Abstract
Night vision greatly affects the efficiency of our vision which we come across daily. In this work we mainly focus on the night vision system to improve the safety and security of people. Research work on night vision is very essential to solve the social problems in the present scenario, but there is still a lack of databases to do research on night vision using deep-learning techniques. In day-time the objects and their features can be easily extracted, but as a consequence of very low-light intensity in night time it becomes difficult for the system to detect the objects and its features. To overcome such hardships, we collected the night vision datasets under various conditions including point source light, blurred images due to vehicle headlights, insect movement and rainy condition. In this study, we compared the performance of three different object detection models, namely fast R-CNN which gave a mAP of 0.84 at 45 FPS, faster R-CNN which gave a mAP of 0.88 at 20 FPS, YOLO v4 which gave a mAP of 0.95 at 79 FPS. Based on the trade-off between accuracy and detection speed, we have picked YOLO v4 as our choice of model. In the Pre-processing step we have used two filters: low-pass filter and unsharp filter have been applied to reduce noise and improve the sharpness of the image respectively and it further helps the object detection model achieve better results to 0.95 mAP. The classes detected by this algorithm are Human, Car, Bike, Animal, Truck, Van.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Yuen Peng Loh, Chee Seng Chan. (2018). Getting to know low-light images with the Exclusively Dark dataset. Computer Vision and Image Understanding 178 (2019), pp 30–42. Elsevier Inc.
Zhu, H., Yan, X., Tang, H., Chang, Y., Li, B., & Yuan, X. (2020). Moving object detection with deep CNNs. IEEE Access., 8, 29729–29741. https://doi.org/10.1109/ACCESS.2020.2972562
Ashiba, M., Tolba, M. S., El-Fishawy, A. S., Abd El-Samie, F. E. J. M. T. (2020). Applications, "Hybrid enhancement of infrared night vision imaging system," 79, 6085–6108
Alonso, M., Brunete, A., Hernando, M., & Gambao, E. J. I. A. (2019). Background-subtraction algorithm optimization for home camera-based night-vision fall detectors. 7, 152399–152411.
Mehmood, F., Ullah, I., Ahmad, S., Kim, D. J. J. o. A. I., (2019). Computing, "Object detection mechanism based on deep learning algorithm using embedded IoT devices for smart home appliances control in CoT," pp. 1–17, 2019.
Nobis, F., Geisslinger, M., Weber, M., Betz, J., Lienkamp, M. (2019). A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection. In Sensor Data Fusion: Trends, Solutions. Applications (SDF), 2019, 1–7.
Kim, D.H., Lee, S., Jeon, J., & Song, B.C. (2020). Real-time purchase behavior recognition system based on deep learning-based object detection and tracking for an unmanned product cabinet. Expert Systems with Applications, 143, 113063. https://doi.org/10.1016/j.eswa.2019.113063.
Park, J., Chen, J., Cho,, Y. K., Kang, D. Y., & Son, B. J. J. S. (2020). CNN-based person detection using infrared images for night-time intrusion warning systems. 20, 34.
Kim, I. S., Jeong, Y., Kim, S. H., Jang, J. S., & Jung, S. K. (2019). Deep learning based effective surveillance system for low-illumination environments. In: Eleventh International Conference on Ubiquitous and Future Networks (ICUFN), 2019, 141–143.
Shakeel, M. F., Bajwa, N. A., Anwaar, A. M., Sohail, A., & Khan, A. (2019). Detecting driver drowsiness in real time through deep learning based object detection. In: International Work-Conference on Artificial Neural Networks, 2019, pp. 283–296.
Schneider, S., Taylor, G. W., & Kremer, S. (2018). Deep learning object detection methods for ecological camera trap data. In: 2018 15th Conference on computer and robot vision (CRV), 2018, pp. 321–328.
Komatsu, S., Markman, A., Mahalanobis, A., Chen, K., & Javidi, B. J. A. O.(2017). Three-dimensional integral imaging and object detection using long-wave infrared imaging, vol. 56, pp. D120–D126.
S. Kuanar, “Deep Learning based Fast Mode Decision in HEVC Intra Prediction using Region Wise Feature Classification,” Ph.D. dissertation, Department of Electrical Engineering, University of Texas Arlington, USA, Dec, 2018.
M. Aladem, S. Baek and S. A. Rawashdeh, "Evaluation of image enhancement techniques for vision-based navigation under low illumination", J. Robot., vol. 2019, 2019.
Cai, Y., Liu, Z., Wang, H., & Sun, X. (2017). Saliency-based pedestrian detection in far infrared images. IEEE Access, 5, 5013–5019. https://doi.org/10.1109/ACCESS.2017.2695721
Portmann, J., Lynen, S., Chli, M., & Siegwart, R. (2014). People detection and tracking from aerial thermal views. In. IEEE international conference on robotics and automation (ICRA), 2014, 1794–1800.
Bilodeau, G.-A.., Torabi, A., St-Charles, P.-L., Riahi, D. J. I. P. (2014). Thermal–visible registration of human silhouettes: A similarity measure performance evaluation, vol. 64, pp. 79–86.
Davis, J. W., & Keck, M. A. (2005). A two-stage template approach to person detection in thermal imagery. In: 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05)-Volume 1, 2005, pp. 364–369.
Miezianko, R. IEEE OTCBVS WS Series Bench; Terravic Research Infrared Database. 2005. Available online http://vcipl-okstate.org/pbvs/bench/Data/05/download.html
Socarrás, Y., Ramos, S., Vázquez, D., López, A. M., & Gevers, T. (2013). Adapting pedestrian detection from synthetic to far infrared images. In: IEEE ICCV Workshops, 2013.
Felsberg, M., Berg, A., Hager, G., Ahlberg, J., Kristan, M., Matas, J. et al. (2015). The thermal infrared visual object tracking VOT-TIR2015 challenge results. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, 2015, pp. 76–88.
Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Improvement. Computer Science. arXiv: 1804.02767. http://arxiv.org/abs/1804.02767.
Dai, X., Yuan, X., & Wei, X. J. A. I. (2020). TIRNet: Object detection in thermal infrared images for autonomous driving, pp. 1–18.
Acknowledgements
There is no funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors says there is no conflicts of interest.
Ethical compliance.
No.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Murugan, R.A., Sathyabama, B. Object Detection for Night Surveillance Using Ssan Dataset Based Modified Yolo Algorithm in Wireless Communication. Wireless Pers Commun 128, 1813–1826 (2023). https://doi.org/10.1007/s11277-022-10020-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-022-10020-9