, 1611-3349
KITopen-ID: 1000128099
Erschienen in Computer Vision – ECCV 2020 Workshops. Ed.: A. Bartoli. Vol. 4
Verlag Springer Nature Switzerland AG
Seiten 675–691
Serie Lecture Notes in Computer Science ; 12538
Schlagwörter VisDrone, Crowd counting, Challenge, Benchmark
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page