A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features
We propose a tracking-by-detection algorithm to track the movements of meeting participants from an overhead camera. An advantage of using overhead cameras is that all objects can typically be seen clearly, with little occlusion; however, detecting people from a wide-angle overhead view also poses c...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/6/4/25 |
| _version_ | 1797570038089121792 |
|---|---|
| author | Nahlah Algethami Sam Redfern |
| author_facet | Nahlah Algethami Sam Redfern |
| author_sort | Nahlah Algethami |
| collection | DOAJ |
| description | We propose a tracking-by-detection algorithm to track the movements of meeting participants from an overhead camera. An advantage of using overhead cameras is that all objects can typically be seen clearly, with little occlusion; however, detecting people from a wide-angle overhead view also poses challenges such as people’s appearance significantly changing due to their position in the wide-angle image, and generally from a lack of strong image features. Our experimental datasets do not include empty meeting rooms, and this means that standard motion based detection techniques (e.g., background subtraction or consecutive frame differencing) struggle since there is no prior knowledge for a background model. Additionally, standard techniques may perform poorly when there is a wide range of movement behaviours (e.g. periods of no movement and periods of fast movement), as is often the case in meetings. Our algorithm uses a novel coarse-to-fine detection and tracking approach, combining motion detection using adaptive accumulated frame differencing (AAFD) with Shi-Tomasi corner detection. We present quantitative and qualitative evaluation which demonstrates the robustness of our method to track people in environments where object features are not clear and have similar colour to the background. We show that our approach achieves excellent performance in terms of the multiple object tracking accuracy (MOTA) metrics, and that it is particularly robust to initialisation differences when compared with baseline and state of the art trackers. Using the Online Tracking Benchmark (OTB) videos we also demonstrate that our tracker is very strong in the presence of background clutter, deformation and illumination variation. |
| first_indexed | 2024-03-10T20:19:25Z |
| format | Article |
| id | doaj.art-8a231c4615d148039fe9b2cd47a3985d |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T20:19:25Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-8a231c4615d148039fe9b2cd47a3985d2023-11-19T22:18:26ZengMDPI AGJournal of Imaging2313-433X2020-04-01642510.3390/jimaging6040025A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner FeaturesNahlah Algethami0Sam Redfern1School of Computer Science, National University of Ireland Galway, University Road, H91 TK33 T Galway, IrelandSchool of Computer Science, National University of Ireland Galway, University Road, H91 TK33 T Galway, IrelandWe propose a tracking-by-detection algorithm to track the movements of meeting participants from an overhead camera. An advantage of using overhead cameras is that all objects can typically be seen clearly, with little occlusion; however, detecting people from a wide-angle overhead view also poses challenges such as people’s appearance significantly changing due to their position in the wide-angle image, and generally from a lack of strong image features. Our experimental datasets do not include empty meeting rooms, and this means that standard motion based detection techniques (e.g., background subtraction or consecutive frame differencing) struggle since there is no prior knowledge for a background model. Additionally, standard techniques may perform poorly when there is a wide range of movement behaviours (e.g. periods of no movement and periods of fast movement), as is often the case in meetings. Our algorithm uses a novel coarse-to-fine detection and tracking approach, combining motion detection using adaptive accumulated frame differencing (AAFD) with Shi-Tomasi corner detection. We present quantitative and qualitative evaluation which demonstrates the robustness of our method to track people in environments where object features are not clear and have similar colour to the background. We show that our approach achieves excellent performance in terms of the multiple object tracking accuracy (MOTA) metrics, and that it is particularly robust to initialisation differences when compared with baseline and state of the art trackers. Using the Online Tracking Benchmark (OTB) videos we also demonstrate that our tracker is very strong in the presence of background clutter, deformation and illumination variation.https://www.mdpi.com/2313-433X/6/4/25track-by-detectionmotion featuresoverhead camerasmart meeting |
| spellingShingle | Nahlah Algethami Sam Redfern A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features Journal of Imaging track-by-detection motion features overhead camera smart meeting |
| title | A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features |
| title_full | A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features |
| title_fullStr | A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features |
| title_full_unstemmed | A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features |
| title_short | A Robust Tracking-by-Detection Algorithm Using Adaptive Accumulated Frame Differencing and Corner Features |
| title_sort | robust tracking by detection algorithm using adaptive accumulated frame differencing and corner features |
| topic | track-by-detection motion features overhead camera smart meeting |
| url | https://www.mdpi.com/2313-433X/6/4/25 |
| work_keys_str_mv | AT nahlahalgethami arobusttrackingbydetectionalgorithmusingadaptiveaccumulatedframedifferencingandcornerfeatures AT samredfern arobusttrackingbydetectionalgorithmusingadaptiveaccumulatedframedifferencingandcornerfeatures AT nahlahalgethami robusttrackingbydetectionalgorithmusingadaptiveaccumulatedframedifferencingandcornerfeatures AT samredfern robusttrackingbydetectionalgorithmusingadaptiveaccumulatedframedifferencingandcornerfeatures |