Histogram Encoding of SIFT Based Visual Words for Target Recognition in Infrared Images

Several algorithms for target recognition in infrared images were proposed by reasearchers to develop an efficient advanced driver assistance systems. In this paper, an approach based on bag of features framework, SIFT and SVM, is evaluated for target recognition problem. First, SIFT extractor is applied to all the training set. Then, features were clustered by K-means; the cluster centers are regarded as visual words to form a visual vocabulary. For each image, a histogram of quantized local descriptors is computed according to the frequency of visual words in each sub-region, which are obtained by the spatial pyramid matching technique. The generated feature vector will be mapped for later use as an input to SVM. Extensive experiments are carried out in FLIR dataset. Our experimental results show that the proposed method exceeds the-state-of-art in target recognition on two class FLIR dataset with 3% improvement in accuracy classification.