Online multi‐object tracking based on time and frequency domain features
Abstract Multi‐object tracking (MOT) can be considered as an interesting field in computer vision research. Its application can be found in video motion analysis, smart interfaces, and visual surveillance. It is a challenging issue due to difficulties made by a variable number of objects and interac...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | IET Computers & Digital Techniques |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cdt2.12037 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546670361968640 |
|---|---|
| author | Mahbubeh Nazarloo Meisam Yadollahzadeh‐Tabari Homayun Motameni |
| author_facet | Mahbubeh Nazarloo Meisam Yadollahzadeh‐Tabari Homayun Motameni |
| author_sort | Mahbubeh Nazarloo |
| collection | DOAJ |
| description | Abstract Multi‐object tracking (MOT) can be considered as an interesting field in computer vision research. Its application can be found in video motion analysis, smart interfaces, and visual surveillance. It is a challenging issue due to difficulties made by a variable number of objects and interaction between them. In this work, a new method for online MOT based on time and frequency domain features is presented. The features are obtained from the wavelet transform and fractal dimension. The modified cuckoo optimization algorithm is utilized for feature selection, which has the ability such as fast convergence and global optima finding. The features are given for learning vector quantization, which is a supervised artificial neural network (ANN). It is used to classify the dataset. To evaluate the performance of the presented technique, simulations are performed using the ETH Mobile Platform and VS‐PETS 2009 datasets. The simulation results show the superiority of the presented technique for MOT compared to earlier studies in terms of accuracy. The mostly tracked values for the datasets are 74.3% and 97.2%, which leads to at least 4.2% and 2.5% better performance according to the other methods, respectively. |
| format | Article |
| id | doaj-art-75b1fbc4cb6044c49a4fb700fe9263cc |
| institution | Kabale University |
| issn | 1751-8601 1751-861X |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computers & Digital Techniques |
| spelling | doaj-art-75b1fbc4cb6044c49a4fb700fe9263cc2025-02-03T06:47:34ZengWileyIET Computers & Digital Techniques1751-86011751-861X2022-01-01161192810.1049/cdt2.12037Online multi‐object tracking based on time and frequency domain featuresMahbubeh Nazarloo0Meisam Yadollahzadeh‐Tabari1Homayun Motameni2Department of Computer Engineering Babol Branch, Islamic Azad University Babol IranDepartment of Computer Engineering Babol Branch, Islamic Azad University Babol IranDepartment of Computer Engineering Sari Branch, Islamic Azad University Sari IranAbstract Multi‐object tracking (MOT) can be considered as an interesting field in computer vision research. Its application can be found in video motion analysis, smart interfaces, and visual surveillance. It is a challenging issue due to difficulties made by a variable number of objects and interaction between them. In this work, a new method for online MOT based on time and frequency domain features is presented. The features are obtained from the wavelet transform and fractal dimension. The modified cuckoo optimization algorithm is utilized for feature selection, which has the ability such as fast convergence and global optima finding. The features are given for learning vector quantization, which is a supervised artificial neural network (ANN). It is used to classify the dataset. To evaluate the performance of the presented technique, simulations are performed using the ETH Mobile Platform and VS‐PETS 2009 datasets. The simulation results show the superiority of the presented technique for MOT compared to earlier studies in terms of accuracy. The mostly tracked values for the datasets are 74.3% and 97.2%, which leads to at least 4.2% and 2.5% better performance according to the other methods, respectively.https://doi.org/10.1049/cdt2.12037fractal dimensionlearning vector quantizationmodified cuckoo optimization algorithmmulti‐object trackingtime and frequency domain featureswavelet transform |
| spellingShingle | Mahbubeh Nazarloo Meisam Yadollahzadeh‐Tabari Homayun Motameni Online multi‐object tracking based on time and frequency domain features IET Computers & Digital Techniques fractal dimension learning vector quantization modified cuckoo optimization algorithm multi‐object tracking time and frequency domain features wavelet transform |
| title | Online multi‐object tracking based on time and frequency domain features |
| title_full | Online multi‐object tracking based on time and frequency domain features |
| title_fullStr | Online multi‐object tracking based on time and frequency domain features |
| title_full_unstemmed | Online multi‐object tracking based on time and frequency domain features |
| title_short | Online multi‐object tracking based on time and frequency domain features |
| title_sort | online multi object tracking based on time and frequency domain features |
| topic | fractal dimension learning vector quantization modified cuckoo optimization algorithm multi‐object tracking time and frequency domain features wavelet transform |
| url | https://doi.org/10.1049/cdt2.12037 |
| work_keys_str_mv | AT mahbubehnazarloo onlinemultiobjecttrackingbasedontimeandfrequencydomainfeatures AT meisamyadollahzadehtabari onlinemultiobjecttrackingbasedontimeandfrequencydomainfeatures AT homayunmotameni onlinemultiobjecttrackingbasedontimeandfrequencydomainfeatures |