UAV Remote Sensing for Campus Monitoring: A Comparative Evaluation of Nearest Neighbor and Rule-Based Classification
- PDF / 3,192,848 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 89 Downloads / 175 Views
RESEARCH ARTICLE
UAV Remote Sensing for Campus Monitoring: A Comparative Evaluation of Nearest Neighbor and Rule-Based Classification Anuj Tiwari1
•
Surendra Kumar Sharma1,2 • Abhilasha Dixit3 • Vishal Mishra1
Received: 4 November 2020 / Accepted: 10 November 2020 Indian Society of Remote Sensing 2020
Abstract UAV technology when aided with the unique data acquisition strategies, preprocessing techniques and analytical abilities of an established domain of remote sensing provide more affordable, customized and user-friendly option of ‘‘UAVRemote Sensing’’. This extended branch of remote sensing flourishes in both the mapping and measurement, if implemented in the ordered fashion to ensure remote sensing grade data. The current study integrates the potential of UAV technology to the high-resolution data classification approach of object-based image analysis. Department of Civil Engineering, Indian Institute of Technology-Roorkee, India, is selected as study area. In the first part of the study, a detailed UAV survey followed by UAV data processing was carried out to capture the VHR orthorectified image of the selected study area. In the second step, a comparative assessment of nearest neighbor (NN) and rule-based classifications were performed. Orthorectified image was segmented using a multi-resolution segmentation. The overall accuracy for NN and rule-based classifier were 95.13% and 93.87%, respectively. Detailed assessment of user accuracy and producer accuracy described that tree, road, solar panel and waterbody were more accurately classified with NN classifier, whereas building, grass land, open land and vehicle were more accurately classified with rule-based classifier. Keywords Very high-resolution image (VHRI) Object-based image analysis (OBIA) Nearest neighbor (NN) Rule-based classifier Multi-resolution segmentation
Introduction
& Anuj Tiwari [email protected] Surendra Kumar Sharma [email protected] Abhilasha Dixit [email protected] Vishal Mishra [email protected] 1
Department of Civil Engineering, Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India
2
Urban and Regional Studies Department, Indian Institute of Remote Sensing Dehradun, Dehradun, Uttarakhand, India
3
Centre of Excellence in Disaster Mitigation and Management, Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India
Unmanned aerial vehicles (UAVs) have received swift and extensive acceptance for defense applications (Mancini et al. 2013). As these defense arrangements grew in maturity, a number of UAV systems with different inbuilt sensor systems have been industrialized for non-military purposes (Mancini et al. 2013; Yao et al. 2019). Latest advances in the UAV technology transform these aerial vehicles into an ideal remote sensing platform for earth observations. Compared with manned aerial vehicles, remote sensing systems with the platform of UAV can operate all-day and all-weather and perform flight tasks in high-risk zones (Ada˜o et al. 2017; Noor et al. 2018; Yao et al. 2
Data Loading...
