Too Far to See? Not Really! --- Pedestrian Detection with Scale-aware Localization Policy

TL;DR

This paper introduces a scale-aware pedestrian detection method that leverages multi-layer neural representations and active localization to significantly improve detection accuracy, especially for small, far-away pedestrians.

Contribution

It proposes an active pedestrian detector that explicitly uses multi-layer CNN features and coordinate transformations to better detect pedestrians of varying sizes, especially small ones.

Findings

Achieves lower detection errors on benchmark datasets.

Significantly improves detection of far-scale pedestrians.

Reduces miss rate by 18.68% compared to state-of-the-art.

Abstract

A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparate spatial scales exhibit distinct visual appearances, we propose in this paper an active pedestrian detector that explicitly operates over multiple-layer neuronal representations of the input still image. More specifically, convolutional neural nets such as ResNet and faster R-CNNs are exploited to provide a rich and discriminative hierarchy of feature representations as well as initial pedestrian proposals. Here each pedestrian observation of distinct size could be best characterized in terms of the ResNet feature representation at a certain layer of the hierarchy; Meanwhile, initial pedestrian proposals are attained by faster R-CNNs techniques, i.e. region proposal network and follow-up region of interesting pooling layer employed right after the specific ResNet convolutional layer of interest, to produce joint predictions on the bounding-box proposals' locations and categories (i.e. pedestrian or not). This is engaged as input to our active detector where for each initial pedestrian proposal, a sequence of coordinate transformation actions is carried out to determine its proper x-y 2D location and layer of feature representation, or eventually terminated as being background. Empirically our approach is demonstrated to produce overall lower detection errors on widely-used benchmarks, and it works particularly well with far-scale pedestrians. For example, compared with 60.51% log-average miss rate of the state-of-the-art MS-CNN for far-scale pedestrians (those below 80 pixels in bounding-box height) of the Caltech benchmark, the miss rate of our approach is 41.85%, with a notable reduction of 18.68%.