CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

02/27/2018
by   Yuhong Li, et al.
0

We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace pooling operations. CSRNet is an easy-trained model because of its pure convolutional structure. To our best acknowledge, CSRNet is the first implementation using dilated CNNs for crowd counting tasks. We demonstrate CSRNet on four datasets (ShanghaiTech dataset, the UCF_CC_50 dataset, the WorldEXPO'10 dataset, and the UCSD dataset) and we deliver the state-of-the-art performance on all the datasets. In the ShanghaiTech Part_B dataset, we significantly achieve the MAE which is 47.3 lower than the previous state-of-the-art method. We extend the applications for counting other objects, such as the vehicle in TRANCOS dataset. Results show that CSRNet significantly improves the output quality with 15.4 the previous state-of-the-art approach.

READ FULL TEXT

page 7

page 8

page 11

page 12

page 13

page 14

page 15

page 16

research
03/19/2023

Wheat Head Counting by Estimating a Density Map with Convolutional Neural Networks

Wheat is one of the most significant crop species with an annual worldwi...
research
08/17/2020

An Improved Dilated Convolutional Network for Herd Counting in Crowded Scenes

Crowd management technologies that leverage computer vision are widespre...
research
06/11/2023

Hinting Pipeline and Multivariate Regression CNN for Maize Kernel Counting on the Ear

Maize is a highly nutritional cereal widely used for human and animal co...
research
06/29/2023

BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models

With the increasing popularity and the increasing size of vision transfo...
research
08/10/2022

Multi-scale Feature Aggregation for Crowd Counting

Convolutional Neural Network (CNN) based crowd counting methods have ach...
research
11/19/2017

MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images

This paper is aimed at creating extremely small and fast convolutional n...
research
01/17/2020

Methodology for Efficient CNN Architectures in Profiling Attacks

The side-channel community recently investigated a new approach, based o...

Please sign up or login with your details

Forgot password? Click here to reset