基于细部地物组合检测的建设项目场景识别

doi:10.16843/j.sswc.2022081

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (7506 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract [Background] Construction projects belong to complex semantic scenes, and their automatic recognition is a technical challenge for dynamic monitoring of soil erosion and supervision of soil and water conservation. The construction projects in high-resolution remote sensing images lack a unified semantic concept definition, and their scenes contain a variety of artificial and natural features, with highly unstructured and significantly different image features inside the scenes. Therefore, it is necessary to study the target detection method for Construction projects. [Methods] We proposed a target detection method and theoretical system for complex semantic scenes of construction projects. GF-1 remote sensing image of 2 m resolution was used for annotation. Firstly, based on the construction projects data and its detailed ground object dataset for target detection, we selected high-information detailed ground objects for target detection according to the information content. Then, the Faster RCNN algorithm was used to detect construction projects and high-information detail ground objects separately, and the prediction result frame merging with detail ground objects combination correction was used to jointly increase the confidence of construction projects identification and optimize the detection results. [Results] Wuhan construction projects dataset is built, including construction project, bare land(rock), cover, construction road, prefabricated house, construction structure and built building, which amount is 752, 763, 154, 82, 372, 292, and 278, information content is 18.81, 20.96, 9.93, 44.82, 28.77, and 8.22, respectively. Comparing this method with three other methods under the same experimental conditions, including Faster RCNN, Yolo, and variation of this method. The experimental results show that the accuracy evaluation indexes of the method on the produced Wuhan construction projects dataset are better than other comparison methods, and its AP(average precision) value and F₁ score reach 0.773 and 0.417, respectively. The AP values of the three other methods were 0.755,0.693 and 0.754, and the F₁ scores were 0.415,0.361, and 0.405, respectively. Compared with the other three methods, all of them have a certain degree of improvement. This method can effectively reduce the rate of wrong detection and improve the coincidence of correct detection results. [Conclusions] Better recognition results for construction projects in complex semantic scenes can be gained by this method. By the application of this method we can accurately and effectively identify the construction project, and by comparing it with the water and soil conservation program that has been reported, it can determine whether the construction project is built before approval and disturbed beyond the approved boundary, so as to achieve full coverage supervision of the construction project.

Key words： construction projects remote sensing image detailed ground object detection complex semantics context soil and water conservation

Received: 06 May 2022

PACS:	TP751
	S157

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	PU Jian
	LIU Renyu
	WANG Zhigang
	ZHANG Tong
	LI Jianming
	SHEN Shengyu
	XU Wensheng
	LIU Jigen

Cite this article:

PU Jian,LIU Renyu,WANG Zhigang, et al. Scene recognition for construction projects based on the combination detection of detailed ground objects[J]. SSWC, 2024, 22(6): 155-162.

URL:

http://journal12.magtechjournal.com/Jweb_stbc/EN/10.16843/j.sswc.2022081 OR http://journal12.magtechjournal.com/Jweb_stbc/EN/Y2024/V22/I6/155

