Paper Info
Title
CrowdHuman: A Benchmark for Detecting Human in a Crowd.
Abstract
Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowd scenarios are still under-represented in current human detection benchmarks. In this paper, we introduce a new dataset, called CrowdHuman, to better evaluate detectors in crowd scenarios. The CrowdHuman dataset is large, rich-annotated and contains high diversity. There are a total of $470K$ human instances from the train and validation subsets, and $~22.6$ persons per image, with various kinds of occlusions in the dataset. Each human instance is annotated with a head bounding-box, human visible-region bounding-box and human full-body bounding-box. Baseline performance of state-of-the-art detection frameworks on CrowdHuman is presented. The cross-dataset generalization results of CrowdHuman dataset demonstrate state-of-the-art performance on previous dataset including Caltech-USA, CityPersons, and Brainwash without bells and whistles. We hope our dataset will serve as a solid baseline and help promote future research in human detection tasks.
Year
Venue
Field
2018
arXiv: Computer Vision and Pattern Recognition
Computer science,Artificial intelligence,Machine learning
DocType
Volume
Citations 
Journal
abs/1805.00123
7
PageRank 
References 
Authors
0.46
13
7
Name
Order
Citations
PageRank
Shuai Shao1262.03
Zijian Zhao270.46
Boxun Li357131.13
Tete Xiao4123.93
Gang Yu538219.85
Xiangyu Zhang613044437.66
Jian Sun725842956.90