Airport surface target tracking method based on improved LBP algorithm and KLT

To effectively solve the drifting problem of moving target tracking in airport surface video surveillance system, airport surface target tracking method based on improved LBP (Local Binary Patterns) algorithm and KLT (Kanade-Lucas-Tomasi) is proposed. Firstly, the improved LBP Operator is combined with Gaussian mixture model for background modeling and target detection to suppress the interference of shadow by that the texture and color of LBP Operator are insensitive to shadow. Meanwhile, LBP image information is fused with target feature point tracking of KLT. If most of the feature points found by KLT are in the contour of LBP target, the contour is marked as the area of real target; otherwise, feature points of KLT are used to determine the contour of the target. Ultimately, the precise and reliable tracking of moving targets are achieved. The experiment based on the surface aircraft shows that the proposed method can not only track pose-varied aircraft accurately and stably, but also be suitable for complex airport environments.