TraCount: A Deep Convolutional Neural Network for Highly Overlapping Vehicle Counting

Surya, Shiv and Babu, Venkatesh R (2016) TraCount: A Deep Convolutional Neural Network for Highly Overlapping Vehicle Counting. In: 10th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), DEC 18-22, 2016, Indian Inst Technol, Guwahati, INDIA. (In Press)

PDF 10th_I_C_C_V_G_I_P_2016.pdf - Published Version Restricted to Registered users only Download (979kB) | Request a copy

Abstract

We propose a novel deep framework, TraCount, for highly overlapping vehicle counting in congested traffic scenes. TraCount uses multiple fully convolutional(FC) sub-networks to predict the density map for a given static image of a traffic scene. The different FC sub-networks provide a range in size of receptive fields that enable us to count vehicles whose perspective effect varies significantly in a scene due to the large visual field of surveillance cameras. The predictions of different FC sub-networks are fused by weighted averaging to obtain a final density map. We show that TraCount outperforms the state of the art methods on the challenging TRANCOS dataset that has a total of 46796 vehicles annotated across 1244 images.

Item Type:	Conference Proceedings
Additional Information:	Copy right for this article belongs to the ASSOC COMPUTING MACHINERY, 1515 BROADWAY, NEW YORK, NY 10036-9998 USA
Department/Centre:	Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre
Date Deposited:	15 Jul 2017 07:42
Last Modified:	15 Jul 2017 07:42
URI:	http://eprints.iisc.ac.in/id/eprint/57433

Actions (login required)

View Item