Human Orientation Estimation under Partial Observation

TL;DR

This paper introduces Part-HOE, a novel method for human orientation estimation from partial observations, improving accuracy and confidence estimation, and demonstrating benefits in robot person following tasks.

Contribution

The paper proposes Part-HOE and a confidence-aware approach to enhance human orientation estimation under partial observation conditions.

Findings

Improved accuracy in orientation estimation under partial observation.

Enhanced confidence estimation aligning with prediction reliability.

Better performance in robot person following tasks.

Abstract

Reliable Human Orientation Estimation (HOE) from a monocular image is critical for autonomous agents to understand human intention. Significant progress has been made in HOE under full observation. However, the existing methods easily make a wrong prediction under partial observation and give it an unexpectedly high confidence. To solve the above problems, this study first develops a method called Part-HOE that estimates orientation from the visible joints of a target person so that it is able to handle partial observation. Subsequently, we introduce a confidence-aware orientation estimation method, enabling more accurate orientation estimation and reasonable confidence estimation under partial observation. The effectiveness of our method is validated on both public and custom-built datasets, and it shows great accuracy and reliability improvement in partial observation scenarios. In particular, we show in real experiments that our method can benefit the robustness and consistency of the Robot Person Following (RPF) task.