One of the critical challenges of object counting is the dramatic scale variations, which is introduced by arbitrary perspectives. We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs. The reverse perspective network explicitly evaluates the perspective distortions, and efficiently corrects the distortions by uniformly warping the input images. Then the proposed network delivers images with similar instance scales to the regressor. Thus the regression network doesn't need multi-scale receptive fields to match the various scales. Besides, to further solve the scale problem of more congested areas, we enhance the corresponding regions of ground-truth with the evaluation errors. Then we force the regressor to learn from the augmented ground-truth via an adversarial process. Furthermore, to verify the proposed model, we collected a vehicle counting dataset based on Unmanned Aerial Vehicles (UAVs). The proposed dataset has fierce scale variations. Extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts.

Reverse perspective network for perspective-aware object counting / Yang, Yifan; Li, Guorong; Wu, Zhe; Su, Li; Huang, Qingming; Sebe, Nicu. - (2020), pp. 4373-4382. ((Intervento presentato al convegno IEEE CVPR 2020 tenutosi a online nel 14th-19th June 2020 [10.1109/CVPR42600.2020.00443].

Reverse perspective network for perspective-aware object counting

Sebe, Nicu
2020

Abstract

One of the critical challenges of object counting is the dramatic scale variations, which is introduced by arbitrary perspectives. We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs. The reverse perspective network explicitly evaluates the perspective distortions, and efficiently corrects the distortions by uniformly warping the input images. Then the proposed network delivers images with similar instance scales to the regressor. Thus the regression network doesn't need multi-scale receptive fields to match the various scales. Besides, to further solve the scale problem of more congested areas, we enhance the corresponding regions of ground-truth with the evaluation errors. Then we force the regressor to learn from the augmented ground-truth via an adversarial process. Furthermore, to verify the proposed model, we collected a vehicle counting dataset based on Unmanned Aerial Vehicles (UAVs). The proposed dataset has fierce scale variations. Extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts.
Proceedings: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Piscataway, NJ
IEEE
978-1-7281-7168-5
Yang, Yifan; Li, Guorong; Wu, Zhe; Su, Li; Huang, Qingming; Sebe, Nicu
Reverse perspective network for perspective-aware object counting / Yang, Yifan; Li, Guorong; Wu, Zhe; Su, Li; Huang, Qingming; Sebe, Nicu. - (2020), pp. 4373-4382. ((Intervento presentato al convegno IEEE CVPR 2020 tenutosi a online nel 14th-19th June 2020 [10.1109/CVPR42600.2020.00443].
File in questo prodotto:
File Dimensione Formato  
Yang_Reverse_Perspective_Network_for_Perspective-Aware_Object_Counting_CVPR_2020_paper.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.08 MB
Formato Adobe PDF
5.08 MB Adobe PDF Visualizza/Apri
Reverse_Perspective_Network_for_Perspective-Aware_Object_Counting.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.58 MB
Formato Adobe PDF
1.58 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11572/284528
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 50
  • ???jsp.display-item.citation.isi??? 42
social impact