Visual motion perception for mobile robots through dense optical flow fields

详细信息    查看全文

• 作者：Andry Maykol Pinto ; ^{andry.pinto@fe.up.pt}Author Vitae ; Paulo G. CostaAuthor Vitae ; Miguel V. CorreiaAuthor Vitae ; Anibal C. MatosAuthor Vitae ; A. Paulo MoreiraAuthor Vitae
• 关键词：Motion analysis ; Clustering ; Optical-flow ; Real-time ; Robotics
• 刊名：Robotics and Autonomous Systems
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：87
• 期：Complete
• 页码：1-14
• 全文大小：3641 K
• 卷排序：87

文摘

This paper focuses on clustering the motion from dense optical flow fields. An unsupervised clustering methods are presented and a model selection is proposed. A comparison between the proposed technique with the K-means and EM is made. The experimental evaluations reveal that the proposed technique achieved the best F1 score. The proposed technique is superior in terms of robustness and computational demands.