Anomalous Trajectory Detection and Classification Based on Difference and Intersection Set Distance

Wang, Jingwei; Yuan, Yun; Ni, Tianle; Ma, Yunlong; Liu, Min; Xu, Gaowei; Shen, Weiming

doi:10.1109/tvt.2020.2967865

Cited by 41 publications

(18 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For clear demonstration, we denote AT N T i as N T i in Eq. (13). It shows that positive and negative terms of Q N T i cancel each other, making it close to zero.…”

Section: B Analysis Of Atdcmentioning

confidence: 87%

“…However, these studies only focus on distinguishing anomalous trajectories from normal ones, without considering that anomalous trajectories are also extremely different from each other. A recent study [13] has noticed this and sorted out four different patterns of abnormal trajectories: global detour (GD), local detour (LD), global shortcut (GS), and local shortcut (LS). This study also proposed a new algorithm, called the anomalous trajectory detection and classification (ATDC) algorithm, which achieved excellent performance.…”

Section: Introductionmentioning

confidence: 95%

“…Zhu et al utilized topk most popular traces as a reference and used an Edit distance in both spatial and temporal domains to measure the difference between trajectories [16]. Inspired by these algorithms and findings, Wang et al proposed a two-stage method called ATDC for anomalous trajectory detection and classification [13], which is the foundation of our work.…”

Section: Related Workmentioning

confidence: 99%

“…Note that the preprocessing of trajectory data in our work is the same as in [13], and details (including concepts and notations) can be found in this paper and will not be repeated here due to the limited space.…”

Section: A Atdcmentioning

confidence: 99%

“…Wang et al proposed the difference and intersection distance (DIS) metric to quantify the difference between any two trajectories [13]. Given a trajectory dataset with a set of trajectories τ = {AT 1 , AT 2 , ..., AT N }, the DIS distance between two trajectories AT i and AT j is defined as…”

Section: A Atdcmentioning

confidence: 99%

See 4 more Smart Citations

FastATDC: Fast Anomalous Trajectory Detection and Classification

Ni¹,

Wang²,

Ma³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Automated detection of anomalous trajectories is an important problem with considerable applications in intelligent transportation systems. Many existing studies have focused on distinguishing anomalous trajectories from normal trajectories, ignoring the large differences between anomalous trajectories. A recent study has made great progress in identifying abnormal trajectory patterns and proposed a two-stage algorithm for anomalous trajectory detection and classification (ATDC). This algorithm has excellent performance but suffers from a few limitations, such as high time complexity and poor interpretation. Here, we present a careful theoretical and empirical analysis of the ATDC algorithm, showing that the calculation of anomaly scores in both stages can be simplified, and that the second stage of the algorithm is much more important than the first stage. Hence, we develop a FastATDC algorithm that introduces a random sampling strategy in both stages. Experimental results show that FastATDC is 10 to 20 times faster than ATDC on real datasets. Moreover, FastATDC outperforms the baseline algorithms and is comparable to the ATDC algorithm.

show abstract

“…For clear demonstration, we denote AT N T i as N T i in Eq. (13). It shows that positive and negative terms of Q N T i cancel each other, making it close to zero.…”

Section: B Analysis Of Atdcmentioning

confidence: 87%

Section: Introductionmentioning

confidence: 95%