IDP-YOLOV9: Improvement of Object Detection Model in Severe Weather Scenarios from Drone Perspective
Source abstract
Abstract
Despite their proficiency with typical environmental datasets, deep learning-based object detection algorithms struggle when faced with diverse adverse weather conditions. Moreover, existing methods often address single adverse weather scenarios, neglecting situations involving multiple concurrent adverse conditions. To tackle these challenges, we propose an enhanced approach to object detection in power construction sites under various adverse weather conditions, dubbed IDP-YOLOV9. This model leverages a parallel architecture comprising the Image Dehazing and Enhancement Processing (IDP) module and an improved YOLOV9 object detection module. Specifically, for images captured in adverse weather, our approach employs a parallel architecture that includes the Three-Weather Removal Algorithm (TRA) module and the Deep Learning-based Image Enhancement (DLIE) module, which, together, filter multiple weather factors to enhance image quality. Subsequently, we introduce an improved YOLOV9 detection network module that incorporates a three-layer routing attention mechanism for object detection. Experiments demonstrate that the IDP module significantly improves image quality by mitigating the impact of various adverse weather conditions. Compared to traditional single-processing models, our method improves recognition accuracy on complex weather datasets by 6.8% in terms of mean average precision (mAP50).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Advanced Neural Network Applications · Fire Detection and Safety Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Artificial Intelligence Security Innovation Research, Beijing Information Science and Technology University, Beijing 100192, China
Department of Information Security, Beijing Information Science and Technology University, Beijing 100192, China
National Computer System Engineering Research Institute of China, Beijing 100083, China
School of Computer Science and Technology, East China Normal University, Shanghai 200062, China
Shanghai International School of Chief Technology Officer, East China Normal University, Shanghai 200062, China
Funding
Basic Research Project of the National Defence Science and Industry Bureau
References (64)
Show source-provided references
1. Diaz Linares, I., Pardo, A., and Patch, E. (2022). IoT Privacy, Security and Forensics Challenges: An Unmanned Aerial Vehicle (UAV) Case Study. Handbook of Big Data Analytics and Forensics, Springer.10.1007/978-3-030-74753-4_2 ↗
2. (2021). Introducing the Discrete Path Transform (DPT) and its applications in signal analysis, artefact removal, and spoken word recognition. Digit. Signal Process., 117, 103158.10.1016/j.dsp.2021.103158 ↗
3. Silvestrov, S., and Rančić, M. (2016). Fractional-Wavelet Analysis of Positive definite Distributions and Wavelets on D’(C). Engineering Mathematics II, Springer.
4. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
5. Wu, T.H., Wang, T.W., and Liu, Y.Q. (2021, January 18–20). Real-time vehicle and distance detection based on improved yolo v5 network. Proceedings of the 2021 3rd World Symposium on Artificial Intelligence (WSAI), Guangzhou, China.10.1109/WSAI51899.2021.9486316 ↗
6. Wang, C.Y., Bochkovskiy, A., and Liao HY, M. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
7. Farhadi, A., and Redmon, J. (2018, January 18–22). Yolov3: An incremental improvement. Proceedings of the Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.
