CaltechAUTHORS
  A Caltech Library Service

Pedestrian Detection: An Evaluation of the State of the Art

Dollár, Piotr and Wojek, Christian and Schiele, Bernt and Perona, Pietro (2012) Pedestrian Detection: An Evaluation of the State of the Art. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34 (4). pp. 743-761. ISSN 0162-8828. https://resolver.caltech.edu/CaltechAUTHORS:20120320-093151300

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20120320-093151300

Abstract

Pedestrian detection is a key problem in computer vision, with several applications that have the potential to positively impact quality of life. In recent years, the number of approaches to detecting pedestrians in monocular images has grown steadily. However, multiple data sets and widely varying evaluation protocols are used, making direct comparisons difficult. To address these shortcomings, we perform an extensive evaluation of the state of the art in a unified framework. We make three primary contributions: 1) We put together a large, well-annotated, and realistic monocular pedestrian detection data set and study the statistics of the size, position, and occlusion patterns of pedestrians in urban scenes, 2) we propose a refined per-frame evaluation methodology that allows us to carry out probing and informative comparisons, including measuring performance in relation to scale and occlusion, and 3) we evaluate the performance of sixteen pretrained state-of-the-art detectors across six data sets. Our study allows us to assess the state of the art and provides a framework for gauging future efforts. Our experiments show that despite significant progress, performance still has much room for improvement. In particular, detection is disappointing at low resolutions and for partially occluded pedestrians.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/TPAMI.2011.155DOIArticle
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2011 IEEE. Manuscript received 2 Nov. 2010; revised 17 June 2011; accepted 3 July 2011; published online 28 July 2011. Recommended for acceptance by G. Mori. P. Perona and P. Dollár acknowledge the support of ONR MURI Grants #N00014-06-1-0734 and #1015-G-NA127. This project was also partially supported by Nissan Motor Co., Ltd. The authors thank Seigo Watanabe of Nissan for collecting the video and for many useful discussions. They would also like to thank all authors that made their detection code available.
Funders:
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-06-1-0734
Office of Naval Research (ONR)1015-G-NA127
Nissan Motor Co,. Ltd.UNSPECIFIED
Subject Keywords:Pedestrian detection; object detection; benchmark; evaluation; data set; Caltech Pedestrian data set
Issue or Number:4
Record Number:CaltechAUTHORS:20120320-093151300
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20120320-093151300
Official Citation:Dollar, P.; Wojek, C.; Schiele, B.; Perona, P.; , "Pedestrian Detection: An Evaluation of the State of the Art," Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol.34, no.4, pp.743-761, April 2012 doi: 10.1109/TPAMI.2011.155 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5975165&isnumber=6155150
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:29782
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:20 Mar 2012 21:25
Last Modified:30 Mar 2020 23:47

Repository Staff Only: item control page