Aiming at the tracking real-time and accuracy problem of traffic videos, a efficient Multi-target tracking method based on Fusion morphology filter is proposed. The proposed Multi-target tracking method used by Morphologically Fused Tracking approach and combined with pyramid mean shift algorithm, quantizes the deterioration effects encountered on marble surfaces by providing the number, location and shape of deterioration spots. First the detection based on the application of morphological operator sequential filters by reconstruction with structuring elements of growing size. Then adopt a traditional tracking method such as adaptive pyramid mean shift, because it uses the pyramid analysis technique and can determine the pyramid level adaptively to decrease the number of iterations required to achieve region. We validate our approach on tracking examples using real video sequences, it can precisely partition and track the predetermined objects in video frames.