Instance Segmentation of Water Body from Aerial Image using Mask Region-based Convolutional Neural Network

What is it about?

Land use is constantly changing, and water plays a critical role in the process. If changes are noticed quickly or are predictable, land use planning and policies can be devised to mitigate almost any problem. Accordingly, researchers present a mask region-based convolutional neural network (Mask R-CNN) for water body segmentation from aerial images. The system's Aerial image water resources dataset (AIWR) was tested. The AIWR areas were agricultural and lowland areas that require rainwater for farming. Many wells were spotted throughout the agricultural areas. The AIWR dataset presents two types of data: natural water bodies and artificial water bodies. The two different areas appear as aerial area images that are different in color, shape, size, and similarity. A pre-trained model of Mask R-CNN was used to reduce network learning time. ResNet-101 was used as backbone architecture. The information gathered in the learning process is limited, and only 720 pictures were produced, Researchers used data augmentation to increase the amount of information for training by using affine image transformation, including scale, translation, rotation, and shear. The experiment found that mask R-CNN architecture can specify the position of the water surface. Measuring method in this case is mAP value. The mAP value is at 0.30 without data augmentation. However, if using the R-CNN mask with data augmentation, the mAP value increased to 0.59.

Featured Image

Photo by NASA on Unsplash

Photo by NASA on Unsplash

Why is it important?

This article presents mask region-based convolutional neural network (Mask R-CNN) for water body segmentation from aerial images. This method has been called instance segmentation. ResNet-101 was used as backbone architecture. Mask R-CNN architecture was tested with aerial image water resources dataset (AIWR). The AIWR is the images of agricultural areas in the northeast region of Thailand; these are fertile agricultural areas where people grow rice. The areas require rainwater for farming and many wells can be spotted throughout the agricultural area. Water body data were collected from 2 types, natural water bodies (W1) and artificial water bodies (W2). The aerial images of water bodies were different in color, shape, size, and similarity. This dataset includes 800 images, so AIWR dataset challenges the instance segmentation process.