1. 研究目的与意义（文献综述）

1．Purpose and significance

Sporting events are the most popular form of remote live entertainment in the world attracting millions of viewers on television, personal computers, and a variety of emerging devices. They are produced using a numerous cameras and microphones. This production process continues to evolve as it strives to engage and immerse viewers in the action suspense, and drama of the remote live event. Video tracking is the process of locating a moving object or multiple objects over time using a camera. It has a variety of uses, some of which are: human-computer interaction, security and surveillance, video communication and compression, augmented reality, traffic control, medical imaging and video editing. But here we will be focusing on water surface targets tracking. The principal application is to detect and track the contour of objects moving in a cluttered environment that is going to make it so challenging. Video tracking can be a time consuming process due to the amount of data that is contained in video. Adding further to the complexity is the possible need to use object recognition techniques for tracking, a challenging problem in its own right. Keeping a fix on a target at sea can be demanding. It is common practice in the marine community for a person to keep pointing at a target so as not to lose it. To perform video tracking an algorithm analyzes sequential video frames and outputs the movement of targets between the frames. There are a variety of algorithms, each having strengths and weaknesses. Considering the intended use is important when choosing which algorithm to use. There are two major components of a visual tracking system: target representation and localization, as well as filtering and data association. Target representation and localization is mostly a bottom-up process. These methods give a variety of tools for identifying the moving object. Locating and tracking the target object successfully is dependent on the algorithm. For example, using blob tracking is useful for identifying human movement because a person's profile changes dynamically. Typically the computational complexity for these algorithms is low.

The intention of this study is to extract water surface targets more precisely in water surface sport, so that it can make the television broadcast more vivid and helping athletes in their daily training. For example in the canoe competition sport after extraction of athletes from the river the three dimensional trajectory is marked on the canoe, so that after the game the staff can use the tracking result to direct athletes. The first step is identifying and tracking a specific point in the image that a tracking algorithm can lock onto and follow through multiple frames. Here cameras will be used on different sides to measure athletes positions and athletes movement on the visual system. In canoe competition, this system will help us to compare our result with a standard three dimensional trajectory and calculate it by putting markers on the canoe. The aim of the tracking is to associate target objects or athletes video frames from different sights get with cameras.

2. 研究的基本内容与方案

2．Content of research and objectives

This paper presents a real time tracking system for moving objects on a water surface. The study is operated in a river where athletes perform, that’s a challenging task regarding material we are using cause of the cluttered environment moving targets are and the splashed water that occluded them. The problem on many occasions is the amount of motion an athlete will experience in even moderate river. If this motion is present without visual reference it can often become disorientating, making it tough for a person to successfully follow the target. Since there is not special tracking algorithm for water surface target, a multi-view tracking system is constructed in this paper. By employing motion and color statistical characters of water surface, an automatically target extraction algorithm is proposed to extract moving targets without any prior information of background and targets. In the framework of Extended Kalman Filter, the 3D trajectory of water surface moving target is estimated. The paper is organized as follows: we begin with a description of the visual tracking algorithm together with our improvements in section, then describe the full system in section and present results and evaluation from field-tests in section. We conclude with a discussion on the result and suggestions for further research.

3. 研究计划与安排

第1周—第3周 查阅资料和制定方案,写开题报告；

第4周—第8周 构建传感器系统，进行识别算法设计，并编写相应软件；

第9周—第13周 对系统进行调试；

4. 参考文献（12篇以上）

[1]. yang g, li b, ji s, et al. ship detection from opticalsatellite images based on sea surface analysis[j]. ieee geoscience and remotesensing letters, 2014, 11(3): 641-645.

[2]. tsuruta n, khayyer a, gotoh h. a short note on dynamicstabilization of moving particle semi-implicit method[j]. computers amp;fluids, 2013, 82: 158-164.

[3]. 王辉昊, 张旻, 牛文鑫, 等. 三维运动捕捉技术在颈椎整复手法中肢体运动轨迹的在体研究[j]. 中国骨伤, 2015, 10: 019.