A Caltech Library Service

Pedestrian Detection: A Benchmark

Dollár, Piotr and Wojek, Christian and Schiele, Bernt and Perona, Pietro (2009) Pedestrian Detection: A Benchmark. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE , Piscataway, NJ, pp. 304-311. ISBN 978-1-4244-3991-1.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Pedestrian detection is a key problem in computer vision, with several applications including robotics, surveillance and automotive safety. Much of the progress of the past few years has been driven by the availability of challenging public datasets. To continue the rapid rate of innovation, we introduce the Caltech Pedestrian Dataset, which is two orders of magnitude larger than existing datasets. The dataset contains richly annotated video, recorded from a moving vehicle, with challenging images of low resolution and frequently occluded people. We propose improved evaluation metrics, demonstrating that commonly used per-window measures are flawed and can fail to predict performance on full images. We also benchmark several promising detection systems, providing an overview of state-of-the-art performance and a direct, unbiased comparison of existing methods. Finally, by analyzing common failure cases, we help identify future research directions for the field.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2009 IEEE. We would like to thank Eugene Bart, Ryan Gomes and Mohamed Aly for valuable help and feedback, and Irina Bart for her many long hours labeling small pedestrians. This work was partially supported by the Office of Naval Research grant N00014–06-1–0734 and a gift from an automobile manufacturer who wishes to remain anonymous.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014–06-1–0734
Record Number:CaltechAUTHORS:20180615-160221639
Persistent URL:
Official Citation:P. Dollar, C. Wojek, B. Schiele and P. Perona, "Pedestrian detection: A benchmark," 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, 2009, pp. 304-311. doi: 10.1109/CVPR.2009.5206631
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:87172
Deposited By: George Porter
Deposited On:15 Jun 2018 23:06
Last Modified:03 Oct 2019 19:53

Repository Staff Only: item control page