Probabilistic fusion for pedestrian detection from thermal and colour images
- Author
- Zuhaib Ahmed Shaikh (UGent) , David Van Hamme (UGent) , Peter Veelaert (UGent) and Wilfried Philips (UGent)
- Organization
- Abstract
- Pedestrian detection is an important research domain due to its relevance for autonomous and assisted driving, as well as its applications in security and industrial automation. Often, more than one type of sensor is used to cover a broader range of operating conditions than a single-sensor system would allow. However, it remains difficult to make pedestrian detection systems perform well in highly dynamic environments, often requiring extensive retraining of the algorithms for specific conditions to reach satisfactory accuracy, which, in turn, requires large, annotated datasets captured in these conditions. In this paper, we propose a probabilistic decision-level sensor fusion method based on naive Bayes to improve the efficiency of the system by combining the output of available pedestrian detectors for colour and thermal images without retraining. The results in this paper, obtained through long-term experiments, demonstrate the efficacy of our technique, its ability to work with non-registered images, and its adaptability to cope with situations when one of the sensors fails. The results also show that our proposed technique improves the overall accuracy of the system and could be very useful in several applications.
- Keywords
- Sensor fusion, Probabilistic fusion, Pedestrian detection, Multi-modal images, Decision-level fusion
Downloads
-
sensors-22-08637.pdf
- full text (Published version)
- |
- open access
- |
- |
- 1.00 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8773042
- MLA
- Ahmed Shaikh, Zuhaib, et al. “Probabilistic Fusion for Pedestrian Detection from Thermal and Colour Images.” SENSORS, vol. 22, no. 22, 2022, doi:10.3390/s22228637.
- APA
- Ahmed Shaikh, Z., Van Hamme, D., Veelaert, P., & Philips, W. (2022). Probabilistic fusion for pedestrian detection from thermal and colour images. SENSORS, 22(22). https://doi.org/10.3390/s22228637
- Chicago author-date
- Ahmed Shaikh, Zuhaib, David Van Hamme, Peter Veelaert, and Wilfried Philips. 2022. “Probabilistic Fusion for Pedestrian Detection from Thermal and Colour Images.” SENSORS 22 (22). https://doi.org/10.3390/s22228637.
- Chicago author-date (all authors)
- Ahmed Shaikh, Zuhaib, David Van Hamme, Peter Veelaert, and Wilfried Philips. 2022. “Probabilistic Fusion for Pedestrian Detection from Thermal and Colour Images.” SENSORS 22 (22). doi:10.3390/s22228637.
- Vancouver
- 1.Ahmed Shaikh Z, Van Hamme D, Veelaert P, Philips W. Probabilistic fusion for pedestrian detection from thermal and colour images. SENSORS. 2022;22(22).
- IEEE
- [1]Z. Ahmed Shaikh, D. Van Hamme, P. Veelaert, and W. Philips, “Probabilistic fusion for pedestrian detection from thermal and colour images,” SENSORS, vol. 22, no. 22, 2022.
@article{8773042,
abstract = {{Pedestrian detection is an important research domain due to its relevance for autonomous and assisted driving, as well as its applications in security and industrial automation. Often, more than one type of sensor is used to cover a broader range of operating conditions than a single-sensor system would allow. However, it remains difficult to make pedestrian detection systems perform well in highly dynamic environments, often requiring extensive retraining of the algorithms for specific conditions to reach satisfactory accuracy, which, in turn, requires large, annotated datasets captured in these conditions. In this paper, we propose a probabilistic decision-level sensor fusion method based on naive Bayes to improve the efficiency of the system by combining the output of available pedestrian detectors for colour and thermal images without retraining. The results in this paper, obtained through long-term experiments, demonstrate the efficacy of our technique, its ability to work with non-registered images, and its adaptability to cope with situations when one of the sensors fails. The results also show that our proposed technique improves the overall accuracy of the system and could be very useful in several applications.}},
articleno = {{8637}},
author = {{Ahmed Shaikh, Zuhaib and Van Hamme, David and Veelaert, Peter and Philips, Wilfried}},
issn = {{1424-8220}},
journal = {{SENSORS}},
keywords = {{Sensor fusion,Probabilistic fusion,Pedestrian detection,Multi-modal images,Decision-level fusion}},
language = {{eng}},
number = {{22}},
pages = {{17}},
title = {{Probabilistic fusion for pedestrian detection from thermal and colour images}},
url = {{http://doi.org/10.3390/s22228637}},
volume = {{22}},
year = {{2022}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: