Browse > Article
http://dx.doi.org/10.5139/JKSAS.2021.49.10.883

A Study on Realtime Drone Object Detection Using On-board Deep Learning  

Lee, Jang-Woo (LIG Nex1 Co.)
Kim, Joo-Young (LIG Nex1 Co.)
Kim, Jae-Kyung (LIG Nex1 Co.)
Kwon, Cheol-Hee (LIG Nex1 Co.)
Publication Information
Journal of the Korean Society for Aeronautical & Space Sciences / v.49, no.10, 2021 , pp. 883-892 More about this Journal
Abstract
This paper provides a process for developing deep learning-based aerial object detection models that can run in realtime on onboard. To improve object detection performance, we pre-process and augment the training data in the training stage. In addition, we perform transfer learning and apply a weighted cross-entropy method to reduce the variations of detection performance for each class. To improve the inference speed, we have generated inference acceleration engines with quantization. Then, we analyze the real-time performance and detection performance on custom aerial image dataset to verify generalization.
Keywords
Deep Learning; Object Detection; Data Augmentation; Transfer Learning; Class Imbalance; Inference Acceleration;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Panchapagesan, S., Sun, M., Khare, A., Matsoukas, S., Mandal, A., Hoffmeister, B. and Vitaladevuni, S., "Multi-task learning and weighted cross-entropy for DNN-based keyword spotting," Interspeech, Vol. 9, September 2016, pp. 760~764.
2 Lee, J., Wang, J., Crandall, D., Sabanovic, S. and Fox, G., "Real-time, cloud-based object detection for unmanned aerial vehicles," International Conference on Robotic Computing (IRC) IEEE, April 2017, pp. 36~43.
3 Du, D., et al, "The unmanned aerial vehicle benchmark: Object detection and tracking," Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 370~386.
4 Xia, G. S., et al, "DOTA: A large-scale dataset for object detection in aerial images," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3974~3983.
5 Du, D., et al, "VisDrone-DET2019: The vision meets drone object detection in image challenge results," Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019.
6 Ren, S., He, K., Girshick, R. and Sun, J., "Faster r-cnn: Towards real-time object detection with region proposal networks," Advances in Neural Information Processing Systems, Vol. 28, 2015, pp. 91~99.
7 Redmon, J. and Farhadi, A., "Yolov3: An incremental improvement," Computer Vision and Pattern Recognition, April 2018.
8 Hanif, A. and Azhar, N., "Resolving class imbalance and feature selection in customer churn dataset," International Conference on Frontiers of Information Technology (FIT), 2017, pp. 82~86.
9 Jiao, L., Zhang, F., Liu, F., Yang, S., Li, L., Feng, Z. and Qu, R., "A survey of deep learningbased object detection," IEEE Access, Vol. 7, 2019, pp. 128837~128868.   DOI
10 Vaddi, S., "Efficient object detection model for real-time UAV applications," Doctoral dissertation Iowa State University, 2019.
11 Yoo, S. M., Lee, K. H., Park, J., Yoon, S. J., Cho, C., Jung, Y. J. and Cho, I. Y., "Trends in Deep Learning Inference Engines for Embedded Systems," Electronics and Telecommunications Trends, Vol. 34, No. 4, 2019, pp. 23~31.
12 Padilla, R., Netto, S. L. and da Silva, E. A., "A survey on performance metrics for object-detection algorithms.," International Conference on Systems, Signals and Image Processing (IWSSIP), 2020, pp. 237~242.
13 Lin, T. Y., et al, "Microsoft coco: Common objects in context," European Conference on Computer Vision, 2014, pp. 740~755.
14 Salman, H., Ilyas, A., Engstrom, L., Kapoor, A. and Madry, A., "Do adversarially robust imagenet models transfer better?," arXiv preprint arXiv:2007.08489, 2020.
15 Shorten, C. and Khoshgoftaar, T. M., "A survey on image data augmentation for deep learning," Journal of Big Data, Vol. 6, No. 1, 2019, pp. 1~48.   DOI
16 Yosinski, J., Clune, J., Bengio, Y. and Lipson, H., "How transferable are features in deep neural networks?," arXiv preprint arXiv:1411.1792, 2014.