CARF-Net: CNN attention and RNN fusion network for video-based person reidentification

Kajal Kansal; Subramanyam Venkata; Dilip K. Prasad; Mohan Kankanhalli

doi:10.1117/1.JEI.28.2.023036

25 April 2019 CARF-Net: CNN attention and RNN fusion network for video-based person reidentification

Kajal Kansal, Subramanyam Venkata, Dilip K. Prasad, Mohan Kankanhalli

Author Affiliations +

Journal of Electronic Imaging, Vol. 28, Issue 2, 023036 (April 2019). https://doi.org/10.1117/1.JEI.28.2.023036

Abstract

Video-based person reidentification is a challenging and important task in surveillance-based applications. Toward this, several shallow and deep networks have been proposed. However, the performance of existing shallow networks does not generalize well on large datasets. To improve the generalization ability, we propose a shallow end-to-end network which incorporates two stream convolutional neural networks, discriminative visual attention and recurrent neural network with triplet and softmax loss to learn the spatiotemporal fusion features. To effectively use both spatial and temporal information, we apply spatial, temporal, and spatiotemporal pooling. In addition, we contribute a large dataset of airborne videos for person reidentification, named DJI01. It includes various challenging conditions, such as occlusion, illuminationchanges, people with similar clothes, and the same people on different days. We perform elaborate qualitative and quantitative analyses to demonstrate the robust performance of the proposed model.

Citation Download Citation

Kajal Kansal, Subramanyam Venkata, Dilip K. Prasad, and Mohan Kankanhalli "CARF-Net: CNN attention and RNN fusion network for video-based person reidentification," Journal of Electronic Imaging 28(2), 023036 (25 April 2019). https://doi.org/10.1117/1.JEI.28.2.023036

Received: 27 December 2018; Accepted: 2 April 2019; Published: 25 April 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available