Next Article in Journal
WiFi-Based Real-Time Calibration-Free Passive Human Motion Detection
Next Article in Special Issue
Moving Object Detection on a Vehicle Mounted Back-Up Camera
Previous Article in Journal
Design, Implementation and Evaluation of an Indoor Navigation System for Visually Impaired People
Previous Article in Special Issue
Robust Road Condition Detection System Using In-Vehicle Standard Sensors
Open AccessArticle

Far-Infrared Based Pedestrian Detection for Driver-Assistance Systems Based on Candidate Filters, Gradient-Based Feature and Multi-Frame Approval Matching

School of Software Engineering, South China University of Technology, No. 382 Waihuan East Rd., Guangzhou 510006, China
*
Author to whom correspondence should be addressed.
Academic Editor: Felipe Jimenez
Sensors 2015, 15(12), 32188-32212; https://doi.org/10.3390/s151229874
Received: 13 October 2015 / Revised: 23 November 2015 / Accepted: 9 December 2015 / Published: 21 December 2015
(This article belongs to the Special Issue Sensors in New Road Vehicles)
Far-infrared pedestrian detection approaches for advanced driver-assistance systems based on high-dimensional features fail to simultaneously achieve robust and real-time detection. We propose a robust and real-time pedestrian detection system characterized by novel candidate filters, novel pedestrian features and multi-frame approval matching in a coarse-to-fine fashion. Firstly, we design two filters based on the pedestrians’ head and the road to select the candidates after applying a pedestrian segmentation algorithm to reduce false alarms. Secondly, we propose a novel feature encapsulating both the relationship of oriented gradient distribution and the code of oriented gradient to deal with the enormous variance in pedestrians’ size and appearance. Thirdly, we introduce a multi-frame approval matching approach utilizing the spatiotemporal continuity of pedestrians to increase the detection rate. Large-scale experiments indicate that the system works in real time and the accuracy has improved about 9% compared with approaches based on high-dimensional features only. View Full-Text
Keywords: pedestrian detection; far-infrared video; advanced driver-assistance systems; gradient-based feature; candidate filters pedestrian detection; far-infrared video; advanced driver-assistance systems; gradient-based feature; candidate filters
Show Figures

Figure 1

MDPI and ACS Style

Wang, G.; Liu, Q. Far-Infrared Based Pedestrian Detection for Driver-Assistance Systems Based on Candidate Filters, Gradient-Based Feature and Multi-Frame Approval Matching. Sensors 2015, 15, 32188-32212.

Show more citation formats Show less citations formats

Article Access Map

1
Back to TopTop