Going beyond the regression paradigm with accurate dot prediction for dense crowds

Sam, DB and Vishwanath Peri, S and Mukuntha, NS and Venkatesh Babu, R (2020) Going beyond the regression paradigm with accurate dot prediction for dense crowds. In: 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020, 1-5 March 2020, Snowmass Village; United States, pp. 2853-2861.

PDF IEEE_WIN_CON_APP_COM_VIS_2853-2861_2020.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

We present an alternative to the paradigm of density regression widely being employed for tackling crowd counting. In the prevalent regression approach, a model is trained for mapping images to its crowd density rather than counting by detecting every person. This framework is motivated from the difficulty to discriminate humans in highly dense crowds where unfavorable perspective, occlusion and clutter are prevalent. Though regression methods estimate overall crowd counts pretty well, localization of individual persons suffers and varies considerably across the entire density spectrum. Moreover, individual detection of people aids more explainable practical systems than predicting blind crowd count or density map. Hence, we move away from density regression and reformulate the task as localized dot prediction in dense crowds. Our dot detection model, DD-CNN, is trained for pixel-wise binary classification to detect people instead of regressing local crowd density. In order to handle severe scale variation and detect people of all scales with accurate dots, we use a novel multi-scale architecture which does not require any ground truth scale information. This training regime, which incorporates top-down feedback, helps our model to localize people in sparse as well as dense crowds. Our model delivers superior counting performance on major crowd datasets. We also evaluate on some additional metrics and evidence superior localization of the dot detection formulation. © 2020 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	cited By 0; Conference of 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 ; Conference Date: 1 March 2020 Through 5 March 2020; Conference Code:159803
Keywords:	Computer vision; Forecasting, Binary classification; Crowd density; Density spectrum; Detection models; Highly dense; Practical systems; Regression method; Top-down feedback, Regression analysis
Department/Centre:	Division of Interdisciplinary Sciences > Computational and Data Sciences
Date Deposited:	20 Nov 2020 06:27
Last Modified:	20 Nov 2020 06:27
URI:	http://eprints.iisc.ac.in/id/eprint/65620

Actions (login required)

View Item