Adaptive Fractional-order Variational Dynamic Optical Flow Selection Algorithm For Target Tracking In Dynamic Scenarios

In this paper, an adaptive fractional-order optical flow selection algorithm with improved ant colony clustering is proposed to address the issues of texture processing and dynamic noise perturbation in simultaneous localization and mapping algorithms in dynamic scenes with strong static assumption theory. The algorithm combines the characteristics of fractional differentiation and sparse optical flow algorithm, and makes full use of the weak texture gradient of the image. The ant colony algorithm is improved by using the elite sharing mechanism, and the improved ant colony algorithm is combined with the clustering algorithm. The experimental results show that the algorithm not only realizes the adaptive selection of the best order, but also achieves better dynamic disturbance differentiation ability through the clustering of feature selection. While distinguishing dynamic and static information effectively, more details of optical flow with weak gradient feature are preserved. The proposed algorithm holds promise for simultaneous localization and mapping systems.