ARCN: A Real-time Attention-based Network for Crowd Counting from Drone Images

Nag, Subhrajit and Khandelwal, Yash and Mittal, Sparsh and Mohan, C. Krishna and Qin, A. Kai (2021) ARCN: A Real-time Attention-based Network for Crowd Counting from Drone Images. In: 18th IEEE India Council International Conference, INDICON 2021, 19 December 2021 through 21 December 2021, Guwahati.

Text
Proceedings_of_the_2021_IEEE_18th .pdf - Published Version
Restricted to Registered users only
Download (660kB) | Request a copy

Abstract

Crowd counting is the process of counting or estimating the number of individuals in a crowd. There has been a rapid surge in the amount of Unmanned Aerial Vehicles (UAV) images over the last few years. However, efficient crowd counting techniques from UAV images have hardly come into the focus of the research community. Crowd counting from UAV images has its unique challenges compared to crowd counting from images in natural scenes. Moreover, solving the problem in real-time makes the task even harder.In this paper, we introduce an attention-based encoder-decoder model called Attention-based Real-time CrowdNet (ARCN). ARCN is a computationally efficient density estimation-based crowd counting model. It can perform crowd-counting from UAV images in real-time with high accuracy. Ours is the first work that proposes a real-time density map estimation and crowd counting model from drone-based images. The key idea of our work is to add 'Convolution Block Attention Module' (CBAM) blocks in-between the bottleneck layers of the MobileCount architecture. The proposed ARCN model achieves an MAE of 19.9 and MSE of 27.7 on the DroneCrowd dataset. Also, on NVIDIA GTX 2080 Ti GPU, ARCN has a processing speed of 48 FPS, making it a real-time technique. The pre-trained model is available at https://bit.ly/3na7LUy © 2021 IEEE.

[error in script]

IITH Creators:

IITH Creators	ORCiD
Mohan, C. Krishna	https://orcid.org/0000-0002-7316-0836

Item Type:

Conference or Workshop Item (Paper)

Uncontrolled Keywords:

Computationally efficient; Counting models; Counting techniques; Density estimation; Encoder-decoder; High-accuracy; Natural scenes; Real- time; Research communities; Vehicle images

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

05 Aug 2022 04:40

Last Modified:

05 Aug 2022 04:40

URI:

http://raiithold.iith.ac.in/id/eprint/10100