Effective license plate detection using fast candidate region selection and covariance feature based filtering
AVSS(2014)
摘要
This paper presents a new real-time license plate detection method aiming for fast and accurate detection in live videos. Compared with the previous learning based detection schemes which scan multi-scale images with sliding window, our method takes a cascaded scheme. In the first stage, candidate plate regions are detected based on edge density in reduced image of very low resolution for guaranteeing high speed. In the second stage, the candidate regions are verified using a linear SVM classifier with covariance features for high accuracy. Experimental results on two datasets collected from practical traffic surveillance videos indicate the robustness of our method, which is relatively invariant to scaling, rotation, blurring and illumination. This method takes only 10 msec for detection on a 768 × 576 image.
更多查看译文
关键词
fast candidate region selection,traffic engineering computing,automobiles,character recognition,covariance feature based filtering,image recognition,edge density,linear SVM classifier,live video,learning based detection,traffic surveillance video,filtering theory,cascaded method,license plate detection,support vector machines,video surveillance
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络