| 引用本文: | 李超能,冯冠文,姚航,刘如意,李宇楠,谢琨,苗启广.轨迹异常检测研究综述.软件学报,2024,35(2):927-974 |
| |
|
| |
|
|
| 本文已被：浏览 5038次 下载 9855次 |
码上扫一扫！ |
|
|
| 轨迹异常检测研究综述 |
|
李超能1,2, 冯冠文1,2, 姚航1,2, 刘如意1,2, 李宇楠1,2, 谢琨1,2, 苗启广1,2
|
|
1.西安电子科技大学 计算机科学与技术学院, 陕西 西安 710071;2.西安市大数据与视觉智能关键技术重点实验室 (西安电子科技大学), 陕西 西安 710071
|
|
| 摘要: |
| 传感器技术的飞速发展催生大量交通轨迹数据, 轨迹异常检测在智慧交通、自动驾驶、视频监控等领域具有重要的应用价值. 不同于分类、聚类和预测等轨迹挖掘任务, 轨迹异常检测旨在发现小概率、不确定和罕见的轨迹行为. 轨迹异常检测中一些常见的挑战与异常值类型、轨迹数据标签、检测准确率以及计算复杂度有关. 针对上述问题, 全面综述近20年来轨迹异常检测技术的研究现状和最新进展. 首先, 对轨迹异常检测问题的特点与目前存在的研究挑战进行剖析. 然后, 基于轨迹标签的可用性、异常检测算法原理、离线或在线算法工作方式等分类标准, 对现有轨迹异常检测算法进行对比分析. 对于每一类异常检测技术, 从算法原理、代表性方法、复杂度分析以及算法优缺点等方面进行详细总结与剖析. 接着, 讨论开源的轨迹数据集、常用的异常检测评估方法以及异常检测工具. 在此基础上, 给出轨迹异常检测系统架构, 形成从轨迹数据采集到异常检测应用等一系列相对完备的轨迹挖掘流程. 最后, 总结轨迹异常检测领域关键的开放性问题, 并展望未来的研究趋势和解决思路. |
| 关键词: 轨迹数据 异常检测 数据挖掘 机器学习 深度学习 |
| DOI：10.13328/j.cnki.jos.006996 |
| 分类号: |
| 基金项目:科技创新2030—“新一代人工智能”重大项目(2022ZD0117103);国家自然科学基金(62272364,62002271);陕西省重点研发计划(2020LSFP3-15);中国成人教育协会“十四五”成人继续教育科研规划重点课题(2021-414ZA);陕西高等继续教育教学改革研究课题(21XJZ004);广西可信软件重点实验室研究课题(KX202061);青岛市科技计划重点研发专项(21-1-2-18-xx) |
|
| Survey on Trajectory Anomaly Detection |
|
LI Chao-Neng1,2, FENG Guan-Wen1,2, YAO Hang1,2, LIU Ru-Yi1,2, LI Yu-Nan1,2, XIE Kun1,2, MIAO Qi-Guang1,2
|
|
1.School of Computer Science and Technology, Xidian University, Xi'an 710071, China;2.Xi'an Key Laboratory of Big Data and Intelligent Vision(Xidian University), Xi'an 710071, China
|
| Abstract: |
| The rapid advancement of sensor technology has resulted in a vast volume of traffic trajectory data, and trajectory anomaly detection has a wide range of applications in sectors including smart transportation, autonomous driving, and video surveillance. Trajectory anomaly detection, unlike other trajectory mining tasks like classification, clustering, and prediction, tries to find low-probability, uncertain, and unusual trajectory behavior. The types of anomalies, trajectory data labels, detection accuracy, and computational complexity are all frequent issues in trajectory anomaly detection. In view of the above problems, the research status and latest progress of trajectory anomaly detection technology in the past two decades are comprehensively reviewed. First, the characteristics of trajectory anomaly detection and the current research challenges are analyzed. Then, the existing trajectory anomaly detection algorithms are compared and analyzed based on the classification criteria such as the availability of trajectory labels, the principle of anomaly detection algorithms, and the working mode of offline or online algorithms. For each type of anomaly detection technology, the algorithm principle, representative method, complexity analysis and algorithm advantages and disadvantages are summarized and analyzed in detail. Then, the open source trajectory datasets, commonly used anomaly detection evaluation methods and anomaly detection tools are discussed. On this basis, the architecture of the trajectory anomaly detection system is presented, and a series of relatively complete trajectory mining processes from trajectory data collection to anomaly detection application are formed. Finally, the significant open issues in the domain of trajectory anomaly detection are discussed, as well as potential research trends and solutions. |
| Key words: trajectory data anomaly detection data mining machine learning deep learning |
|
|
|
|
