Sukanya Randhawa
Alexander Zipf
ABSTRACT
Filling data gaps in various global regions requires a robust approach that can accurately provide detection results from earth observation data. One of the challenges arises from significant heterogeneity in satellite images and variation in features and characteristics for specific ground objects like Wastewater Treatment Plants (WTPs). To overcome these challenges, we propose a novel multiscale multifeature hybrid model. This model leverages the power of deep learning-based object detection models, namely Yolov6, RTMDET, EfficientDET, and Domain Adaptation, to accurately and efficiently identify WTP locations worldwide. Our approach focuses on performance enhancements, including reduced false positives (FPs) and broad coverage. The strategies for achieving these improvements involve effective data processing approaches, model tuning, and adaptation. Moreover, we optimize training data features using Volunteered Geographic Information (VGI) data. We demonstrated the effectiveness of the suggested approach for three diverse global regions: Germany, France, and Malaysia. Our study gives new insights into WTP distribution when compared to existing databases like OpenStreetMap (OSM). The resulting pipeline delivers good results even in challenging rural and urban context. Moreover, it is well-suited for generating large scale WTP datasets, which is useful for many applications such as Critical Water Infrastructure mapping, Urban Planning, Climate Action and many more.
- U.S. Environmental Protection Agency. 2016. (2016).Google Scholar
- Tolga Bakırman. 2023. An Assessment of YOLO Architectures for Oil Tank Detection from SPOT Imagery. International Journal of Environment and Geoinformatics 10, 1 (2023), 9 -- 15. Google ScholarCross Ref
- Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-End Object Detection with Transformers. http://arxiv.org/abs/2005.12872 cite arxiv:2005.12872.Google Scholar
- Jiaoyan Chen, Yan Zhou, Alexander Zipf, and Hongchao Fan. 2019. Deep Learning From Multiple Crowds: A Case Study of Humanitarian Mapping. IEEE Transactions on Geoscience and Remote Sensing 57, 3 (2019), 1713--1722. Google ScholarCross Ref
- Jiaoyan Chen and Alexander Zipf. 2017. Deep Learning with Satellite Images and Volunteered Geographic Information. 63--78. Google ScholarCross Ref
- Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, and Jian Sun. 2021. RepVGG:Making VGG-stay ConvNets Great Again. In in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.Google Scholar
- P Gajalakshmi, J V Satyanarayana, G Venkat Reddy, and Sunita Dhavale. 2020. Detection of Strategic Targets of Interest in Satellite Images using YOLO. In 2020 4th International Conference on Computer, Communication and Signal Processing (ICCCSP). 1--5. Google ScholarCross Ref
- Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. The Journal of Machine Learning Research 17, 1 (2016), 2096--2030.Google ScholarDigital Library
- Zhora Gevorgyan. 2022. SIoU Loss: More Powerful Learning for Bounding Box Regression. arXiv preprint arXiv:2205.12740 (2022). Google ScholarCross Ref
- Yulia Grinblat, Sukanya Randhawa, Yuze Li, and et. al. [n. d.]. Towards scalable geosmart wastewater treatment plant detection with decision-tree-based models and Sentinel-2 data. ([n. d.]). https://doi.org/TBAGoogle Scholar
- Mazin Hnewa and Hayder Radha. 2021. Multiscale Domain Adaptive Yolo For Cross-Domain Object Detection. In 2021 IEEE International Conference on Image Processing (ICIP). 3323--3327. Google ScholarCross Ref
- Toan Minh Hoang, Phong Ha Nguyen, Noi Quang Truong, Young Won Lee, and Kang Ryoung Park. 2019. Deep RetinaNet-Based Detection and Classification of Road Markings by Visible Light Camera Sensors. Sensors 19, 2 (2019). Google ScholarCross Ref
- Chuyi Li, Lulu Li, Hongliang Jiang, Kaiheng Weng, Yifei Geng, Liang Li, Zaidan Ke, Qingyuan Li, Meng Cheng, Weiqiang Nie, et al. 2022. YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022).Google Scholar
- Guofa Li, Zefeng Ji, Xingda Qu, Rui Zhou, and Dongpu Cao. 2022. Cross-Domain Object Detection for Autonomous Driving: A Stepwise Domain Adaptative YOLO Approach. IEEE Transactions on Intelligent Vehicles 7, 3 (2022), 603--615. Google ScholarCross Ref
- Hao Li, Pedram Ghamisi, Benhood Rasti, Zhaoyan Wu, Aurelie Shapiro, Michael Schultz, and Alexander Zipf. 2020. A multi-sensor fusion framework based on coupled residual convolutional neural networks. Remote Sensing 12, 12 (2020).Google Scholar
- Hao Li, Johannes Zech, Danfeng Hong, Pedram Ghamisi, Michael Schultz, and Alexander Zipf. 2022. Leveraging OpenStreetMap and Multimodal Remote Sensing Data with Joint Deep Learning for Wastewater Treatment Plants Detection. International Journal of Applied Earth Observation and Geoinformation 110 (2022).Google ScholarCross Ref
- Hao Li, Johannes Zech, Christina Ludwig, Sascha Fendrich, Aurelie Shapiro, Michael Schultz, and Alexander Zipf. 2021. Automatic mapping of national surface water with Open-StreetMap and Sentinel-2 MSI data using deep learning. International Journal of Applied Earth Observation and Geoinformation 104 (2021).Google Scholar
- Wenwen et. al. Li. 2020. GeoAI: Where machine learning and big data converge in GIScience. Journal of Spatial Information Science 20 (2020), 71--77. Google ScholarCross Ref
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal Loss for Dense Object Detection. In 2017 IEEE International Conference on Computer Vision (ICCV). 2999--3007. Google ScholarCross Ref
