Abstract
Air targets are often fast and varied. For air targets monitoring tasks, traditional methods tend to be slow and resource-intensive. Therefore, this paper proposes a method of target detection and location using binocular synchronous camera as acquisition device and combining SSD, ORB and binocular stereo vision. Firstly, the left and right images collected synchronously are detected by SSD, and the ROI region of the target is taken as a new image. Then, the new sub-images are detected and matched by ORB algorithm, and the matched feature points are corrected. Then, the three-dimensional coordinates of the target are obtained by binocular stereo vision. This method maximizes the speed of target detection and location. For this method, we validate it through simulation experiments. The experimental results show that the speed of this method in single target detection and location can reach 12 frames per second when the left and right image resolutions are 1280 × 720 respectively. The experimental results show that this method is effective and high-speed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wilson DB, Göktoğan AH, Sukkarieh S (2015) Experimental validation of a drogue estimation algorithm for autonomous aerial refueling. In: Proceedings of the IEEE international conference on robotics and automation (ICRA), pp 5318–5323
Portmann J, Lynen S, Chli M et al (2014) People detection and tracking from aerial thermal views. In: Proceedings of the IEEE international conference on robotics and automation (ICRA), pp 1794–1800
Gossow D, Weikersdorfer D, Beetz M (2012) Distinctive texture features from perspective-invariant keypoints. In: Proceedings of the 21st international conference on pattern recognition (ICPR 2012), pp 2764–2767
Langer M, Kuhnert KD (2008) A new hierarchical approach in robust real-time image feature detection and matching. In: Proceedings of the 2008 19th international conference on pattern recognition, pp 1–4
Kaur J, Bathla AK (2016) Video stabilization for an aerial surveillance system using SIFT and SURF. In: Proceedings of the 2016 2nd international conference on next generation computing technologies (NGCT), pp 742–747
Sangineto E, Nabi M, Culibrk D et al (2019) Self paced deep learning for weakly supervised object detection. IEEE Trans Pattern Anal Mach Intell 41(3):712–725
Zhou X, Wei G, Fu WL et al (2017) Application of deep learning in object detection. In: Proceedings of the 2017 IEEE/ACIS 16th international conference on computer and information science (ICIS), pp 631–634
Girshick R (2015) Fast R-CNN. In: Proceedings of the 2015 IEEE international conference on computer vision (ICCV), pp. 1440–1448
Ren S, He K, Girshick R et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Redmon J, Divvala S, Girshick R et al (2016) You only look once: unified, real-time object detection. In: Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 779–788
Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot multibox detector. In: Proceedings of the European conference on computer vision, pp 21–37
He K, Gkioxari G, Dollar P et al (2018) Mask R-CNN. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/tpami.2018.2844175
Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Bay H, Tuytelaars T, Gool LV (2006) SURF: speeded up robust features. In: Proceedings of the European conference on computer vision, pp 404–417
Rublee E, Rabaud V, Konolige K et al (2011) ORB: an efficient alternative to SIFT or SURF. In: Proceedings of the international conference on computer vision, pp 2564–2571
Chatfield K, Simonyan K, Vedaldi A et al (2014) Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of the British machine vision conference. arXiv:1405.3531
Brown DC (1971) Close-range camera calibration. Photogramm Eng 37:855–866
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Q., Liang, Y., Wang, Z., Li, W., Jiang, Z., Zhao, Y. (2020). Deep Learning and Binocular Stereovision to Achieve Fast Detection and Location of Target. In: Jia, Y., Du, J., Zhang, W. (eds) Proceedings of 2019 Chinese Intelligent Systems Conference. CISC 2019. Lecture Notes in Electrical Engineering, vol 593. Springer, Singapore. https://doi.org/10.1007/978-981-32-9686-2_36
Download citation
DOI: https://doi.org/10.1007/978-981-32-9686-2_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9685-5
Online ISBN: 978-981-32-9686-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)