8. Engin, D., Genç, A., and Kemal Ekenel, H. (2018, January 18–23). Cycle-dehaze: Enhanced cyclegan for single image dehazing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA.10.1109/CVPRW.2018.00127 ↗
9. Abbasi, H., Amini, M., and Yu, F.R. (2023, January 18–20). Fog-Aware Adaptive YOLO for Object Detection in Adverse Weather. Proceedings of the 2023 IEEE Sensors Applications Symposium (SAS), Ottawa, ON, Canada.10.1109/SAS58821.2023.10254059 ↗
10. Luo, K., Luo, R., and Zhou, Y. (2021, January 18–20). UAV detection based on rainy environment. Proceedings of the 2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China.10.1109/IMCEC51613.2021.9482383 ↗
11. Benchmarking single-image dehazing and beyond10.1109/TIP.2018.2867951 ↗
12. Yang, H.H., Yang CH, H., and Tsai, Y.-C.J. (2020, January 4–8). Y-net: Multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazing. Proceedings of the ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9053920 ↗
13. Content feature and style feature fusion network for single image dehazing
14. Zhang, K., Yan, X., and Wang, Y. (2023, January 26–29). Adaptive Dehazing YOLO for Object Detection. Proceedings of the International Conference on Artificial Neural Networks, Heraklion, Greece.10.1007/978-3-031-44195-0_2 ↗
15. Selective generative adversarial network for raindrop removal from a single image10.1016/j.neucom.2020.06.134 ↗
16. Qin, Q., Chang, K., Huang, M., and Li, G. (2022, January 4–8). DENet: Detection-driven Enhancement Network for Object Detection Under Adverse Weather Conditions. Proceedings of the Asian Conference on Computer Vision, Macao, China.10.1007/978-3-031-26313-2_30 ↗
17. Object detection based on semi-supervised domain adaptation for imbalanced domain resources10.1007/s00138-020-01068-3 ↗
18. Yin, X., Yu, Z., Fei, Z., Lv, W., and Gao, X. (2023, January 26–29). PE-YOLO: Pyramid Enhancement Network for Dark Object Detection. Proceedings of the International Conference on Artificial Neural Networks, Heraklion, Greece.10.1007/978-3-031-44195-0_14 ↗
19. Sindagi, V.A., Oza, P., and Yasarla, R. (2020, January 23–28). Prior-based domain adaptive object detection for hazy and rainy conditions. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XIV 16.10.1007/978-3-030-58568-6_45 ↗
20. Vehicle detection and tracking in adverse weather using a deep learning framework10.1109/TITS.2020.3014013 ↗
21. A fast and adaptive method for image contrast enhancement
22. Adaptive image enhancement method for correcting low-illumination images10.1016/j.ins.2019.05.015 ↗
23. Exposure: A white-box photo post-processing framework
24. Yu, R., Liu, W., Zhang, Y., Qu, Z., Zhao, D., and Zhang, B. (2018, January 2–8). Deepexposure: Learning to expose photos with asynchronously reinforced adversarial learning. Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS), Montreal, QC, Canada.
25. Hyperspectral image classification using wavelet transform-based smooth ordering10.1142/S0219691319500504 ↗
26. Learning image-adaptive 3d lookup tables for high performance photo enhancement in real-time
27. TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning10.1111/cgf.14692 ↗
28. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising10.1109/TIP.2017.2662206 ↗
29. Kim, J., Lee, J.K., and Lee, K.M. (2016, January 27–30). Accurate image super-resolution using very deep convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.182 ↗
30. Guariglia, E. (2018). Harmonic Sierpinski Gasket and Applications. Entropy, 20.10.3390/e20090714 ↗
31. Neural style transfer: A review10.1109/TVCG.2019.2921336 ↗
32. Automatic single-image-based rain streaks removal via image decomposition10.1109/TIP.2011.2179057 ↗
33. Fu, X., Huang, J., and Zeng, D. (2017, January 21–26). Removing rain from single images via a deep detail network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.186 ↗
34. Joint rain detection and removal from a single image with contextualized deep networks10.1109/TPAMI.2019.2895793 ↗
35. Li, R., Cheong, L.F., and Tan, R.T. (2019, January 15–20). Heavy rain image restoration: Integrating physics model and conditional adversarial learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00173 ↗
36. Eigen, D., Krishnan, D., and Fergus, R. (2013, January 1–8). Restoring an image taken through a window covered with dirt or rain. Proceedings of the 2013 IEEE International Conference on Computer Vision, Sydney, NSW, Australia.10.1109/ICCV.2013.84 ↗
