CrowdHuman: A Benchmark for Detecting Human in a Crowd

04/30/2018
by   Shuai Shao, et al.
0

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.

READ FULL TEXT

page 2

page 4

page 7

page 8

research
08/23/2020

Visible Feature Guidance for Crowd Pedestrian Detection

Heavy occlusion and dense gathering in crowd scene make pedestrian detec...
research
09/22/2019

Double Anchor R-CNN for Human Detection in a Crowd

Detecting human in a crowd is a challenging problem due to the uncertain...
research
03/15/2019

GolfDB: A Video Database for Golf Swing Sequencing

The golf swing is a complex movement requiring considerable full-body co...
research
09/18/2023

NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarios

With the increasing reliance on small Unmanned Aerial Systems (sUAS) for...
research
10/16/2020

A Simple Baseline for Pose Tracking in Videos of Crowded Scenes

This paper presents our solution to ACM MM challenge: Large-scale Human-...
research
03/17/2022

deepNIR: Datasets for generating synthetic NIR images and improved fruit detection system using deep learning techniques

This paper presents datasets utilised for synthetic near-infrared (NIR) ...
research
09/13/2019

MinneApple: A Benchmark Dataset for Apple Detection and Segmentation

In this work, we present a new dataset to advance the state-of-the-art i...

Please sign up or login with your details

Forgot password? Click here to reset