Patch-based vehicle logo detection with patch intensity and weight matrix
来源期刊：中南大学学报(英文版)2015年第12期
论文作者：LIU Hai-ming HUANG Zhang-can Ahmed Mahgoub Ahmed Talab
文章页码：4679 - 4686
Key words：vehicle logo detection; prior knowledge; gradient extraction; patch intensity; weight matrix; background removing
Abstract: A patch-based method for detecting vehicle logos using prior knowledge is proposed. By representing the coarse region of the logo with the weight matrix of patch intensity and position, the proposed method is robust to bad and complex environmental conditions. The bounding-box of the logo is extracted by a thershloding approach. Experimental results show that 93.58% location accuracy is achieved with 1100 images under various environmental conditions, indicating that the proposed method is effective and suitable for the location of vehicle logo in practical applications.
LIU Hai-ming(刘海明)1, HUANG Zhang-can(黄樟灿)1, Ahmed Mahgoub Ahmed Talab1, 2
(1. School of Science, Wuhan University of Technology, Wuhan 430070, China;
2. College of Engineering, Elimam ELMahdi University, Kosti, Sudan)
Abstract:A patch-based method for detecting vehicle logos using prior knowledge is proposed. By representing the coarse region of the logo with the weight matrix of patch intensity and position, the proposed method is robust to bad and complex environmental conditions. The bounding-box of the logo is extracted by a thershloding approach. Experimental results show that 93.58% location accuracy is achieved with 1100 images under various environmental conditions, indicating that the proposed method is effective and suitable for the location of vehicle logo in practical applications.
Key words:vehicle logo detection; prior knowledge; gradient extraction; patch intensity; weight matrix; background removing
