Combining multiple complementary features for pedestrian and motorbike detection

Cheng En Wu, Yi Ming Chan, Li Chen Fu, Pei Yung Hsiao, Shin Shinh Huang, Han Hsuan Chen, Pang Ting Huang, Shao Chung Hu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Pedestrian and motorbike detection are two important areas in obstacle detection on road. Most state-of-the-art detectors are constructed with new features or learning methods on Histograms of Oriented Gradients (HOG) features. However, few researches focus on analyzing which features are complementary for the aforementioned detection. According to our study of pedestrians and motorbikes, there are three major properties including shape, texture, and self-similarity. We design a Shape, Texture and Self-Similarity (STSS) feature for these properties. The features we have employed here are HOG, Local Oriented Pattern (LOP), Color Self-Similarity (CSS), and Texture Self-Similarity (TSS). The STSS detector which combines Shape, Texture, and Self-Similarty features achieves 31% log-average miss rate. At the same time, 93% detection rate at 10-4 false positives per window on INRIA Person Dataset has also been concluded. Besides, we also have evaluated our detector on Caltech Motorbike Dataset and Caltech Pedestrian Dataset, and found the detector outperforms HOG detector in these datasets. As a result, we have shown that these features are complement to each other and useful in pedestrian and motorbike detection.

Original languageEnglish
Title of host publication2013 16th International IEEE Conference on Intelligent Transportation Systems
Subtitle of host publicationIntelligent Transportation Systems for All Modes, ITSC 2013
Pages1358-1363
Number of pages6
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 16th International IEEE Conference on Intelligent Transportation Systems: Intelligent Transportation Systems for All Modes, ITSC 2013 - The Hague, Netherlands
Duration: 06 10 201309 10 2013

Publication series

NameIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

Conference

Conference2013 16th International IEEE Conference on Intelligent Transportation Systems: Intelligent Transportation Systems for All Modes, ITSC 2013
Country/TerritoryNetherlands
CityThe Hague
Period06/10/1309/10/13

Fingerprint

Dive into the research topics of 'Combining multiple complementary features for pedestrian and motorbike detection'. Together they form a unique fingerprint.

Cite this