一种背景运动视频中运动目标的检测方法

针对成像平台运动情况下的运动目标检测问题,提出了一种从特征点稀疏运动场估计到运动分类的目标检测算法.首先通过快速特征点检测与跟踪恢复出图像稀疏运动场;然后依据特征点之间运动一致性关系实现属于同一运动模式的特征点分类,根据分类得到的各组特征点计算场景图像重建误差,剔除重建误差最小的特征点组,实现对前景目标的检测.仿真实验对该算法在复杂场景中检测运动目标的有效性进行了验证.

A Moving Target Detection Method for Backgroud Motion Video

In order to detect target in the background motion video, an algorithm with sparse motion field estimation, motion classification is proposed. Firstly, sparse motion field is recovered by fast local feature detection and tracking. The local features that belong to the same motion pattern are classified according to their motion consistency, then, the resulting local feature groups are used to reconstructed scene image, and the foreground targets are identified by getting rid of the group with the least reconstruction error. The proposed method is tested on the dataset of real complex scenarios and its effectiveness is demonstrated in the results.