Trajectory outlier detection approach based on common slices sub-sequence

Yu, Qingying; Luo, Yonglong; Chen, Chuanming; Wang, Xiaohan

doi:10.1007/s10489-017-1104-z

Cited by 33 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang et al [23] calculated the weighted multi-feature distance between the trajectory segments to cluster trajectories according to the trajectory deflection angle and velocity, and the anomaly detection is realized by comparing the trajectory information entropy. Yu et al [24] proposed trajectory outlier detection algorithm based on common slices sub-sequence (TODCSS) which used a novel CSS distance calculation method with the length and time of trajectory and verified the accuracy and stability of the method on the Atlantic hurricane data set and real-life mobility trajectory data set.…”

Section: B Abnormal Trajectory Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Nowadays, massive data has been brought by the rapid development of technology. When finding whether trajectory to be detected is abnormal under the premise of given normal trajectories, we innovatively propose 1) Seq2Seq model based on LSTM prediction network for trajectory modelling (SL-Modelling), and 2) abnormal trajectory detection method with spatio-temporal and semantic information. Firstly, SL-Modelling is used to obtain sequence-type trajectory models of normal trajectory groups directly for subsequent detection with no need to extract a large number of features manually and adapting to different sequence length. Then we introduce the concept of distance and semantic interest sequence that makes full use of spatio-temporal and semantic information of trajectories. Finally, the similarity between models and trajectory to be detected is calculated to detect abnormal trajectory. The experimental results of publicly available flight data set show that trajectory models obtained are descriptive enough to represent normal trajectory groups well, and the accuracy of modelling is higher than the existing advanced methods. Besides, the detection with spatio-temporal and semantic information has been verified that it has stronger detection ability with higher accuracy and takes less time.

show abstract

Section: B Abnormal Trajectory Detectionmentioning

confidence: 99%

“…To verify the performance, we compare the performance of SL-Modelling with that of ATD-RNN proposed by [9], gradient descent (GD) proposed by [25], BP neural network proposed by [24] and nonlinear autoregressive neural network (NAR) which is mature and widely applied in prediction.…”

Section: ) Comparison and Disccusionmentioning

confidence: 99%

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Yu et al [68] suggested Trajectory Outlier Detection based on Common Slices Sub-sequences (TODCSS) approach for discovering sub-trajectory outliers. For each trajectory t i , a set of trajectory slices are generated where each j th slice sl i j is obtained by connecting consecutive line segments having the same direction.…”

Section: B Online Processingmentioning

confidence: 99%

A Survey on Urban Traffic Anomalies Detection Algorithms

et al. 2019

View full text Add to dashboard Cite

This paper reviews the use of outlier detection approaches in urban traffic analysis. We divide existing solutions into two main categories: flow outlier detection and trajectory outlier detection. The first category groups solutions that detect flow outliers and includes statistical, similarity and pattern mining approaches. The second category contains solutions where the trajectory outliers are derived, including offline processing for trajectory outliers and online processing for sub-trajectory outliers. Solutions in each of these categories are described, illustrated, and discussed, and open perspectives and research trends are drawn. Compared to the state-of-the-art survey papers, the contribution of this paper lies in providing a deep analysis of all the kinds of representations in urban traffic data, including flow values, segment flow values, trajectories, and sub-trajectories. In this context, we can better understand the intuition, limitations, and benefits of the existing outlier urban traffic detection algorithms. As a result, practitioners can receive some guidance for selecting the most suitable methods for their particular case. INDEX TERMS Urban traffic analysis, outlier detection, machine learning, data mining.

show abstract

“…Each trajectory segment has a direction code, which is calculated based on the trajectory direction-code sequence acquisition method proposed in our previous work [29]. At first, the 2D plane coordinate system is evenly divided into N regions according to the angle.…”

Section: Average Direction Difference Of Stay Placementioning

confidence: 99%

“…Figure 4a shows the N (=16) direction codes introduced above, and Figure 4b shows the direction codes of different trajectory segments within S2. More specifically, the directioncode sequence of S2 is [13,2,14,10,15 Each trajectory segment has a direction code, which is calculated based on the trajectory direction-code sequence acquisition method proposed in our previous work [29]. At first, the 2D plane coordinate system is evenly divided into N regions according to the angle.…”

Section: Average Direction Difference Of Stay Placementioning

confidence: 99%

Road Congestion Detection Based on Trajectory Stay-Place Clustering

Luo

Chen

et al. 2019

IJGI

Self Cite

View full text Add to dashboard Cite

The results of road congestion detection can be used for the rational planning of travel routes and as guidance for traffic management. The trajectory data of moving objects can record their positions at each moment and reflect their moving features. Utilizing trajectory mining technology to effectively identify road congestion locations is of great importance and has practical value in the fields of traffic and urban planning. This paper addresses the issue by proposing a novel approach to detect road congestion locations based on trajectory stay-place clustering. First, this approach estimates the speed status of each time-stamped location in each trajectory. Then, it extracts the stay places of the trajectory, each of which is denoted as a seven-tuple containing information such as starting and ending time, central coordinate, average direction difference, and so on. Third, the time-stamped locations included in stay places are partitioned into different stay-place equivalence classes according to the timestamps. Finally, stay places in each equivalence class are clustered to mine the congestion locations of multiple trajectories at a certain period of time. Visual representation and experimental results on real-life cab trajectory datasets show that the proposed approach is suitable for the detection of congestion locations at different timestamps.

show abstract

Trajectory outlier detection approach based on common slices sub-sequence

Cited by 33 publications

References 30 publications

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection

A Survey on Urban Traffic Anomalies Detection Algorithms

Road Congestion Detection Based on Trajectory Stay-Place Clustering

Contact Info

Product

Resources

About