Maritime Target Detection and Tracking
Method of object detection and tracking is one of hot topics in image processing and computer vision field,which is significant not only in military such as imaging guidance and military target tracking,but also for civil use such as security and monitoring and the intelligent man-machine interaction.For marine targets,how to eliminate interference effectively and achieve accurate detection of moving targets is a key problem to be solved.In this paper,a method of image segmentation and line detection is proposed to detect the horizon,which can help to determine the area to be detected.Prior knowledge is used to detect the ship target in this area.To identify the suspected ship,we detect it in multiple frames.After identifying the ship,the mean shift algorithm is applied to lock tracked target.The experiment shows that the algorithm we proposed has good effect of detection and tracking for the ship target in the infrared image,and this algorithm has low computational complexity and small computation.It has been realized in the embedded hardware system and has high application value.
object tracking object detection line detection
Liu Jian Gao Wen
Changchun University of Science and Technology,China;Changchun Institute of Optics,Fine Mechanics an Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,China
国际会议
西安
英文
96-104
2018-09-21（万方平台首次上网日期，不代表论文的发表时间）