Continuous Object Tracking via Joint Global-Local Binary Tree Topological Transformation in Underwater Acoustic Sensor Networks

作     者：Liu, Li Zhao, Tengfei Chan, Sammy Wu, Changmao 

作者机构：Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Peoples R China Hohai Univ Coll Informat Sci & Engn Changzhou 213022 Peoples R China City Univ Hong Kong Dept Elect Engn Kowloon Tong Hong Kong Peoples R China Chinese Acad Sci Inst Software Beijing Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON MOBILE COMPUTING》 (IEEE Trans. Mob. Comput.)

年 卷 期：2024年第23卷第12期

页      面：11091-11104页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China National Key R&D Program of China [2023YFC3008202] Fundamental Research Funds for the Central Universities [JUSRP124016] 

主　　题：Binary trees Partitioning algorithms Object tracking Target tracking Protocols Oils Underwater acoustics Continuous objects boundary tracking joint topological transformation sensor networks 

摘      要：Frequent activities in marine energy exploration and transportation have led to the ongoing presence of continuous objects, such as oil spills and radioactive waste, in the ocean. This article focuses on enhancing the understanding of these objects boundaries for accurate assessment of their shape, coverage, and evolution. We introduce a continuous object tracking algorithm named JGL-COT, based on joint global-local binary tree topological transformations and specifically designed for underwater acoustic sensor networks. The contribution of JGL-COT lies in its ability to leverage the correlation between the morphologies of a continuous object s boundaries over time, alternating between global and local binary tree topological transformations. When the present boundary features a strong resemblance to its previous form, JGL-COT switches to a local transformation by establishing a semi-infinite region. Otherwise, it transitions to a global transformation. Following this, JGL-COT chooses a group of binary tree-structured cells for boundary mapping, creating virtual boundary nodes as sampling points for boundary fitting. Building upon graph theory, we derive the lower bound on the effectiveness and time complexity of the proposed joint global and local binary tree topological transformations when applied to object boundary tracking. Experiments in both realistic and simulated settings confirm that JGL-COT provides highly accurate tracking and significantly reduces network energy consumption.