Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections
The approach for the detection of vehicle trajectory abnormalities on CCTV video from road intersections was proposed and evaluated. We mainly focused on the trajectory analysis method rather than objects detection and tracking. Two basic challenges have been overcome in the suggested approach—spati...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/3/388 |
| _version_ | 1797486374138413056 |
|---|---|
| author | Rifkat Minnikhanov Igor Anikin Aigul Mardanova Maria Dagaeva Alisa Makhmutova Azat Kadyrov |
| author_facet | Rifkat Minnikhanov Igor Anikin Aigul Mardanova Maria Dagaeva Alisa Makhmutova Azat Kadyrov |
| author_sort | Rifkat Minnikhanov |
| collection | DOAJ |
| description | The approach for the detection of vehicle trajectory abnormalities on CCTV video from road intersections was proposed and evaluated. We mainly focused on the trajectory analysis method rather than objects detection and tracking. Two basic challenges have been overcome in the suggested approach—spatial perspective on the image and performance. We used trajectory approximation by polynomials as well as the Ramer-Douglas-Peucker N thinning technique to increase the performance of the trajectory comparison method. Special modification of trajectory similarity metric LCSS was suggested to consider the spatial perspective. We used clustering to discover two types of classes—with normal and abnormal trajectories. The framework, which implements the suggested approach, was developed. A series of experiments were carried out for testing the approach and defining recommendations for using different techniques in the scope of it. |
| first_indexed | 2024-03-09T23:33:16Z |
| format | Article |
| id | doaj.art-873b2a0035214ee3b98608ca10a3f80c |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T23:33:16Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-873b2a0035214ee3b98608ca10a3f80c2023-11-23T17:06:42ZengMDPI AGMathematics2227-73902022-01-0110338810.3390/math10030388Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road IntersectionsRifkat Minnikhanov0Igor Anikin1Aigul Mardanova2Maria Dagaeva3Alisa Makhmutova4Azat Kadyrov5Road Safety State Company, 420059 Kazan, RussiaInformation Security Systems Department, Kazan National Research Technical University Named after A.N. Tupolev-KAI, 420111 Kazan, RussiaZalando Logistics SE & Co. KG, 99098 Erfurt, GermanyRoad Safety State Company, 420059 Kazan, RussiaInformation Security Systems Department, Kazan National Research Technical University Named after A.N. Tupolev-KAI, 420111 Kazan, RussiaRoad Safety State Company, 420059 Kazan, RussiaThe approach for the detection of vehicle trajectory abnormalities on CCTV video from road intersections was proposed and evaluated. We mainly focused on the trajectory analysis method rather than objects detection and tracking. Two basic challenges have been overcome in the suggested approach—spatial perspective on the image and performance. We used trajectory approximation by polynomials as well as the Ramer-Douglas-Peucker N thinning technique to increase the performance of the trajectory comparison method. Special modification of trajectory similarity metric LCSS was suggested to consider the spatial perspective. We used clustering to discover two types of classes—with normal and abnormal trajectories. The framework, which implements the suggested approach, was developed. A series of experiments were carried out for testing the approach and defining recommendations for using different techniques in the scope of it.https://www.mdpi.com/2227-7390/10/3/388intelligent transport systemsvideo processingtrajectoriesclusteringanomaly detection |
| spellingShingle | Rifkat Minnikhanov Igor Anikin Aigul Mardanova Maria Dagaeva Alisa Makhmutova Azat Kadyrov Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections Mathematics intelligent transport systems video processing trajectories clustering anomaly detection |
| title | Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections |
| title_full | Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections |
| title_fullStr | Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections |
| title_full_unstemmed | Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections |
| title_short | Evaluation of the Approach for the Identification of Trajectory Anomalies on CCTV Video from Road Intersections |
| title_sort | evaluation of the approach for the identification of trajectory anomalies on cctv video from road intersections |
| topic | intelligent transport systems video processing trajectories clustering anomaly detection |
| url | https://www.mdpi.com/2227-7390/10/3/388 |
| work_keys_str_mv | AT rifkatminnikhanov evaluationoftheapproachfortheidentificationoftrajectoryanomaliesoncctvvideofromroadintersections AT igoranikin evaluationoftheapproachfortheidentificationoftrajectoryanomaliesoncctvvideofromroadintersections AT aigulmardanova evaluationoftheapproachfortheidentificationoftrajectoryanomaliesoncctvvideofromroadintersections AT mariadagaeva evaluationoftheapproachfortheidentificationoftrajectoryanomaliesoncctvvideofromroadintersections AT alisamakhmutova evaluationoftheapproachfortheidentificationoftrajectoryanomaliesoncctvvideofromroadintersections AT azatkadyrov evaluationoftheapproachfortheidentificationoftrajectoryanomaliesoncctvvideofromroadintersections |