Filtered Channel Features for Pedestrian Detection
This work addresses pedestrian detection for autonomous driving and surveillance, offering incremental improvements over existing methods.
The paper tackles pedestrian detection by proposing a unifying framework based on filtered channel features, achieving top performance on Caltech and KITTI datasets with HOG+LUV features, and reaching 93% recall at 1 FPPI on Caltech when adding optical flow.
This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combination with a boosted decision forest. Based on this observation we propose a unifying framework and experimentally explore different filter families. We report extensive results enabling a systematic analysis. Using filtered channel features we obtain top performance on the challenging Caltech and KITTI datasets, while using only HOG+LUV as low-level features. When adding optical flow features we further improve detection quality and report the best known results on the Caltech dataset, reaching 93% recall at 1 FPPI.