- Pengyuan Liu and Filip Biljecki. 2022. A review of spatially-explicit GeoAI applications in Urban Geography. International Journal of Applied Earth Observation and Geoinformation 112 (2022), 102936. 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, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International Publishing, Cham, 21--37.Google Scholar
- Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo. 2021. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, Los Alamitos, CA, USA, 9992--10002. Google ScholarCross Ref
- Chengqi Lyu, Wenwei Zhang, Haian Huang, Yue Zhou, Yudong Wang, Yanyi Liu, Shilong Zhang, and Kai Chen. 2022. RTMDet: An Empirical Study of Designing Real-Time Object Detectors. arXiv:2212.07784 [cs.CV]Google Scholar
- Chengqi Lyu, Wenwei Zhang, Haian Huang, Yue Zhou, Yudong Wang, Yanyi Liu, Shilong Zhang, and Kai Chen. 2022. RTMDet: An Empirical Study of Designing Real-Time Object Detectors. arXiv preprint arXiv:2212.07784 (2022). Google ScholarCross Ref
- World Health Organization. 2019. (2019).Google Scholar
- Claudio Persello, Jan Wegner, Ronny Hänsch, Devis Tuia, Pedram Ghamisi, Mila Koeva, and Gustau Camps-Valls. 2022. Deep Learning and Earth Observation to Support the Sustainable Development Goals: Current Approaches, Open Challenges, and Future Opportunities. IEEE Geoscience and Remote Sensing Magazine (2022).Google Scholar
- M. Raifer, Rafael Troilo, and F. et al. Kowatsch. 2019. OSHDB: a framework for spatio-temporal analysis of OpenStreetMap history data. (Aug. 2019). Google ScholarCross Ref
- Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You Only Look Once: Unified, Real-Time Object Detection. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 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. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (Eds.), Vol. 28. Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2015/file/14bfa6bb14875e45bba028a21ed38046-Paper.pdfGoogle Scholar
- Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, and Silvio Savarese. 2019. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. In in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.Google ScholarCross Ref
- Dimitrios Sykas, Maria Sdraka, Dimitrios Zografakis, and Ioannis Papoutsis. 2022. A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 15 (2022), 3323--3339. Google ScholarCross Ref
- Mingxing Tan, Ruoming Pang, and Quoc V. Le. 2020. EfficientDet: Scalable and Efficient Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
- Franklin; Stensel David Tchobanoglous, George; Burton. 2003. (2003).Google Scholar
- Eric Tzeng, Judy Hoffman, Kate Saenko, and Trevor Darrell. 2017. Adversarial Discriminative Domain Adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google ScholarCross Ref
- Brandon Victor, Zhen He, and Aiden Nibali. 2022. A systematic review of the use of Deep Learning in Satellite Imagery for Agriculture.Google Scholar
- Zhaoxan Wu, Hao Li, and Alexander Zipf. 2020. From Historical OpenStreetMap data to customized training samples for geospatial machine learning. Proceedings of the Academic Track at the State of the Map 2020 Online Conference (2020).Google Scholar
- Gui-Song Xia, Xiang Bai, Jian Ding, Zhen Zhu, Serge Belongie, Jiebo Luo, Mihai Datcu, Marcello Pelillo, and Liangpei Zhang. 2018. DOTA: A Large-Scale Dataset for Object Detection in Aerial Images. In in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.Google Scholar
- Jiangye Yuan, Hsiu-Han Lexie Yang, Olufemi A. Omitaomu, and Budhendra L. Bhaduri. 2016. Large-scale solar panel mapping from aerial images using deep convolutional networks. In 2016 IEEE International Conference on Big Data (Big Data). 2703--2708. Google ScholarCross Ref
- Haoyang Zhang, Ying Wang, Feras Dayoub, and Sünderhauf Niko. 2021. VerifocalNet: An IoU-aware Dense Object Detector. In in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.Google Scholar
- Barret Zoph, Ekin D. Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, and Quoc V. Le. 2020. Learning Data Augmentation Strategies for Object Detection. In Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision - ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12372. Springer, Cham.Google Scholar
Index Terms
- Multiscale Multifeature Vision Learning for Scalable and Efficient Wastewater Treatment Plant Detection using Hi-Res Satellite Imagery and OSM
Recommendations
VGI as a dynamically updating data source in location-based services in urban environments
UbiCrowd '11: Proceedings of the 2nd international workshop on Ubiquitous crowdsouringUrban environments, or living cities, share the characteristic of a high degree of organized complexity. This complexity arises from the components of the urban fabric: streets, shops, offices, houses, pedestrian zones, green spaces, plazas, parking ...
Precise orbit determination for BDS-3 satellites using satellite-ground and inter-satellite link observations
Since November 2017, eight BeiDou global navigation system (BDS-3) satellites equipped with Ka-band inter-satellite link (ISL) payloads have been launched into medium earth orbit. We present the precise orbit determination (POD) for BDS-3 satellites ...
Automatic Geolocation Correction of Satellite Imagery
Modern satellites tag their images with geolocation information using GPS and star tracking systems. Depending on the quality of the geopositioning equipment, errors may range from a few meters to tens of meters on the ground. At the current state of ...
Comments