Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features

TL;DR

This paper introduces a pedestrian detection method that uses spatially pooled features and direct optimization of the partial AUC, achieving state-of-the-art results on multiple benchmarks.

Contribution

It presents a novel feature extraction approach with spatial pooling and optimizes detection performance directly on the most relevant ROC range.

Findings

Lowered average miss rate on INRIA from 13% to 11%

Improved detection on ETH from 41% to 37%

Enhanced results on TUD-Brussels and Caltech-USA datasets

Abstract

We propose a simple yet effective approach to the problem of pedestrian detection which outperforms the current state-of-the-art. Our new features are built on the basis of low-level visual features and spatial pooling. Incorporating spatial pooling improves the translational invariance and thus the robustness of the detection process. We then directly optimise the partial area under the ROC curve (\pAUC) measure, which concentrates detection performance in the range of most practical importance. The combination of these factors leads to a pedestrian detector which outperforms all competitors on all of the standard benchmark datasets. We advance state-of-the-art results by lowering the average miss rate from $13\%$ to $11\%$ on the INRIA benchmark, $41\%$ to $37\%$ on the ETH benchmark, $51\%$ to $42\%$ on the TUD-Brussels benchmark and $36\%$ to $29\%$ on the Caltech-USA benchmark.