摘要
本文利用SURF特征进行目标跟踪,通过匹配模板图像和视频序列中各个运动对象的SURF特征确定目标位置。文中用于目标匹配的特征是图像中的局部性特征,具有尺度不变性和旋转不变性,对缩放、小视角改变、噪声、亮度变化具有很好的适应性。实验表明该方法是一种简洁有效的目标跟踪识别方法。
In this paper SURF features are used for object tracking.The object location is determined by matching the SURF features of the template image and each sub-image containing moving object in video sequence.In this paper local feature is used for object matching,with the scale and rotation invariance.The features have very good adaptability for zooming,small perspective changes,noise,and brightness changes.Experimental results show that this is a simple and efficient object tracking and identification method.
出处
《中国体视学与图像分析》
2011年第1期28-32,共5页
Chinese Journal of Stereology and Image Analysis
