All Issue

2025 Vol.16, Issue 4 Preview Page

General Article

Weather-aware deep learning framework for sustainable urban surveillance and infrastructure resilience
Sandhya Sharma1
,
Arjit Tomar2*
,
Pramod Kumar Sagar3
1Research Scholar, Department of Computer Science and Engineering, Noida International University, Noida, Uttar Pradesh, India
2Associate Professor, Department of Computer Science and Engineering, Noida International University, Noida, Uttar Pradesh, India
3Associate Professor, Department of Computer Science and Engineering, Raj Kumar Goel Institute of Technology, Ghaziabad, Uttar Pradesh, India
*Corresponding Author
31 December 2025. pp. 445-460
PDF XML Citation
Abstract

Extreme weather conditions such as fog, rain, snow, and sandstorms reduce visibility, hindering reliable monitoring of urban spaces and critical infrastructure. This limitation affects structural health inspections, facility management, and public safety, key components of sustainable urban development. This study introduces a weather-aware computer vision framework designed to maintain high detection accuracy under adverse meteorological conditions, supporting resilient and climate-adaptive urban monitoring. The system employs a modular two-stage deep learning pipeline, integrating weather-specific enhancement modules (AOD-Net for dehazing, DerainNet for deraining) into a learnable adaptive fusion network. Enhanced images are processed with Faster R-CNN for high- precision object detection. Evaluations on benchmark datasets (DAWN, MS COCO, EXDARK, PASCAL VOC) demonstrate superior performance over SSD, YOLOv3, and RetinaNet, achieving mAP@ [.5:.95] of 68.93 with F1-score 0.76, recall 0.73, precision 0.79, and IoU 0.64. Image quality metrics (SSIM = 0.89, PSNR = 27.93 dB, MSE = 101.37) confirm significant restoration capability. By ensuring accurate detection in challenging climates, the framework enables early hazard identification, improved asset management, and safer public spaces. Its scalability makes it suitable for smart city surveillance, autonomous inspection of building facades, and infrastructure resilience assessments. Future research will focus on lightweight deployment for real-time inference on edge devices, enabling cost- effective, energy-efficient, and sustainable monitoring solutions for weather-vulnerable urban environments.

Keywords
object detection
AOD-net
DerainNet
faster R-CNN
image enhancement
critical infrastructure
building facades
References
1

J. Kaur and W. Singh, Tools, techniques, datasets and application areas for object detection in an image: a review. Multimed. Tools Appl. 81(27) (2022), pp. 38297-38351. DOI: 10.1007/s11042-022-13153-y.

10.1007/s11042-022-13153-y35493415PMC9033309
2

M. Jeon, J. Seo, and J. Min, DA-RAW: Domain Adaptive Object Detection for Real-World Adverse Weather Conditions. Proc. - IEEE Int. Conf. Robot. Autom. (2024), pp. 2013-2020. DOI: 10.1109/ICRA57147.2024.10611219 57147.2024.10611219.

10.1109/ICRA57147.2024.10611219
3

T. Sharma, B. Debaque, N. Duclos, A. Chehri, B. Kinder, and P. Fortier, Deep Learning-Based Object Detection and Scene Perception under Bad Weather Conditions. Electron. 11(4) (2022), pp. 1-11. DOI: 10.3390/electronics11040563.

10.3390/electronics11040563
4

F. Yu, H. Chen, X. Wang, W. Xian, Y. Chen, F. Liu, V. Madhavan, and T. Darrell, BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (2020), pp. 2633-2642. DOI: 10.1109/CVPR42600.2020.00271.

10.1109/CVPR42600.2020.00271
5

K. Burnett, D.J. Yoon, Y. Wu, A.Z. Li, H. Zhang, S. Lu, J. Qian, W.-K. Tseng, A. Lambert, K.Y.K. Leung, A.P. Schoellig, and T.D. Barfoot,, Boreas: A multi-season autonomous driving dataset. Int. J. Rob. Res. 42(1-2) (2023), pp. 33-42. DOI: 10. 1177/02783649231160195.

