Viola-Jones approach to object detection is by far the most widely used object detection technique because of speed of detection in images with clutter. SVM-based object detection techniques have the disadvantage of slow detection speeds because of exhaustive window search. Appearance-based detection techniques do not generalize well in the presence of pose variations. In this paper, we propose a feature-based technique which classifies salient-points as belonging to object or background classes and performs object detection based on classified key points. Since keypoints are sparse, the technique is very fast. The use of SIFT descriptor provides invariance to scale and pose changes.
机译:通过局部和全局流形正规化SVM模型进行显着目标检测
机译:使用Fuz-SVM分类器的基于局部特征描述符的目标人脸活动度检测
机译:基于使用FUZ-SVM分类器的本地特征描述符的对象情感检测
机译:使用基于本地特征的SVMS的快速对象检测
机译:使用快速准确的变化检测和阈值检测视频对象
机译:通过集成多种检测方法和本地装配使用SVMerge增强了结构变异和断点检测
机译:用于对象检测及其后的Exemplar-sVm集合
机译:基于NN和sVm的电磁反散射方法在埋地物体在线检测中的比较研究。