Improving UAV Object Detection through Image Augmentation
Keywords:Computer Vision, Deep Learning, Image Processing
Ground-image based object detection algorithms have had great improvements over the years and provided good results for challenging image datasets such as COCO and PASCAL VOC. These models, however, are not as successful when it comes to unmanned aerial vehicle (UAV)-based object detection and commonly performance deterioration is observed. It is due to the reason that it is a much harder task for the models to detect and classify smaller objects rather than medium-size or large-size objects, and drone imagery is prone to variances caused by different flying altitudes, weather conditions, camera angles and quality. This work explores the performance of two state-of-art-object detection algorithms on the drone object detection task and proposes image augmentation 1 procedures to improve model performance. We compose three image augmentation sequences and propose two new image augmentation techniques and further explore their different combinations on the performances of the models. The augmenters are evaluated for two deep learning models, which include model-training with high-resolution images (1056×1056 pixels) to observe their overall effectiveness. We provide a comparison of augmentation techniques across each model. We identify two augmentation procedures that increase object detection accuracy more effectively than others and obtain our best model using a transfer learning 2 approach, where the weights for the transfer are obtained from training the model with our proposed augmentation technique. At the end of the experiments, we achieve a robust model performance and accuracy, and identify the aspects of improvement as part of our future work.
L Jangwon, J Wang, D Crandall, S Sabanovic and G Fox, “Real-Time, cloud-based ˇ object detection for unmanned aerial vehicles” First IEEE International Conference on Robotic Computing (IRC), Taichung, Taiwan, DOI: 10.1109/IRC.2017.77, pp. 36 - 43, 2017.
A. Carrio, C. Sampedro, A. Rodriguez-Ramos and P. Campoy, “A review of deep learning methods and applications for unmanned aerial vehicles” Journal of Sensors, https://doi.org/10.1155/2017/3296874, 2017.
Zh. Wu, K. Suresh, P. Narayanan, H. Xu, H. Kwon and Zh. Wang, “Delving into robust object detection from unmanned aerial vehicles: A deep nuisance disentanglement approach”, Proceedings of the IEEE International Conference on Computer Vision, pp. 1201–1210, 2019.
J. Redmon and A. Farhadi, “Yolov3: An incremental improvement”, arXiv:1804.02767v1, 2018.
Zh. Huang and J. Wang, “Dc-spp-yolo: Dense connection and spatial pyramid pooling based yolo for object detection”, arXiv:1903.08589, 2019.
Glenn Jocher. Ultralytics yolov3. (2019). https://github.com/ultralytics/yolov3
Glenn Jocher. Ultralytics yolov5. (2020). https://github.com/ultralytics/yolov5
Dheeraj Reddy Pailla et al., “Visdrone-det2019: The vision meets drone object detection in image challenge results”, IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), DOI: 10.1109/ICCVW.2019.00030, 2019.
A. Jung. imgaug. (2020). Online.Available: https://github.com/aleju/imgaug
A. Bochkovskiy, C.-Yao Wang and Hong-Yuan Mark Lia, “Yolov4: Optimal speed and accuracy of object detection”, arXiv preprint arXiv:2004.10934, 2020.