10.1177/02783649231160195
6

M.A. Kenk and M. Hassaballah, DAWN: Vehicle Detection in Adverse Weather Nature Dataset. (2020), pp. 1-6. DOI: 10.17632/766ygrbt8y.3.

10.17632/766ygrbt8y.3
7

X. Huang, M.Y. Liu, S. Belongie, and J. Kautz, Multimodal Unsupervised Image-to-Image Translation. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), LNCS, 11207 (2018), pp. 179-196. DOI: 10.1007/978-3-030-01219-9_11.

10.1007/978-3-030-01219-9_11
8

X. Li, K. Kou, and B. Zhao, Weather GAN: Multi- Domain Weather Translation Using Generative Adversarial Networks. (2021), pp. 1-10.

9

N. Zhang, L. Zhang, and Z. Cheng, Towards Simulating Foggy and Hazy Images and Evaluating Their Authenticity BT - Neural Information Processing. D. Liu, S. Xie, Y. Li, D. Zhao, and E.-S. M. El-Alfy, Eds. 2017, Cham: Springer International Publishing, pp. 405-415.

10.1007/978-3-319-70090-8_42
10

K. Garg and S.K. Nayar, Photorealistic rendering of rain streaks. ACM SIGGRAPH 2006 Pap. SIGGRAPH ’06. (2006), pp. 996-1002. DOI: 10. 1145/1179352.1141985.

10.1145/1179352.1141985
11

M. Tremblay, S.S. Halder, R. de Charette, and J.-F. Lalonde, Rain Rendering for Evaluating and Improving Robustness to Bad Weather. Int. J. Comput. Vis. 129(2) (2021), pp. 341-360. DOI: 10.1007/s11263-020-01366-3.

10.1007/s11263-020-01366-3
12

F. AlHindaassi, M.T. Alam, and F. Karray, ADAM- Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions. 2025.

13

S. Karavarsamis, I. Gkika, V. Gkitsas, K. Konstantoudakis, and D. Zarpalas, A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze. Sensors. 22(13) (2022). DOI: 10.3390/s22134707.

10.3390/s2213470735808203PMC9269588
14

S. Li, I.B. Araujo, W. Ren, Z. Wang, E.K. Tokuda, R. Hirata Júnior, J. César, M. Roberto, J. Zhang, and X. Guo, Single image deraining: A comprehensive benchmark analysis. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 2019- June (2019), pp. 3833-3842. DOI: 10.1109/CVPR.2019.00396. 2019.00396.

10.1109/CVPR.2019.00396
15

D. Singh and V. Kumar, A Comprehensive Review of Computational Dehazing Techniques. Arch. Comput. Methods Eng. 26(5) (2019), pp. 1395-1413. DOI: 10.1007/s11831-018-9294-z.

10.1007/s11831-018-9294-z
16

G. Jie, C. Xiaofeng, C. Yuan, R. Wenqi, Z. Jun, Z. Jing, and T. Dacheng, A Comprehensive Survey on Image Dehazing Based on Deep Learning. Proc. Thirtieth Int. Jt. Conf. Artif. Intell. (2021), pp. 4426-4433. DOI: 10.24963/ijcai.2021/604.

10.24963/ijcai.2021/604
17

C.A. Zhang, H. Wang, Y. Cai, L. Chen, Y. Li, M.A. Sotelo, Z. Li,, Robust-FusionNet: Deep Multimodal Sensor Fusion for 3-D Object Detection Under Severe Weather Conditions. IEEE Trans. Instrum. Meas. 71 (2022), pp. 1-13. DOI: 10.1109/ TIM.2022.3191724.

10.1109/TIM.2022.3191724
18

P. Shyam and H. Yoo, Lightweight Thermal Super-Resolution and Object Detection for Robust Perception in Adverse Weather Conditions. Proc. - 2024 IEEE Winter Conf. Appl. Comput. Vision, WACV 2024. (2024), pp. 7456-7467. DOI: 10. 1109/WACV57701.2024.00730.

