Scene Recognition for Construction Projects Based on the Combination Detection of Detailed Ground Objects
Source abstract
Abstract
The automatic identification of construction projects, which can be considered as complex scenes, is a technical challenge for the supervision of soil and water conservation in urban areas. Construction projects in high-resolution remote sensing images have no unified semantic definition, thereby exhibiting significant differences in image features. This paper proposes an identification method for construction projects based on the detection of detailed ground objects, which construction projects comprise, including movable slab houses, buildings under construction, dust screens, and bare soil (rock). To create the training data set, we select highly informative detailed ground objects from high-resolution remote sensing images. Then, the Faster RCNN (region-based convolutional neural network) algorithm is used to detect construction projects and the highly informative detailed ground objects separately. The merging of detection boxes and the correction of detailed ground object combinations are used to jointly improve the confidence of construction project detection results. The empirical experiments show that the accuracy evaluation indicators of this method on a data set of Wuhan construction projects outperform other comparative methods, and its AP value and F1 score reached 0.773 and 0.417, respectively. The proposed method can achieve satisfactory identification results for construction projects with complex scenes, and can be applied to the comprehensive supervision of soil and water conservation in construction projects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Remote-Sensing Image Classification · Groundwater and Watershed Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Changjiang River Scientific Research Institute of Changjiang Water Resources Commission, Wuhan 430010, China
Research Center on Mountain Torrent & Geologic Disaster Prevention of the Ministry of Water Resources, Wuhan 430010, China
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, China
Funding
Dynamic Monitoring of Soil Erosion and Production Construction Project Supervision project of Wuhan · Annual Dynamic Monitoring of Soil and Water Loss in Fujian Province · Decomposition and Evaluation of Long-term and Phased Targets of Soil and Water Conservation Rate in Cities and Counties of Fujian Province
References (36)
Show source-provided references
1. Rafiq, W., Musarat, M.A., Altaf, M., Napiah, M., Sutanto, M.H., Alaloul, W.S., Javed, M.F., and Mosavi, A. (2021). Life Cycle Cost Analysis Comparison of Hot Mix Asphalt and Reclaimed Asphalt Pavement: A Case Study. Sustainability, 13.10.3390/su13084411 ↗
2. Built-up expansion between 2001 and 2011 in South America continues well beyond the cities10.1088/1748-9326/aad2e3 ↗
3. Strengthening supervision of engineering industry to strengthen weaknesses and strive to create a new situation of water conservancy in the new era: Speech at the 2019 National Conference on Water Conservancy Work (Abstract)
4. Ideas and requirements for promoting soil and water conservation monitoring and information technology
5. Minister E Jingping put forward clear requirements for national soil and water conservation work in 2020
6. What’s wrong with pixels? Some recent developments interfacing remote sensing and GIS
7. A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images10.1109/TGRS.2006.875360 ↗
8. Automatic Detection and Segmentation of Orchards Using Very High Resolution Imagery10.1109/TGRS.2011.2180912 ↗
9. Object detection in optical remote sensing images: A survey and a new benchark10.1016/j.isprsjprs.2019.11.023 ↗
10. Rotation-invariant object detection in high-resolution satellite imagery using superpixel-based deep Hough forests10.1109/LGRS.2015.2432135 ↗
11. Deep learning for autonomous ship-oriented small ship detection10.1016/j.ssci.2020.104812 ↗
12. Yang, X., Sun, H., Fu, K., Yang, J., Sun, X., Yan, M., and Guo, Z. (2018). Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks. Remote Sens., 10.10.3390/rs10010132 ↗
13. Technical support of artifical intelligence for informatization supervision of soil and water conservation
14. On the identification of construction disturbance patches based on optimal segmentation scale
15. Information content of very-high-resolution SAR images: Semantics, geospatial context, and ontologies10.1109/JSTARS.2014.2363595 ↗
16. Xu, Z.W., Yang, Y., and Hauptmann, A. (2015, January 7–12). A discriminative CNN video representation for event detection. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298789 ↗
17. Fan, H.H., Chang, X.J., Cheng, D., Yang, Y., Xu, D., and Hauptmann, A.G. (2017, January 22–29). Complex event detection by identifying reliable shots from untrimmed videos. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.86 ↗
18. Yu, J., Lei, A., and Hu, Y. (2019, January 8–11). Soccer video event detection based on deep learning. Proceedings of the International Conference on Multimedia Modeling, Thessaloniki, Greece.10.1007/978-3-030-05716-9_31 ↗
19. Computer vision algorithms and hardware implementations: A survey10.1016/j.vlsi.2019.07.005 ↗
20. A review of multimodal human activity recognition with special emphasis on classification, applications, challenges and future directions10.1016/j.knosys.2021.106970 ↗
21. Chang, X.H., Yang, Y., Long, G.D., Zhang, C.Q., and Hauptmann, A.G. (2016, January 12–17). Dynamic concept composition for zero-example event detection. Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.10.1609/aaai.v30i1.10474 ↗
22. Yuan, J., Zha, Z.J., Zheng, Y.T., Wang, M., Zhou, X.D., and Chua, T.S. (December, January 28). Learning concept bundles for video search with complex queries. Proceedings of the 19th ACM International Conference on Multimedia, Scottsdale, AZ, USA.
23. Semantic concept co-occurrence patterns for image annotation and retrieval10.1109/TPAMI.2015.2469281 ↗
24. Recent advances in zero-shot recognition: Toward data-efficient understanding of visual content10.1109/MSP.2017.2763441 ↗
25. Ramos, J. (2003, January 3–8). Using tf-idf to determine word relevance in document queries. Proceedings of the First Instructional Conference on Machine Learning, Piscataway, NJ, USA.
26. An information-theoretic perspective of tf–idf measures10.1016/S0306-4573(02)00021-3 ↗
27. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 24–27). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
28. Girshick, R. (2015, January 7–12). Fast R-CNN. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/ICCV.2015.169 ↗
29. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
30. Zhao, K., Wang, Y., Zhu, Q., and Zuo, Y. (2022). Intelligent Detection of Parcels Based on Improved Faster R-CNN. Appl. Sci., 12.10.3390/app12147158 ↗
31. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
32. Zolfagharian, S., Nourbakhsh, M., Irizarry, J., and Ressang, A. (2012, January 21–23). Environmental impacts assessment on construction sites. Proceedings of the Construction Research Congress 2012, with the Theme Construction Challenges in a Flat World, West Lafayette, IN, USA.10.1061/9780784412329.176 ↗
33. Oke, A., Aghimien, D., Aigbavboa, C., and Madonsela, Z. (2019, January 19). Environmental sustainability: Impact of construction activities. Proceedings of the 11th International Conference on Construction in the 21st Century, London, UK.
34. Current issues in high-resolution earth observation technology10.1007/s11430-012-4445-9 ↗
35. Shi, F., and Zhang, T. (2021). A Multi-Task Network with Distance-Mask-Boundary Consistency Constraints for Building Extraction from Aerial Images. Remote Sens., 13.10.3390/rs13142656 ↗
36. Coal mine area monitoring method by machine learning and multispectral remote sensing images10.1016/j.infrared.2019.103070 ↗