Soil Image Segmentation Based on Mask R-CNN

TL;DR

This paper applies Mask R-CNN, a deep learning model, to soil image segmentation, achieving accurate, real-time results that improve soil recognition by effectively isolating soil areas from complex backgrounds.

Contribution

First application of deep learning, specifically Mask R-CNN, to soil image segmentation, demonstrating high accuracy and real-time performance in natural field environments.

Findings

Segmentation loss value of 0.1999 on training set

Validation mAP of 0.8804 at IoU=0.5

Segmentation completed in 0.06 seconds on GPU

Abstract

The complex background in the soil image collected in the field natural environment will affect the subsequent soil image recognition based on machine vision. Segmenting the soil center area from the soil image can eliminate the influence of the complex background, which is an important preprocessing work for subsequent soil image recognition. For the first time, the deep learning method was applied to soil image segmentation, and the Mask R-CNN model was selected to complete the positioning and segmentation of soil images. Construct a soil image dataset based on the collected soil images, use the EISeg annotation tool to mark the soil area as soil, and save the annotation information; train the Mask R-CNN soil image instance segmentation model. The trained model can obtain accurate segmentation results for soil images, and can show good performance on soil images collected in different environments; the trained instance segmentation model has a loss value of 0.1999 in the training set, and the mAP of the validation set segmentation (IoU=0.5) is 0.8804, and it takes only 0.06s to complete image segmentation based on GPU acceleration, which can meet the real-time segmentation and detection of soil images in the field under natural conditions. You can get our code in the Conclusions. The homepage is https://github.com/YidaMyth.