ABSTRACT
Object detection in aerial images has garnered significant attention from the research community in recent years. The challenges posed by small objects, diverse orientations, and complex backgrounds have spurred extensive research efforts. In this paper, we focus on object detection in a YOLOv7-based framework, to address the issue of overlapping predicted regions, we introduce and apply the Soft-NMS (Non-Maximum Suppression) technique, a post-processing method known for its effectiveness in improving detection accuracy in such scenarios. Soft-NMS adjusts bounding box scores based on the extent of overlap, allowing for more accurate localization of objects in densely populated regions. Furthermore, we present comprehensive experimental results to validate the efficacy of our proposed approach. The analyses encompass a thorough evaluation on the UCAS Aerial Object Detection (UCAS AOD) dataset, comprising over 1500 aerial images captured from diverse perspectives. Our method has demonstrated an improvement in object detection performance, particularly in scenarios with closely positioned objects. The proposed framework showcases its ability to handle complex aerial scenes with higher precision and recall rates compared to conventional methods.
- Navaneeth Bodla, Bharat Singh, Rama Chellappa, and Larry S Davis. 2017. Soft-NMS–improving object detection with one line of code. In Proceedings of the IEEE international conference on computer vision. 5561–5569.Google ScholarCross Ref
- Yaru Cao, Zhijian He, Lujia Wang, Wenguan Wang, Yixuan Yuan, Dingwen Zhang, Jinglin Zhang, Pengfei Zhu, Luc Van Gool, Junwei Han, 2021. VisDrone-DET2021: The vision meets drone object detection challenge results. In Proceedings of the IEEE/CVF International conference on computer vision. 2847–2854.Google ScholarCross Ref
- Chunling Chen, Ziyue Zheng, Tongyu Xu, Shuang Guo, Shuai Feng, Weixiang Yao, and Yubin Lan. 2023. YOLO-Based UAV Technology: A Review of the Research and Its Applications. Drones 7, 3 (2023), 190.Google Scholar
- MMYOLO Contributors. 2022. MMYOLO: OpenMMLab YOLO series toolbox and benchmark.Google Scholar
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980–2988.Google ScholarCross Ref
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer, 21–37.Google Scholar
- Khang Nguyen, Nhut T Huynh, Phat C Nguyen, Khanh-Duy Nguyen, Nguyen D Vo, and Tam V Nguyen. 2020. Detecting objects from space: An evaluation of deep-learning modern approaches. Electronics 9, 4 (2020), 583.Google ScholarCross Ref
- Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 779–788.Google ScholarCross Ref
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015).Google Scholar
- Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. 2023. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7464–7475.Google ScholarCross Ref
- Ze Yang, Shaohui Liu, Han Hu, Liwei Wang, and Stephen Lin. 2019. Reppoints: Point set representation for object detection. In Proceedings of the IEEE/CVF international conference on computer vision. 9657–9666.Google ScholarCross Ref
- Haigang Zhu, Xiaogang Chen, Weiqun Dai, Kun Fu, Qixiang Ye, and Jianbin Jiao. 2015. Orientation robust object detection in aerial images using deep convolutional neural network. In 2015 IEEE International Conference on Image Processing (ICIP). IEEE, 3735–3739.Google ScholarDigital Library
- Pengfei Zhu, Longyin Wen, Dawei Du, Xiao Bian, Heng Fan, Qinghua Hu, and Haibin Ling. 2021. Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 11 (2021), 7380–7399.Google ScholarCross Ref
Index Terms
- Optimizing Results in Aerial Images through Post-Processing Techniques on YOLOv7
Recommendations
Helmet detection algorithm based on improved yolov7
CSAI '23: Proceedings of the 2023 7th International Conference on Computer Science and Artificial IntelligenceIn order to solve the problems of low detection accuracy, wrong detection and missed detection in the traditional target detection algorithm in the safety helmet detection task, a safety helmet detection algorithm based on improved YOLOv7 is proposed. ...
Safety Helmet Detection Based on YOLOv7
CSAE '22: Proceedings of the 6th International Conference on Computer Science and Application EngineeringFrequent safety accidents have posed a significant risk to workers' lives recently. In particular, the risk of head injury is significantly increased by workers not wearing helmets. However, manual supervision is inefficient and costly. Even though ...
Improved YOLOv7 UAV image small target detection algorithm
CSAI '23: Proceedings of the 2023 7th International Conference on Computer Science and Artificial IntelligenceIn order to improve the detection efficiency of small targets in UAV images in traffic systems, a small target detection algorithm for UAV images in traffic systems based on improved YOLOv7 is proposed. In the feature fusion network, the small target ...
Comments