Strengthening the Effectiveness of Pedestrian Detection with Spatially Pooled Features
This work improves pedestrian detection for applications like autonomous driving and surveillance, though it is incremental as it builds on existing low-level features and spatial pooling methods.
The paper tackles pedestrian detection by introducing spatially pooled features and optimizing the partial AUC, achieving state-of-the-art results with miss rate reductions from 13% to 11% on INRIA, 41% to 37% on ETH, 51% to 42% on TUD-Brussels, and 36% to 29% on Caltech-USA benchmarks.
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.