Back to Search Start Over

Att-Mask R-CNN: an individual tree crown instance segmentation method based on fused attention mechanism.

Authors :
Chen, Wenjing
Guan, Zhihao
Gao, Demin
Source :
Canadian Journal of Forest Research; 2024, Vol. 54 Issue 7, p825-838, 14p
Publication Year :
2024

Abstract

Tree detection and canopy area measurement are important and difficult tasks in forest inventory, which are important for understanding forest stand structure. This study utilized remotely piloted aircraft (RPA) aerial photography technology to collect remote sensing images of forests in Xiong County, China, creating a dataset comprising 1200 images of six tree species. Based on this dataset, the paper proposes an optimized model, Att-Mask R-CNN, for canopy detection and segmentation. Att-Mask R-CNN outperforms the original models (Mask R-CNN and MS R-CNN) by achieving 65.29% mean average precision for detection, 80.44% mean intersection over union for segmentation, and 90.67% overall recognition rate for the six tree species. In addition, a pixel statistics method based on segmentation masks is introduced for estimating the vertical projected area of individual tree crowns, and comparisons between the measured and predicted vertical projected area of the crowns of six tree species (100 trees of each class) show an overall goodness-of-fit R2 of 85% and a relative root-mean-square error rRMSE of 12.81%. By using remote sensing images from RPAs and optimizing existing deep learning models, the detection and segmentation of individual tree canopies can be achieved, resulting in a more accurate understanding of forest structure, which provides scientific support for forest management and resource monitoring. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
00455067
Volume :
54
Issue :
7
Database :
Complementary Index
Journal :
Canadian Journal of Forest Research
Publication Type :
Academic Journal
Accession number :
178184970
Full Text :
https://doi.org/10.1139/cjfr-2023-0187