37. Quan, Y., Deng, S., Chen, Y., and Ji, H. (November, January 27). Deep learning for seeing through window with raindrops. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
38. Single-image snow removal algorithm based on generative adversarial networks10.1049/ipr2.12887 ↗
39. Guo, C.G., Li, C., Guo, J., Loy, C.C., Hou, J., Kwong, S., and Cong, R. (2020, January 13–19). Zero-reference deep curve estimation for low-light image enhancement. Proceedings of the IEEE/CVF Conference Computer Vision Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00185 ↗
40. Single image haze removal using dark channel prior
41. Liu, X., Ma, Y., Shi, Z., and Chen, J. (November, January 27). Griddehazenet: Attention-based multi-scale network for image dehazing. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
42. Dong, H., Pan, J., and Xiang, L. (2020, January 13–19). Multi-scale boosted dehazing network with dense feature fusion. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00223 ↗
43. A Framework of Adaptive Multiscale Wavelet Decomposition for Signals on Undirected Graphs10.1109/TSP.2019.2896246 ↗
44. Qin, X., Wang, Z., Bai, Y., Xie, X., and Jia, H. (2020, January 7–12). FFANet: Feature fusion attention network for single image dehazing. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i07.6865 ↗
45. Li, B., Peng, X., Wang, Z., Xu, J., and Feng, D. (2017, January 22–29). Aodnet: All-in-one dehazing network. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.511 ↗
46. IDRLP: Image dehazing using region line prior10.1109/TIP.2021.3122088 ↗
47. Multi-scale deep residual learning-based single image haze removal via image decomposition10.1109/TIP.2019.2957929 ↗
48. Nalla, B.T., Sharma, T., Verma, N.K., and Sahoo, S.R. (2018, January 8–13). Image dehazing for object recognition using faster RCNN. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489280 ↗
49. Likhitaa, P.S., and Anand, R. (2021, January 8–10). A Comparative Analysis of Image Dehazing using Image Processing and Deep Learning Techniques. Proceedings of the 2021 6th International Conference on Communication and Electronics Systems (ICCES), Coimbatre, India.10.1109/ICCES51350.2021.9489118 ↗
50. Hnewa, M., and Radha, H. (2021, January 19–22). Multiscale domain adaptive yolo for cross-domain object detection. Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA.10.1109/ICIP42928.2021.9506039 ↗
51. Liu, W., Ren, G., and Yu, R. (March, January 22). Image-adaptive YOLO for object detection in adverse weather conditions. Proceedings of the AAAI Conference on Artificial Intelligence, Online.
52. On the Weierstrass-Mandelbrot fractal function10.1098/rspa.1980.0044 ↗
53. A Deep Learning-Based Object Detection Scheme by Improving YOLOv5 for Sprouted Potatoes Datasets10.1109/ACCESS.2022.3192406 ↗
54. A dense pedestrian detection algorithm with improved YOLOv8
55. Traffic sign recognition model in haze weather based on YOLOv5
56. Occlusion aware facial expression recognition using CNN with attention mechanism10.1109/TIP.2018.2886767 ↗
57. Occlusion-Aware Transformer With Second-Order Attention for Person Re-Identification10.1109/TIP.2024.3393360 ↗
58. Mosleh, A., Sharma, A., Onzon, E., Mannan, F., Robidoux, N., and Heide, F. (2020, January 13–19). Hardware-in-the-Loop End-to-End Optimization of Camera Image Processing Pipelines. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00755 ↗
59. Guo, Q., Sun, J., and Xu, F.J. (2021, January 2–9). Efficientderain: Learning pixel-wise dilation filtering for high-efficiency single-image deraining. Proceedings of the AAAI Conference on Artificial Intelligence, virtually.10.1609/aaai.v35i2.16239 ↗
60. Ding, Y., Xue, X., and Wang, Z. (December, January 30). Domain knowledge driven deep unrolling for rain removal from single image. Proceedings of the 2018 7th International Conference on Digital Home (ICDH), Guilin, China.10.1109/ICDH.2018.00010 ↗
61. Image snow removal methods for robotic environment fusion10.3901/JME.2019.11.098 ↗
62. Li, R., Tan, R.T., and Cheong, L.F. (2020, January 14–19). All in one bad weather removal using architectural search. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00324 ↗
63. The pascal visual object classes (voc) challenge10.1007/s11263-009-0275-4 ↗
64. Ancuti, C.O., Ancuti, C., and Sbert, M. (2019, January 22–25). Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images. Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan.10.1109/ICIP.2019.8803046 ↗