Error Compensation Heatmap Decoding for Human Pose Estimation

Yang Feiyu,Chen Yu,Zhang Yao,Mo Yaoyang,Qian Beibei,Xiao Zhenzhong,Pan Zhe,Jin Wu,Song Zhan,Zhang Min

doi:10.1109/access.2021.3105553

Abstract

As a fundamental component of heatmap-based human pose estimation methods, heatmap decoding is to transform heatmaps into joint coordinates. We found that previous heatmap decoding methods generally ignored the effect of systematic errors introduced by the resolution increaseing operations in the network decoder. This work fills the gap by taking the systematic errors in heatmap decoding into consideration. We proposed a fast method to reduces the systematic and random errors in one shot by error compensation. The proposed method outperforms the previous best method on the COCO and the MPII datasets while being over 2 times faster. Extensive experiments with different networks, resolutions, metrics and datasets have proved the rationality of the proposed idea.

Highlights

I N recent years, the rapid advance in deep learning [1] has tremendously boosted human pose estimation
Different from other computer vision tasks, like image classification [7]–[9], object detection [10]–[12] and semantic segmentation [13], [14], human pose estimation is more sensitive to heatmap decoding because it employs metrics that conduct point to point comparison of human joints
We propose a method to decode the heatmap with error compensation

Summary

Introduction

I N recent years, the rapid advance in deep learning [1] has tremendously boosted human pose estimation. Among different learning-based approaches, the heatmapbased methods perform the best [2]–[6]. Heatmap decoding is to estimate joint coordinates from the predicted heatmaps. Different from other computer vision tasks, like image classification [7]–[9], object detection [10]–[12] and semantic segmentation [13], [14], human pose estimation is more sensitive to heatmap decoding because it employs metrics that conduct point to point comparison of human joints. Human pose estimation generally require real-time performance (30 FPS) on embedded devices. Developing accurate and fast heatmap decoding methods is of significant importance

Methods

Results

Conclusion