How Far are We from Solving Pedestrian Detection?

Citations Over TimeTop 1% of 2016 papers

Abstract

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 characterise both localisation and background-versusforeground errors. To address localisation 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 sanitised 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 sanitised set of training and test annotations.

Related Papers

• → Pedestrian Detection Based on Improved SSD Object Detection Algorithm(2022)7 cited
• → Multiple-part based Pedestrian Detection using Interfering Object Detection(2007)9 cited
• → Detection of Pedestrian Actions Based on Deep Learning Approach(2019)8 cited
• → Small-size pedestrian detection in large scene based on fast R-CNN(2018)1 cited
• → An Improved Location Model for Pedestrian Detection(2019)1 cited