Tree, Shrub, and Grass Classification Using Only RGB Images

Abstract

In this work, a semantic segmentation-based deep learning method, DeepLabV3+, is applied to classify three vegetation land covers, which are tree, shrub, and grass using only three band color (RGB) images. DeepLabV3+'s detection performance has been studied on low and high resolution datasets that both contain tree, shrub, and grass and some other land cover types. The two datasets are heavily imbalanced where shrub pixels are much fewer than tree and grass pixels. A simple weighting strategy known as median frequency weighting was incorporated into DeepLabV3+ to mitigate the data imbalance issue, which originally used uniform weights. The tree, shrub, grass classification performances are compared when all land cover types are included in the classification and also when classification is limited to the three vegetation classes with both uniform and median frequency weights. Among the three vegetation types, shrub is found to be the most challenging one to classify correctly whereas correct classification accuracy was highest for tree. It is observed that even though the median frequency weighting did not improve the overall accuracy, it resulted in better classification accuracy for the underrepresented classes such as shrub in our case and it also significantly increased the average class accuracy. The classification performance and computation time comparison of DeepLabV3+ with two other pixel-based classification methods on sampled pixels of the three vegetation classes showed that DeepLabV3+ achieves significantly higher accuracy than these methods with a trade-off for longer model training time.

Vegetation Detection Using Deep Learning and Conventional Methods

“…With heavily imbalanced datasets, the error from the overrepresented classes contributes much more to the loss value than the error contribution from the underrepresented classes. This makes the deep learning method's loss function to be biased toward the overrepresented classes resulting in poor classification performance for the underrepresented classes [50]. One should also pay attention when applying deep learning methods to new applications because one requirement for deep learning is the availability of a vast amount of training data.…”

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+ Method

“…Among this series, DeepLabv3+ combines the advantages of encoderdecoder architecture and atrous spatial pyramid pooling (ASPP), which can capture rich contextual information from plant root images at various resolutions and segment clear root loci. Ayhan and Kwan (2020) proposed a DeepLabv3+ network improvement based on a weighting strategy, which is used to segment three vegetation cover types: trees, shrubs, and grasses. They showed that DeepLabv3+ is superior to the most advanced machine learning algorithms, i.e., SVM and random forests, in spatial information extraction and pixel segmentation.…”

Improving Land Cover Classification Using Extended Multi-Attribute Profiles (EMAP) Enhanced Color, Near Infrared, and LiDAR Data

“…In principle, those deep learning methods for object detection using color images can be adapted to land cover classification. Recently, our team initiated an investigation along that direction in [31]. However, those deep learning methods require a lot of training data and may not yield better results when data are scarce, which is the case for the IEEE Houston dataset presented in this paper.…”