Potato Detection and Segmentation Based on Mask R-CNN
- PDF / 2,426,908 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 42 Downloads / 223 Views
Online ISSN 2234-1862 Print ISSN 1738-1266
ORIGINAL ARTICLE
Potato Detection and Segmentation Based on Mask R-CNN Hyeon-Seung Lee 1 & Beom-Soo Shin 1 Received: 12 July 2020 / Revised: 7 September 2020 / Accepted: 10 September 2020 # The Korean Society for Agricultural Machinery 2020
Abstract Purpose Potatoes are similar in color and size to soil and its clods. They are mostly irregular in the shape as well. Therefore, it is not easy to distinguish potatoes from the soil surface background only with machine vision. This study applied Mask R-CNN, one of the object recognition technologies using deep learning to detect potatoes. The size of object in pixel was obtained on individual potato, and they will be used to predict the yield of potatoes. Methods In order to collect the images needed for deep learning, potato images at the time of harvesting were obtained from potato farms. Annotation was entered for each irregular potato shape, where approximately 4500 potatoes were used. Resnet-101 was selected as the backbone of Mask R-CNN with a feature pyramid network. Transfer training was applied to shorten training time and limit the number of images needed to train the model. The classification performance evaluation was conducted to verify the trained model. The size of potato in pixel was obtained from the output image through the potato detection model by the segmentation algorithm using MATLAB. Results The total number of training for the potato detection model was 12,000, and the training loss of Mask R-CNN was less than 0.1%. The potato detection results from 69 randomly selected test images showed that the average detection precision was 90.8%, recall 93.0%, and F1 score 91.9%. Conclusions Potato detection model with Mask R-CNN can detect irregularly shaped potatoes on similar color soil surface. The size of the detected potato region can be extracted as well. Keywords Deep learning . Mask R-CNN . Potato detection . Potato segmentation
Introduction Agricultural monitoring is indispensable in implementing precision agriculture. First of all, crop growing condition and yield should be measured. In addition to the weight-based monitoring system already commercialized in grain harvester, R&D’s for yield monitoring system in other crops such as potato, sugarcane, fruits, and vegetable are under way. Various nondestructive sensors such as near-infrared spectroscopy (Lee and Ehsani 2015), machine vision (Annamalai et al. 2004; Lee et al. 2018), optical sensor (Price et al. 2011), and loadcell (Maja and Ehsani 2010) have been used for monitoring yield as well as crop condition. Among them, machine
* Beom-Soo Shin [email protected] 1
Department of Biosystems Engineering, Kangwon National University, 1 Kangwondaehak-gil, Chuncheon, Gangwon-do 24341, South Korea
vision is preferred as a monitoring tool because it is costeffective and easy to be installed. Tabb et al. (2006) developed the GMOG (Global Mixture of Gaussians) algorithm based on MOG (Mixture of Gaussians) to detect apples for the apple yield prediction
Data Loading...
