How Far are We from Solving Pedestrian Detection?
This work addresses pedestrian detection for autonomous driving and safety systems, offering incremental improvements through error analysis and data sanitization.
The paper investigates the gap between state-of-the-art pedestrian detectors and a perfect single-frame detector by analyzing errors on the Caltech dataset, reporting top performance and providing sanitized annotations.
Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the "perfect single frame detector". We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech dataset), and by manually clustering the recurrent errors of a top detector. Our results characterize both localization and background-versus-foreground errors. To address localization errors we study the impact of training annotation noise on the detector performance, and show that we can improve even with a small portion of sanitized training data. To address background/foreground discrimination, we study convnets for pedestrian detection, and discuss which factors affect their performance. Other than our in-depth analysis, we report top performance on the Caltech dataset, and provide a new sanitized set of training and test annotations.