基于改进SIFT算子的动态障碍物检测方法

Detection of Moving Targets in Auxiliary Driving System Based on Improved SIFT Descriptor

针对行车辅助驾驶系统在进行动态障碍物检测时遇到的背景复杂和实时性要求,提出了一种基于快速鲁棒的动态目标假设检测算法,算法首先采用相邻帧间特征点位置估计改进SIFT匹配算子,实现全局背景运动补偿参数快速估计,然后利用三帧差分法对图像处理后,通过改进背景方差估计,改善传统假设检验方法对图像边缘目标漏检的问题,进一步提高动态目标检测的准确性。实验表明,算法不仅保持了SIFT算子的优越性能,提高了参数估计精确性,而且极大地提高了特征配准和检测速度,满足系统的实时性要求。

In view of the complex background and real time requirement of the dynamic target detection of the vehicle driving system, a fast robust target detection algorithm is proposed. Firstly, the position estimation of feature points between adjacent frames are used to improve the SIFT method to achieve fast parameter estimation for global background motion compensation. And then, by improving the background variance estimation in the three frame difference image, the moving targets closing to the edge of the image can be detected exactly which will be missed in the traditional Hypothesis Testing method. Experimental results demonstrate that not only the superior performance of the SIFF operator is maintained, and the accuracy of parameter estimation is improved in the proposed algorithm, but also the speech of the feature points matching and targets detection is improved greatly, meeting the real-time requirements of the system.