Object tracking plays an important role in the computer vision field and has many applications such as video surveillance and vehicle navigation. But the occlusion problem is one of the most challenging problems in the applications. Although there are many approaches in the object tracking field that focus on dealing with occlusion scenes, the occlusion with large size barriers and long occlusion time still cannot be solved. To handle the problems, this paper proposes a reliable tracking method based on particle filter focus on long-term full occlusion with large size barriers. In this paper the large size is defined as pixel width from 350 to 600 in fixed resolution images. and the long term is defined as occlusion frame number from 180 to 600. First, this paper proposed a particle position reset module to replace the resampling process during the occlusion periods to solve the problem of losing the target after occlusion. In addition, a hybrid feature based likelihood model is proposed for the occlusion happening and ending judgments. Experiments on the extreme occlusion situation sequences demonstrate the reliability and accuracy of the proposed work on these challenging scenes. The algorithm finally implements the average 92% success rate at the tested sequences.

In the volleyball game, estimating the 3D pose of the spiker is very valuable for training and analysis, because the spiker’s technique level determines the scoring or not of a round. The development of computer vision provides the possibility for the acquisition of the 3D pose. Most conventional pose estimation works are data-dependent methods, which mainly focus on reaching a high level on the dataset with the controllable scene, but fail to get good results in the wild real volleyball competition scene because of the lack of large labelled data, abnormal pose, occlusion and overlap. To refine the inaccurate estimated pose, this paper proposes a motion-aware and data-independent method based on a calibrated multi-camera system for a real volleyball competition scene. The proposed methods consist of three key components: 1) By utilizing the relationship of multi-views, an irrelevant projection based potential joint restore approach is proposed, which refines the wrong pose of one view with the other three views projected information to reduce the influence of occlusion and overlap. 2) Instead of training with a large amount labelled data, the proposed motion-aware method utilizes the similarity of specific motion in sports to achieve construct a spike model. Based on the spike model, joint and trajectory matching is proposed for coarse refinement. 3) To finely refine, a point distribution based posterior decision network is proposed. While expanding the receptive field, the pose estimation task is decomposed into a classification decision problem, which greatly avoids the dependence on a large amount of labelled data. The experimental dataset videos with four synchronous camera views are from a real game, the Game of 2014 Japan Inter High School of Men Volleyball. The experiment result achieves 76.25%, 81.89%, and 86.13% success rate at the 30mm, 50mm, and 70mm error range, respectively. Since the proposed refinement framework is based on a real volleyball competition, it is expected to be applied in the volleyball analysis.