A New Method for Forest Canopy Hemispherical Photography Segmentation Based on Deep Learning

Abstract

Research Highlights: This paper proposes a new method for hemispherical forest canopy image segmentation. The method is based on a deep learning methodology and provides a robust and fully automatic technique for the segmentation of forest canopy hemispherical photography (CHP) and gap fraction (GF) calculation. Background and Objectives: CHP is widely used to estimate structural forest variables. The GF is the most important parameter for calculating the leaf area index (LAI), and its calculation requires the binary segmentation result of the CHP. Materials and Methods: Our method consists of three modules, namely, northing correction, valid region extraction, and hemispherical image segmentation. In these steps, a core procedure is hemispherical canopy image segmentation based on the U-Net convolutional neural network. Our method is compared with traditional threshold methods (e.g., the Otsu and Ridler methods), a fuzzy clustering method (FCM), commercial professional software (WinSCANOPY), and the Habitat-Net network method. Results: The experimental results show that the method presented here achieves a Dice similarity coefficient (DSC) of 89.20% and an accuracy of 98.73%. Conclusions: The method presented here outperforms the Habitat-Net and WinSCANOPY methods, along with the FCM, and it is significantly better than the Otsu and Ridler threshold methods. The method takes the original canopy hemisphere image first and then automatically executes the three modules in sequence, and finally outputs the binary segmentation map. The method presented here is a pipelined, end-to-end method.

Keywords

• canopy hemisphere photography
• image segmentation
• gap fraction
• deep learning
• U-Net