Object detection and tracking in video sequences: formalization, metrics and results
One of the promising areas of development and implementation of artificial intelligence is the automatic detection and tracking of moving objects in video sequence. The paper presents a formalization of the detection and tracking of one and many objects in video. The following metrics are considered...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
National Academy of Sciences of Belarus, the United Institute of Informatics Problems
2021-03-01
|
| Series: | Informatika |
| Subjects: | |
| Online Access: | https://inf.grid.by/jour/article/view/1128 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832543418608254976 |
|---|---|
| author | R. P. Bohush S. V. Ablameyko |
| author_facet | R. P. Bohush S. V. Ablameyko |
| author_sort | R. P. Bohush |
| collection | DOAJ |
| description | One of the promising areas of development and implementation of artificial intelligence is the automatic detection and tracking of moving objects in video sequence. The paper presents a formalization of the detection and tracking of one and many objects in video. The following metrics are considered: the quality of detection of tracked objects, the accuracy of determining the location of the object in a frame, the trajectory of movement, the accuracy of tracking multiple objects. Based on the considered generalization, an algorithm for tracking people has been developed that uses the tracking through detection method and convolutional neural networks to detect people and form features. Neural network features are included in a composite descriptor that also contains geometric and color features to describe each detected person in the frame. The results of experiments based on the considered criteria are presented, and it is experimentally confirmed that the improvement of the detector operation makes it possible to increase the accuracy of tracking objects. Examples of frames of processed video sequences with visualization of human movement trajectories are presented. |
| format | Article |
| id | doaj-art-4dc01f13859c4592af073a0e7c467c76 |
| institution | Kabale University |
| issn | 1816-0301 |
| language | Russian |
| publishDate | 2021-03-01 |
| publisher | National Academy of Sciences of Belarus, the United Institute of Informatics Problems |
| record_format | Article |
| series | Informatika |
| spelling | doaj-art-4dc01f13859c4592af073a0e7c467c762025-02-03T11:40:29ZrusNational Academy of Sciences of Belarus, the United Institute of Informatics ProblemsInformatika1816-03012021-03-01181436010.37661/1816-0301-2021-18-1-43-60958Object detection and tracking in video sequences: formalization, metrics and resultsR. P. Bohush0S. V. Ablameyko1Polotsk State UniversityBelarusian State University; The United Institute of Informatics Problems of the National Academy of Sciences of BelarusOne of the promising areas of development and implementation of artificial intelligence is the automatic detection and tracking of moving objects in video sequence. The paper presents a formalization of the detection and tracking of one and many objects in video. The following metrics are considered: the quality of detection of tracked objects, the accuracy of determining the location of the object in a frame, the trajectory of movement, the accuracy of tracking multiple objects. Based on the considered generalization, an algorithm for tracking people has been developed that uses the tracking through detection method and convolutional neural networks to detect people and form features. Neural network features are included in a composite descriptor that also contains geometric and color features to describe each detected person in the frame. The results of experiments based on the considered criteria are presented, and it is experimentally confirmed that the improvement of the detector operation makes it possible to increase the accuracy of tracking objects. Examples of frames of processed video sequences with visualization of human movement trajectories are presented.https://inf.grid.by/jour/article/view/1128video surveillancemoving objectconvolutional neural networktracking by detectionmotion trajectory |
| spellingShingle | R. P. Bohush S. V. Ablameyko Object detection and tracking in video sequences: formalization, metrics and results Informatika video surveillance moving object convolutional neural network tracking by detection motion trajectory |
| title | Object detection and tracking in video sequences: formalization, metrics and results |
| title_full | Object detection and tracking in video sequences: formalization, metrics and results |
| title_fullStr | Object detection and tracking in video sequences: formalization, metrics and results |
| title_full_unstemmed | Object detection and tracking in video sequences: formalization, metrics and results |
| title_short | Object detection and tracking in video sequences: formalization, metrics and results |
| title_sort | object detection and tracking in video sequences formalization metrics and results |
| topic | video surveillance moving object convolutional neural network tracking by detection motion trajectory |
| url | https://inf.grid.by/jour/article/view/1128 |
| work_keys_str_mv | AT rpbohush objectdetectionandtrackinginvideosequencesformalizationmetricsandresults AT svablameyko objectdetectionandtrackinginvideosequencesformalizationmetricsandresults |