CrowdHuman: A Benchmark for Detecting Human in a Crowd

TL;DR

The paper introduces CrowdHuman, a large, diverse dataset designed to evaluate human detection in crowded scenes with occlusions, aiming to advance research and improve detection performance.

Contribution

It presents a new comprehensive dataset for human detection in crowded scenarios, with detailed annotations and baseline evaluations, addressing a gap in existing benchmarks.

Findings

CrowdHuman contains 470K human instances with high diversity.

State-of-the-art detectors perform well on CrowdHuman and generalize across datasets.

The dataset improves evaluation of occlusion handling in crowded human detection.

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.