Multi-target tracking in team-sports videos via multi-level context-conditioned latent behaviour models
نویسندگان
چکیده
Multi-target tracking techniques increasingly exploit contextual information about group dynamics. However, approaches established in pedestrian tracking make assumptions about features and motion models which are often inappropriate to sports team tracking, where motion is erratic and players wear similar uniforms with frequent interplayer occlusions. On the other hand, approaches designed specifically for sports team tracking are predominantly aimed at detecting game-state rather than using game-state to enhance individual tracking. We propose a multi-level multi-target sports-team tracker, which overcomes these problems by modelling latent behaviours at both individual and player-pair levels, informed by team-level context dynamics. At the player-level, targets are tracked using adaptive representations, constrained by probabilistic models of player behaviour with respect to collision avoidance. At the team-level, we exploit an adaptive meshing and voting scheme to predict regions of interest, which inform strong motion priors for key individual players. Thus, latent knowledge is derived from team-level contexts to inform player-level tracking. To evaluate our approach, we have developed a new data-set with fully ground-truthed team-sports videos, and demonstrate significantly improved performance over state-of-the-art trackers from the literature.
منابع مشابه
Detecting and Tracking Sports Players with Random Forests and Context-Conditioned Motion Models
Player movements in team sports are often complex and highly correlated with both nearby and distant players. A single motion model would require many degrees of freedom to represent the full motion diversity of each player and could be difficult to use in practice. Instead, we introduce a set of Game Context Features extracted from noisy detection data to describe the current state of the matc...
متن کاملDecentralized and Cooperative Multi-Sensor Multi-Target Tracking With Asynchronous Bearing Measurements
Bearings only tracking is a challenging issue with many applications in military and commercial areas. In distributed multi-sensor multi-target bearings only tracking, sensors are far from each other, but are exchanging data using telecommunication equipment. In addition to the general benefits of distributed systems, this tracking system has another important advantage: if the sensors are suff...
متن کاملEvaluation of Probabilistic Occupancy Map for Player Tracking in Team Sports
In this paper we focus on tracking of players in team sports with multiple cameras. We evaluate a state of the art multi-camera multi-target tracking algorithm on a novel floorball dataset. We chose recent Probabilistic Occupancy Map and K-Shortest Path algorithms with a publicly available implementation that enables easy deployment. Both algorithms are mathematically well funded and capable of...
متن کاملCollaborative Multi-Camera Tracking of Athletes in Team Sports
A novel approach to tracking athletes in team sports using multiple cameras is proposed that addresses several issues including occlusions and propagation of wrong information. The strength of this approach lies in the use of belief propagation which enables good observations in some views to compensate for poor observations in other views due e.g. to occlusions. Each target is tracked in each ...
متن کاملVisual Tracking using Learning Histogram of Oriented Gradients by SVM on Mobile Robot
The intelligence of a mobile robot is highly dependent on its vision. The main objective of an intelligent mobile robot is in its ability to the online image processing, object detection, and especially visual tracking which is a complex task in stochastic environments. Tracking algorithms suffer from sequence challenges such as illumination variation, occlusion, and background clutter, so an a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014