ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술대회 Vehicle Color Recognition via Representative Color Region Extraction and Convolutional Neural Network
Cited 9 time in scopus Download 8 time Share share facebook twitter linkedin kakaostory
김광주, 김병근, 임길택, 정윤수, 송윤정, 이수인, 최두현
International Conference on Ubiquitous and Future Networks (ICUFN) 2018, pp.89-94
18ZD1100, 대경권 지역산업 기반 ICT융합기술 고도화 지원사업, 문기영
Vehicle color recognition is one of the important part in ITS (Intelligent Transportation System). This paper presents a new vehicle color classification technique for CCTV systems via representative color region extraction and Convolutional Neural Net (CNN). The Harris corner point detection method is used to generate a probability map of a representative color region. From the probability map, point are randomly selected to generate an input image for CNN. Finally, we trained CNN model with it. In order to evaluate the performance of the proposed method, we acquired a total of 5,941 images from camera on highway. We conducted 5-fold cross validation for performance evaluation. Our vehicle color recognition method performance of about 96.1 % was shown.
KSP 제안 키워드
5-Fold cross validation, CCTV systems, CNN model, Classification techniques, Convolution neural network(CNN), Convolutional neural net, Cross validation(CV), Detection Method, Harris corner point detection, Intelligent Transport Systems(ITS), Method performance