[1]	姜德文. 高分遥感和无人机技术在水土保持监管中的应用[J]. 中国水利, 2016(16): 45. JIANG Dewen.Application of high resolution remote sensing and UAV in soil conservation monitoring and supervision[J]. China Water Resources, 2016(16): 45.
[2]	鄂竟平. 工程补短板行业强监管奋力开创新时代水利事业新局面:在2019年全国水利工作会议上的讲话(摘要)[J]. 中国水利, 2019(2): 1. E Jinping. 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)[J]. China Water Resources, 2019(2): 11.
[3]	王志刚, 韩培, 周耀华, 等. 超大城市水土流失空间分布格局及其防治策略:以武汉市为例[J]. 水土保持通报, 2018, 38(5): 122. WANG Zhigang, HAN Pei, ZHOU Yaohua, et al. Spatial distribution pattern of soil and water loss and its conservation strategies in megacity: A case study in Wuhan city[J]. Bulletin of Soil and Water Conservation, 2018, 38(5): 122.
[4]	蒲朝勇. 推动水土保持监测与信息化工作的思路与要求[J]. 中国水土保持, 2017(5): 1. PU Chaoyong. Ideas and requirements for promoting soil and water conservation monitoring and information technology[J]. Soil and Water Conservation in China, 2017(5): 1.
[5]	鄂竟平. 鄂竟平部长对2020年全国水土保持工作提出明确要求[J]. 中国水土保持, 2020(2): 2. E Jinping. Minister E Jingping put forward clear requirements for national soil and water conservation work in 2020[J]. Soil and Water Conservation in China, 2020(2): 2.
[6]	BLASCHKE T, STROBL J. What's wrong with pixels? Some recent developments interfacing remote sensing and GIS[C]//Proceedings of GIS-Zeitschrift fur Geoinformationsysteme, 2001, 6(1): 12.
[7]	BRUZZONE L, CARLIN L. A multilevel context-based system for classification of very high spatial resolution images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(9): 2587
[8]	张帆. 面向高分辨率遥感影像分析的深度学习方法研究[D]. 武汉:武汉大学, 2017: 2. ZHANG Fan. Deep learning for very high resolution remote sensing data analysis[D]. Wuhan:Wuhan University, 2017: 2.
[9]	LI Ke, WAN Gang, CHENG Gong, et al. Object detection in optical remote sensing images: A survey and a new benchmark[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159: 296.
[10]	陈亮, 王志茹, 韩仲, 等. 基于可见光遥感图像的船只目标检测识别方法[J]. 科技导报, 2017, 35(20): 77. CHEN Liang, WANG Zhiru, HAN Zhong, et al. A review of ship detection and recognition based on optical remote sensing image[J]. Science and Technology Review, 2017, 35(20): 77.
[11]	祝文韬, 谢宝蓉, 王琰, 等. 光学遥感图像中的飞机目标检测技术研究综述[J]. 计算机科学, 2020, 47(S2): 165. ZHU Wentao, XIE Baorong, WANG Yan, et al. Survey on aircraft detection in optical remote sensing images[J]. Computer Science, 2020, 47(S2): 165.
[12]	龚健雅, 张觅, 胡翔云, 等. 智能遥感深度学习框架与模型设计[J]. 测绘学报, 2022, 51(4): 475. GONG Jianya, ZHANG Mi, HU Xiangyun, et al. The design of deep learning framework and model for intelligent remote sensing[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(4): 475.
[13]	姜德文, 蒋学玮, 周正立. 人工智能对水土保持信息化监管技术支撑[J]. 水土保持学报, 2021, 35(4): 6. JIANG Dewen, JIANG Xuewei, ZHOU Zhengli. Technical support of artifical intelligence for informatization supervision of soil and water conservation[J]. Journal of Soil and Water Conservation, 2021, 35(4): 6.
[14]	亢庆, 姜德文, 扶卿华, 等. 基于最优尺度的生产建设扰动图斑识别[J]. 中国水土保持科学, 2017, 15(6): 126. KANG Qing, JIANG Dewen, FU Qinghua. On the identification of construction disturbance patches based on optimal segmentation scale[J]. Science of Soil and Water Conservation, 2017, 15(6): 126.
[15]	XU Zhongwen, YANG Yi, HAUPTMANN Alexander. A discriminative CNN video representation for event detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, MA, USA: IEEE, 2014: 1798.
[16]	FAN Hehe, CHANG Xiaojun, CHENG De, et al. Complex event detection by identifying reliable shots from untrimmed videos[C]//Proceedings of the IEEE International Conference on Computer Vision (CVPR). Venice, Italy: IEEE, 2017: 736.
[17]	CHANG Xiaojun, YANG Yi, LONG Guodong, et al. Dynamic concept composition for zero-example event detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Phoenix, Arizona, USA: AAAI, 2016: 3464.
[18]	YUAN Jin, ZHA Zhengjun, ZHENG Yaotao, et al. Learning concept bundles for video search with complex queries[C]//Proceedings of the 19th ACM International Conference on Multimedia. Scottsdale, AZ, USA:ACM, 2011: 453.
[19]	FENG Linan, BHANU B. Semantic concept co-occurrence patterns for image annotation and retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(4): 1.
[20]	GIRSHICK R. Fast r-cnn[C]//Proceedings of the IEEE International Conference on Computer Vision(CVPR). Boston, MA, USA: IEEE, 2015: 1440.
[21]	REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137.