10.1109/WACV57701.2024.00730
19

Y. Wang, H. Yang, W. Zhang, and S. Lu, UniDet- D: A Unified Dynamic Spectral Attention Model for Object Detection under Adverse Weathers. 2025, pp. 1-10.

20

Z. Chu, D-YOLO a robust framework for object detection in adverse weather conditions. 2024.

21

M. Maruzuki, M. Osman, A. Shafie, S. Setumin, A. Ibrahim, H. Saleh, M. Tahir, and A. Rabiain,, Road Image Deblurring with Nonlinear Activation Free Network. in 2024 IEEE 14th International Conference on Control System, Computing and Engineering. (2024), pp. 288-293. DOI: 10. 1109/ICCSCE61582.2024.10696495.

10.1109/ICCSCE61582.2024.10696495
22

D. Li, E. Wang, Z. Li, Y. Yin, L. Zhang, and C. Zhao, STE-YOLO: A Surface Defect Detection Algorithm for Steel Strips. Electron. 14(1) (2025), pp. 1-21. DOI: 10.3390/electronics14010054.

10.3390/electronics14010054
23

Z. Liu, T. Fang, H. Lu, W. Zhang, and R. Lan, MASFNet: Multiscale Adaptive Sampling Fusion Network for Object Detection in Adverse Weather. IEEE Trans. Geosci. Remote Sens. 63 (2025), pp. 1-15. DOI: 10.1109/TGRS.2025.3558541.

10.1109/TGRS.2025.3558541
24

P. Zhang, G. Cheng, C. Lang, X. Xie, and J. Han, NIRNet: Noise Incentive Robust Network in Remote Sensing Object Detection Under Cloud Corruption. IEEE Trans. Geosci. Remote Sens. 63 (2025), pp. 1-13. DOI: 10.1109/TGRS.2025.3581342.

10.1109/TGRS.2025.3581342
25

S. Agarwal, R. Birman, and O. Hadar, WARLearn: Weather-Adaptive Representation Learning. Proc. - 2025 IEEE Winter Conf. Appl. Comput. Vision, WACV 2025. (2025) pp. 4978-4987. DOI: 10. 1109/WACV61041.2025.00487.

10.1109/WACV61041.2025.00487
26

Y. Chen, Y. Wang, Z. Zou, and W. Dan, GMS- YOLO: A Lightweight Real-Time Object Detection Algorithm for Pedestrians and Vehicles Under Foggy Conditions. IEEE Internet Things J. 12(13) (2025), pp. 23879-23890. DOI: 10.1109/JIOT.2025.3553879 25.3553879.

10.1109/JIOT.2025.3553879
27

L. Guo, X. Zhou, Y. Zhao, and W. Wu, Improved YOLOv7 algorithm incorporating InceptionNeXt and attention mechanism for vehicle detection under adverse lighting conditions. Signal, Image Video Process. 19(4) (2025), p. 299. DOI: 10.1007/ s11760-025-03868-4.

10.1007/s11760-025-03868-4
28

Z. Guo, X. Zhang, and S. Yu, Image Defogging Based on Improved AOD-Net Network Modeling. Adv. Transdiscipl. Eng. 57 (2024), pp. 211-222. DOI: 10.3233/ATDE240472.

10.3233/ATDE240472
29

T. Zheng, T. Xu, X. Li, X. Zhao, F. Zhao, and Y. Zhang, Improved AOD-Net Dehazing Algorithm for Target Image. in 2024 5th International Conference on Computer Engineering and Intelligent Control (ICCEIC). (2024), pp. 333-337. DOI: 10. 1109/ICCEIC64099.2024.10775918.

10.1109/ICCEIC64099.2024.10775918
30

B. Li, X. Peng, Z. Wang, J. Xu, and D. Feng, End-to-End United Video Dehazing and Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1) (2018).

