Athlete detection in sports videos is a challenging task due to the dynamic and cluttered background. Distractor-aware SiamRPN (DaSiamRPN) has a simple network structure and can be utilized to perform long-term tracking of large data sets. However, similarly to the Siamese network, the tracking results heavily rely on the given position in the initial frame. Hence, there is a lack of solutions for some complex tracking scenarios, such as running and changing of bodies of athletes, especially in the stage from squatting to standing to running. The Haar feature-based cascade classifier is involved to catch the key frame, representing the video frame of the most dramatic changes of the athletes. DaSiamRPN is implemented as the tracking method. In each frame after the key frame, a detection window is given based on the bounding box generated by the DaSiamRPN tracker. In the new detection window, a fusion method (HOG-SVM) combining features of Histograms of Oriented Gradients (HOG) and a linear Support-Vector Machine (SVM) is proposed for detecting the athlete, and the tracking results are updated in real-time by fusing the tracking results of DaSiamRPN and HOG-SVM. Our proposed method has reached a stable and accurate tracking effect in testing on men’s 100 m video sequences and has realized real-time operation.
Autonomous underwater vehicles (AUVs) rely on a mechanically scanned imaging sonar that is fixedly mounted on AUVs for underwater target barrier-avoiding and tracking. When underwater targets cross or approach each other, AUVs sometimes fail to track, or follow the wrong target because of the incorrect association of the multi-target. Therefore, a tracking method adopting the cloud-like model data association algorithm is presented in order to track underwater multiple targets. The clustering cloud-like model (CCM) not only combines the fuzziness and randomness of the qualitative concept, but also achieves the conversion of the quantitative values. Additionally, the nearest neighbor algorithm is also involved in finding the cluster center paired to each target trajectory, and the hardware architecture of AUVs is proposed. A sea trial adopting a mechanically scanned imaging sonar fixedly mounted on an AUV is carried out in order to verify the effectiveness of the proposed algorithm. Experiment results demonstrate that compared with the joint probabilistic data association (JPDA) and near neighbor data association (NNDA) algorithms, the new algorithm has the characteristic of more accurate clustering.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.