An Objective Method for Pedestrian Occlusion Level Classification

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 interoccluding pedestrians.

The Impact of Partial Occlusion on Pedestrian Detectability

“…The dataset is sourced from three main categories of images: 1) The "occluded body" subset of the partial re-identification dataset "Partial ReID" provided by Zheng et al [40], 2) The Partial ReID "whole body" subset [40] with custom superimposed occlusions and 3) Images collated from publicly available sources including [6] [8] [9] [41]. All images are annotated using the objective occlusion level classification method described in [38]. Complex cases at very high occlusion rates were manually verified using the method of 2D body surface area estimation presented in [6].…”

“…Gilroy et al [38] describes an objective method of occlusion level annotation and visible body surface area estimation of partially occluded pedestrians. Keypoint detection is applied to identify semantic body parts and findings are cross-referenced with a visibility score and the pedestrian mask in order to confirm the presence or occlusion of each semantic part.…”

E-Scooter Rider Detection and Classification in Dense Urban Environments

“…A diverse mix of images are used ensure that a wide variety [36]. All images are annotated using the objective occlusion level classification method described in [33]. Complex cases at very high occlusion rates were manually verified using the method of 2D body surface area estimation presented in [9].…”

“…Gilroy et al [32] present an objective benchmark for partially occluded pedestrian detection, containing 820 pedestrian instances under progressive levels of occlusion from 0-99%. Images are annotated using the objective method of occlusion level annotation described in [33]. Keypoint detection is used to identify semantic body parts and findings are cross-referenced with a visibility score and the pedestrian mask in order to confirm the presence or occlusion of each semantic part.…”