A modified KLT multiple objects tracking framework based on global segmentation and adaptive template

Kang Xue, Patricio A. Vela, Yue Liu, Yongtian Wang

Abstract: This paper presents a modified Kanade-Lucas-Tomasi (KLT) tracking framework for multiple objects tracking applications. First, the framework includes a global pixel-level probabilistic model and an adaptive RGB template model to modify traditional KLT tracker more robust to track multiple objects and partial occlusions. Meanwhile, a Merge and Split algorithm is introduced in the proposed framework to track complete occlusions. The advantage of our method is demonstrated on a variety of challenging video sequences.