10.1609/aaai.v32i1.12287
31

X. Fu, J. Huang, X. Ding, Y. Liao, and J. Paisley, Clearing the skies: A deep network architecture for single-image rain removal. IEEE Trans. Image Process. 26(6) (2017), pp. 2944-2956. DOI: 10. 1109/TIP.2017.2691802.

10.1109/TIP.2017.2691802
32

K. Park, S. Yu, and J. Jeong, A contrast restoration method for effective single image rain removal algorithm. 2018 Int. Work. Adv. Image Technol. IWAIT 2018. (2018), pp. 1-4. DOI: 10.1109/IWAIT.2018.8369644.

10.1109/IWAIT.2018.8369644
33

L. Gao, W. Long, Y. Li, H. Liu, X. Yu, and J. Li, RASWNet: An Algorithm That Can Remove All Severe Weather Features from a Degraded Image. IEEE Access. 8 (2020), pp. 76002-76018. DOI: 10.1109/ACCESS.2020.2989355.

10.1109/ACCESS.2020.2989355
34

S.K. Gupta, P. Gupta, and P. Singh, Enhancing UAV-HetNet Security Through Functional Encryption Framework. Concurrency and Computation: Practice and Experience. 36(20) (2024), pp. 1-22. DOI: https://doi.org/10.1002/cpe.8206.

10.1002/cpe.8206
35

S. Ren, K. He, R. Girshick, and J. Sun, Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6) (2017), pp. 1137-1149. DOI: 10.1109/TPAMI.2016.2577031.

10.1109/TPAMI.2016.2577031
36

X. Xu, M. Zhao, P. Shi, R. Ren, X. He, X. Wei, and H. Yang, Crack Detection and Comparison Study Based on Faster R-CNN and Mask R-CNN. Sensors. 22(3) (2022). DOI: 10.3390/s22031215.

10.3390/s2203121535161961PMC8838761
37

A. Banerjee, S.K. Gupta, and V. Kumar, A Genetic Algorithm-Based Approach for Collision Avoidance in a Multi-UAV Disaster Mitigation Deployment. Concurrency and Computation: Practice and Experience. 37(9-11) (2025), pp. 1-14. DOI: https://doi.org/10.1002/cpe.70061.

10.1002/cpe.70061
38

A. Magdy, M.S. Moustafa, H.M. Ebied, and M.F. Tolba, Lightweight faster R-CNN for object detection in optical remote sensing images. Sci. Rep. 15(1) (2025), pp. 1-14. DOI: 10.1038/s41598-025-99242-y 99242-y.

10.1038/s41598-025-99242-y40346125PMC12064737
39

U. Sara, M. Akter, and M.S. Uddin, Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study. J. Comput. Commun. 7(3) (2019), pp. 8-18. DOI: 10.4236/jcc.2019.73002.

10.4236/jcc.2019.73002
40

T.O. Hodson, T.M. Over, and S.S. Foks, Mean Squared Error, Deconstructed. J. Adv. Model. Earth Syst. 13(12) (2021), pp. 1-10. DOI: 10.1029/2021MS002681 MS002681.

10.1029/2021MS002681
41

D. Brunet, E.R. Vrscay, and Z. Wang, On the mathematical properties of the structural similarity index. IEEE Trans. Image Process. 21(4) (2012), pp. 1488-1495. DOI: 10.1109/TIP.2011.2173206.

10.1109/TIP.2011.2173206
42

B. Wang, A Parallel Implementation of Computing Mean Average Precision. arXiv:2206.09504. 2016 (2022), pp. 1-15.

43

R. Yacouby and D. Axman, Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models. (2020), pp. 79-91. DOI: 10.18653/v1/2020.eval4nlp-1.9 nlp-1.9.

