Abstract
Using high-resolution remote sensing images to automatically identify individual trees is of great significance to forestry ecological environment monitoring. Urban plantation has realistic demands for single tree management such as catkin pollution, maintenance of famous trees, landscape construction, and park management. At present, there are problems of missed detection and error detection in dense plantations and complex background plantations. This paper proposes a single tree detection method based on single shot multibox detector (SSD). Optimal SSD is obtained by adjusting feature layers, optimizing the aspect ratio of a preset box, reducing parameters and so on. The optimal SSD is applied to single tree detection and location in campuses, orchards, and economic plantations. The average accuracy based on SSD is 96.0, 92.9, and 97.6% in campus green trees, lychee plantations, and palm plantations, respectively. It is 11.3 and 37.5% higher than the latest template matching method and chan-vese (CV) model method, and is 43.1 and 54.2% higher than the traditional watershed method and local maximum method. Experimental results show that SSD has a strong potential and application advantage. This research has reference significance for the application of an object detection framework based on deep learning in agriculture and forestry.
Highlights
Single tree detection based on remote sensing images is a crucial technology for establishing a single tree database and monitoring single tree plantation resources, which is of great significance to urban landscape planning and ecological environment monitoring (Congalton et al, 2014; Faridatul and Wu, 2018; Ahl et al, 2019)
For a variety of single tree detection methods, the evaluation of their detection excellence depends on evaluation standard
The point coordinate of single tree detection and a single reference tree are denoted as Mi and Ej
Summary
Single tree detection based on remote sensing images is a crucial technology for establishing a single tree database and monitoring single tree plantation resources, which is of great significance to urban landscape planning and ecological environment monitoring (Congalton et al, 2014; Faridatul and Wu, 2018; Ahl et al, 2019). Single tree detection is a cross-research field of computer vision, measurement, single tree management, and remote sensing (Kupidura et al, 2019; Zhang et al, 2020; Belcore et al, 2021). Researchers began to explore single tree detection methods a long time ago. As early as 1995, Gougeon et al (Gougeon, 1995) used aerial photos to carry out single tree identification; they searched for the local minimum value at the bottom of a tree for the first time. Larsen et al (Larsen and Rudemo, 1998) used an improved template matching method to detect crown vertices of a single tree. Poullot et al (Pollock, 1996) used remote sensing imagery to determine the location of a single tree by selecting a moving window from 15 × 15 to 30 × 30
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
