Fully Convolutional Neural Networks for Crowd Segmentation

Abstract

In this paper, we propose a fast fully convolutional neural network (FCNN) for crowd segmentation. By replacing the fully connected layers in CNN with 1 by 1 convolution kernels, FCNN takes whole images as inputs and directly outputs segmentation maps by one pass of forward propagation. It has the property of translation invariance like patch-by-patch scanning but with much lower computation cost. Once FCNN is learned, it can process input images of any sizes without warping them to a standard size. These attractive properties make it extendable to other general image segmentation problems. Based on FCNN, a multi-stage deep learning is proposed to integrate appearance and motion cues for crowd segmentation. Both appearance filters and motion filers are pretrained stage-by-stage and then jointly optimized. Different combination methods are investigated. The effectiveness of our approach and component-wise analysis are evaluated on two crowd segmentation datasets created by us, which include image frames from 235 and 11 scenes, respectively. They are currently the largest crowd segmentation datasets and will be released to the public.

9 pages,7 figures

References in corpus (3)

• Going Deeper with Convolutions
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Rich feature hierarchies for accurate object detection and semantic segmentation

Cited by in corpus (17)

• A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
• Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
• Crowd Behavior Analysis: A Review where Physics meets Biology
• Learning Independent Instance Maps for Crowd Localization
• SideEye: A Generative Neural Network Based Simulator of Human Peripheral Vision
• PDANet: Pyramid Density-aware Attention Net for Accurate Crowd Counting
• LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
• Towards Using Count-level Weak Supervision for Crowd Counting
• Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
• Scene Invariant Crowd Segmentation and Counting Using Scale-Normalized Histogram of Moving Gradients (HoMG)
• Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks
• Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods
• A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View
• A Miniaturized Semantic Segmentation Method for Remote Sensing Image
• Pixel-wise Crowd Understanding via Synthetic Data
• Automated Lane Detection in Crowds using Proximity Graphs
• MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes