BROWSE
Detail
Conference Paper
A Lazy Decision Approach based on Ternary Thresholding for Robust Target Object Detection
Cited 0 time in 
Share 
Share
- Authors
- Jae-Yeong Lee, Wonpil Yu, Jungwon Hwang, ChangHwan Kim
- Issue Date
- 2014-06
- Citation
- International Conference on Robotics and Automation (ICRA) 2014, pp.3924-3929
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- One of the main problems of binary classification of overlapping distributions is that there always exist misclassification errors with any value of threshold. In this paper, we propose a novel lazy decision approach for robust object detection and tracking, where decision on an uncertain observation whose evaluation lies between low and high thresholds is postponed until a clear evidence appears. As a practical application of the proposed approach, we present a sensor fusion pedestrian detection system for safe navigation of UGVs in driving environment. We combine a laser-based detection of target candidates and vision-based evaluation within the proposed lazy decision framework. Experimental results on real test data demonstrate effectiveness of the proposed approach, showing significant improvement of precision-recall performance.
- KSP Keywords
- Binary Classification, Decision framework, Intrusion detection system(IDS), Object Detection and Tracking, Pedestrian detection system, Precision and recall, Safe navigation, Target object detection, Test data, Uncertain Observation, driving environment