【摘要】 提出一种基于Gabor滤波器和支持向量机(SVM)的红外车辆检测方法。该方法首先应用阈值分割并结合边检测确定候选区域;其次应用Gabor滤波器对选定的车辆和背景样本集进行特征提取,训练SVM分类器。这里提出一种特征加权技术,即根据特征矢量中邻近分量的离散程度对其自身进行加权;最后应用SVM进行分类检测,以判断候选区域内是否存在车辆。实验数据表明了该方法的实用性和可行性。更多还原

【Abstract】 This paper puts forward a novel infrared vehicle detection algorithm with Gabor filter and Support Vector Machines (SVM) classifier here. It consists of two main steps: driven hypothesis generation and hypothesis verification. In the hypothesis generation step, possible image locations where vehicles might be present are hypothesized by pixel-dependent threshold selection and edge detection. Hypothesis verification verifies those hypothesis using Gabor filter for feature extraction and SVM for classification. A feature weighting technique is proposed, that is, the extracted features are weighted according to their neighboring features degree of dispersion. This method is tested under four different videos, illustrating good performance.更多还原