Crowd Counting by Adapting Convolutional Neural Networks with Side Information

11/21/2016
by   Di Kang, et al.
0

Computer vision tasks often have side information available that is helpful to solve the task. For example, for crowd counting, the camera perspective (e.g., camera angle and height) gives a clue about the appearance and scale of people in the scene. While side information has been shown to be useful for counting systems using traditional hand-crafted features, it has not been fully utilized in counting systems based on deep learning. In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN), where the convolutional filter weights adapt to the current scene context via the side information. In particular, we model the filter weights as a low-dimensional manifold, parametrized by the side information, within the high-dimensional space of filter weights. With the help of side information and adaptive weights, the ACNN can disentangle the variations related to the side information, and extract discriminative features related to the current context. Since existing crowd counting datasets do not contain ground-truth side information, we collect a new dataset with the ground-truth camera angle and height as the side information. On experiments in crowd counting, the ACNN improves counting accuracy compared to a plain CNN with a similar number of parameters. We also apply ACNN to image deconvolution to show its potential effectiveness on other computer vision applications.

READ FULL TEXT

page 2

page 5

page 7

page 8

research
10/23/2020

AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting

We address the problem of image-based crowd counting. In particular, we ...
research
02/23/2020

Multi-Stream Networks and Ground-Truth Generation for Crowd Counting

Crowd scene analysis has received a lot of attention recently due to the...
research
03/18/2020

3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels

Crowd counting has been studied for decades and a lot of works have achi...
research
10/26/2017

Deep Spatial Regression Model for Image Crowd Counting

Computer vision techniques have been used to produce accurate and generi...
research
02/01/2020

Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning

We consider the problem of few-shot scene adaptive crowd counting. Given...
research
02/16/2020

A Real-Time Deep Network for Crowd Counting

Automatic analysis of highly crowded people has attracted extensive atte...
research
08/17/2020

An Improved Dilated Convolutional Network for Herd Counting in Crowded Scenes

Crowd management technologies that leverage computer vision are widespre...

Please sign up or login with your details

Forgot password? Click here to reset