An Objective Method for Pedestrian Occlusion Level Classification

TL;DR

This paper introduces an objective, automated method for classifying pedestrian occlusion levels in images, improving the accuracy and consistency of ground truth annotations for pedestrian detection benchmarks.

Contribution

The paper presents a novel approach combining visible keypoints and 2D body surface area estimation to objectively classify pedestrian occlusion levels, reducing subjectivity in annotations.

Findings

Method accurately reflects pixel-wise occlusion levels

Effective across various occlusion types including edge cases

Improves consistency of ground truth annotations

Abstract

Pedestrian detection is among the most safety-critical features of driver assistance systems for autonomous vehicles. One of the most complex detection challenges is that of partial occlusion, where a target object is only partially available to the sensor due to obstruction by another foreground object. A number of current pedestrian detection benchmarks provide annotation for partial occlusion to assess algorithm performance in these scenarios, however each benchmark varies greatly in their definition of the occurrence and severity of occlusion. In addition, current occlusion level annotation methods contain a high degree of subjectivity by the human annotator. This can lead to inaccurate or inconsistent reporting of an algorithm's detection performance for partially occluded pedestrians, depending on which benchmark is used. This research presents a novel, objective method for pedestrian occlusion level classification for ground truth annotation. Occlusion level classification is achieved through the identification of visible pedestrian keypoints and through the use of a novel, effective method of 2D body surface area estimation. Experimental results demonstrate that the proposed method reflects the pixel-wise occlusion level of pedestrians in images and is effective for all forms of occlusion, including challenging edge cases such as self-occlusion, truncation and inter-occluding pedestrians.