Deep Semantic Segmentation of Trees Using Multispectral Images

Abstract

Forests can be efficiently monitored by automatic semantic segmentation of trees using satellite and/or aerial images. Still, several challenges can make the problem difficult, including the varying spectral signature of different trees, lack of sufficient labelled data, and geometrical occlusions. In this paper, we address the tree segmentation problem using multispectral imagery. While we carry out large-scale experiments on several deep learning architectures using various spectral input combinations, we also attempt to explore whether hand-crafted spectral vegetation indices can improve the performance of deep learning models in the segmentation of trees. Our experiments include benchmarking a variety of multispectral remote sensing image sets, deep semantic segmentation architectures, and various spectral bands as inputs, including a number of hand-crafted spectral vegetation indices. From our large-scale experiments, we draw several useful conclusions. One particularly important conclusion is that, with no additional computation burden, combining different categories of multispectral vegetation indices, such as NVDI, ARVI, and SAVI, within a single three-channel input, and using the state-of-the-art semantic segmentation architectures, tree segmentation accuracy can be improved under certain conditions, compared to using high-resolution visible and/or nearinfrared input.

MangroveSeg: Deep-Supervision-Guided Feature Aggregation Network for Mangrove Detection and Segmentation in Satellite Images

“…A MangroveSeg network based on FAPNet [31] to obtain a mangrove segmentation model using 3002 training images achieved 89.58% overall accuracy, 89.02% precision, and 80.7% mIoU for the testing data. Although the trained mangrove segmentation model can automatically and accurately detect the distribution and area of mangroves from satellite remote sensing images, there are still some limitations in application.…”

“…Lomeo and Singh [30] designed a mangrove monitoring model for Southeast Asia, in which three types of networks are used to extract mangrove distributions. Ulku et al [31] tested various multispectral remote sensing image and spectral bands using deep semantic segmentation architectures, and it was concluded that combining different categories of multispectral vegetation inDices into a single three-channel input and using state-of-the-art semantic segmentation architectures can improve tree segmentation accuracy under certain conditions. These studies demonstrate the advantages of deep learning frameworks in satellite image processing and analysis.…”

Seeing the Forest for the Trees: Mapping Cover and Counting Trees from Aerial Images of a Mangrove Forest Using Artificial Intelligence

“…Paired with machine learning automation, studies of long time-series of images can be carried out. Recent improvements in satellite image resolutions (i.e., 0.031 m for the World-View 3 satellite) have allowed for more resolved classification of trees using semantic segmentation neural networks [23,24], detection of individual trees using instance segmentation networks [25][26][27][28] and detection of mangrove forest clearings [29] on highresolution RGB images. Nonetheless, the calculation of certain variables, such as the height of trees extracted from canopy height models (CHMs) is error-prone at the current resolution of satellite imagery and should be paired with low-flying platforms, such as planes or UASs [28] for better validation and performance.…”

LPASS-Net: Lightweight Progressive Attention Semantic Segmentation Network for Automatic Segmentation of Remote Sensing Images

“…How to interpret large-size and high-resolution remote sensing images automatically, quickly, and efficiently has become a hot issue for research. Among them, the semantic segmentation of remote sensing images plays a vital role in urban planning [1][2][3][4][5], environmental monitoring [6][7][8][9][10], forest and crop analysis [11][12][13][14][15], and smart city construction [16][17][18][19][20].…”