Babu Sam, D and Venkatesh Babu, R (2018) Top-down feedback for crowd counting convolutional neural network. In: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, 2 - 7 February 2018, New Orleans, pp. 7323-7330.
PDF
AAAI 2018_7323-7330_2018.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy |
Abstract
Counting people in dense crowds is a demanding task even for humans. This is primarily due to the large variability in appearance of people. Often people are only seen as a bunch of blobs. Occlusions, pose variations and background clutter further compound the difficulty. In this scenario, identifying a person requires larger spatial context and semantics of the scene. But the current state-of-the-art CNN regressors for crowd counting are feedforward and use only limited spatial context to detect people. They look for local crowd patterns to regress the crowd density map, resulting in false predictions. Hence, we propose top-down feedback to correct the initial prediction of the CNN. Our architecture consists of a bottom-up CNN along with a separate top-down CNN to generate feedback. The bottom-up network, which regresses the crowd density map, has two columns of CNN with different receptive fields. Features from various layers of the bottom-up CNN are fed to the top-down network. The feedback, thus generated, is applied on the lower layers of the bottom-up network in the form of multiplicative gating. This masking weighs activations of the bottom-up network at spatial as well as feature levels to correct the density prediction. We evaluate the performance of our model on all major crowd datasets and show the effectiveness of top-down feedback.
Item Type: | Conference Paper |
---|---|
Publication: | 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 |
Publisher: | AAAI press |
Additional Information: | The copyright for this article belongs to the AAAI press. |
Keywords: | Forecasting; Neural networks; Semantics, Background clutter; Convolutional neural network; Density prediction; Pose variation; Receptive fields; Spatial context; State of the art; Top-down feedback, Feedback |
Department/Centre: | Division of Electrical Sciences > Computer Science & Automation |
Date Deposited: | 18 Aug 2022 06:13 |
Last Modified: | 18 Aug 2022 06:13 |
URI: | https://eprints.iisc.ac.in/id/eprint/75956 |
Actions (login required)
View Item |