Images

OCHuman

Introduced in Pose2Seg: Detection Free Human Instance Segmentation

About this Dataset

This dataset focuses on heavily occluded human with comprehensive annotations including bounding-box, humans pose and instance mask. This dataset contains 13,360 elaborately annotated human instances within 5081 images. With average 0.573 MaxIoU of each person, OCHuman is the most complex and challenging dataset related to human.

Source: https://github.com/liruilong940607/OCHumanApi Image Source: https://github.com/liruilong940607/OCHumanApi

Source: Pose2Seg: Detection Free Human Instance Segmentation

Dataset Variants

OCHuman

Papers1

Pose2Seg: Detection Free Human Instance Segmentation

This paper introduces a new benchmark "Occluded Human (OCHuman)", which focuses on occluded humans with comprehensive annotations including bounding-box, human pose and instance masks, and demonstrates that this pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.

Dataset Loaders

EDIT

🔥

open-mmlab/mmpose

pytorch

📦

liruilong940607/OCHumanApi

none

Tasks

EDIT

Pose Estimation 2D Human Pose Estimation Multi-Person Pose Estimation Keypoint Detection Human Instance Segmentation Pose-Based Human Instance Segmentation

Similar Datasets