10.18653/v1/2020.eval4nlp-1.9
44

S.K. Gupta, M. Kumar, A. Nayyar, and S. Mahajan, Unmanned Aircraft Systems. 2025, Scrivener Publishing, Wiley, 1st edition, ISBN-10: 1394230613, ISBN-13:‎ 978-1394230617.

45

O. Kaiwartya, K. Kaushik, S.K. Gupta, A. Mishra, and M. Kumar, Security and Privacy in Cyberspace. 2022. Springer Nature, 1st ed. 2022 edition (Aug. 20 2022), ISBN-10: 9811919593, ISBN-13: 978-9811919596. pp. 1-226.

46

F. van Beers, A. Lindström, E. Okafor, and M.A. Wiering, Deep Neural Networks with Intersection over Union Loss for Binary Image Segmentation. Int. Conf. Pattern Recognit. Appl. Methods. 1 (2019), pp. 438-445. DOI: 10.5220/0007347504380445.

10.5220/0007347504380445
47

A. Sharma, N. Kumar, C. Diwaker, B. Sharma, R. Baniwal, S.B. Bhattacharjee, and S. Rani. A Machine learning-based framework for energy-efficient load balancing in sustainable urban infrastructure and smart buildings. International Journal of Sustainable Building Technology and Urban Development. 15(4) (2024), pp. 498-512. DOI: 10. 22712/susb.20240035.

48

S.K. Gupta and A. Banerjee, Energy and Experimental Trust-based Task Offloading in the Domain of Connected Autonomous Vehicles. Vehicular Communications. 55 (2025), pp. 1-14. DOI: https://doi.org/10.1016/j.vehcom.2025.100954.

10.1016/j.vehcom.2025.100954
49

D. Jung and H. Lee. An analytical study on the prediction of carbonation velocity coefficient using deep learning algorithm. International Journal of Sustainable Building Technology and Urban Development. 10(4) (2019), pp. 205-215. DOI: 10. 22712/susb.20190022.

50

K. Lee, S. Lee, and H. Kim. Accelerating multi- class defect detection of building façades using knowledge distillation of DCNN-based model. International Journal of Sustainable Building Technology and Urban Development. 12(2) (2021), pp. 80-95. DOI: 10.22712/susb.20210008.

10.22712/susb.20210008
51

A. Gupta and S.K. Gupta, A Survey on Green UAV-based Fog Computing: Challenges and Future Perspective. Transactions on Emerging Telecommunications Technologies. 33(11) (2022), pp. 1-29. DOI: 10.1002/ett.4603.

10.1002/ett.4603
52

M. Kumar, N. Goyal, R.M.A. Qaisi, M. Najim, and S.K. Gupta, Game Theory based Hybrid Localization Technique for Underwater Wireless Sensor Networks. Transactions on Emerging Telecommunications Technologies. 33(11) (2022), pp. 1-23. DOI: doi.org/10.1002/ett.4572.

10.1002/ett.4572
53

P. Singh, S. Kumar, S.K. Gupta, A.K. Rai, and A, Saif, Wireless Ad-hoc and Sensor Networks: Architecture, Protocols, and Applications. 2024, Routledge, CRC Press, Taylor and Francis Group 2024, 1st Edition, eBook ISBN9781003528982, pp. 1-412. DOI: https://doi.org/10.1201/9781003528982.

10.1201/9781003528982
Information
  • Publisher :Sustainable Building Research Center (ERC) Innovative Durable Building and Infrastructure Research Center
  • Publisher(Ko) :건설구조물 내구성혁신 연구센터
  • Journal Title :International Journal of Sustainable Building Technology and Urban Development
  • Volume : 16
  • No :4
  • Pages :445-460
  • Received Date : 2025-08-19
  • Accepted Date : 2025-09-02
  • DOI :https://doi.org/10.22712/susb.20250030
Journal Informaiton International Journal of Sustainable Building Technology and Urban Development International Journal of Sustainable Building Technology and Urban Development
Online Submission
  • scopus
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
  • isc
Journal Informaiton Journal Informaiton - close