Rice Ear Counting Based on Image Segmentation and Establishment of a Dataset.

Hongmin Shao,Ying Xiang,Rong Tang,Jiong Mu,Yan Guan,Yujie Lei

doi:10.3390/plants10081625

Abstract

The real-time detection and counting of rice ears in fields is one of the most important methods for estimating rice yield. The traditional manual counting method has many disadvantages: it is time-consuming, inefficient and subjective. Therefore, the use of computer vision technology can improve the accuracy and efficiency of rice ear counting in the field. The contributions of this article are as follows. (1) This paper establishes a dataset containing 3300 rice ear samples, which represent various complex situations, including variable light and complex backgrounds, overlapping rice and overlapping leaves. The collected images were manually labeled, and a data enhancement method was used to increase the sample size. (2) This paper proposes a method that combines the LC-FCN (localization-based counting fully convolutional neural network) model based on transfer learning with the watershed algorithm for the recognition of dense rice images. The results show that the model is superior to traditional machine learning methods and the single-shot multibox detector (SSD) algorithm for target detection. Moreover, it is currently considered an advanced and innovative rice ear counting model. The mean absolute error (MAE) of the model on the 300-size test set is 2.99. The model can be used to calculate the number of rice ears in the field. In addition, it can provide reliable basic data for rice yield estimation and a rice dataset for research.

Highlights

(2) This paper proposes a method that combines the LC-FCN model based on transfer learning with the watershed algorithm for the recognition of dense rice images
The results show that the model is superior to traditional machine learning methods and the single-shot multibox detector (SSD) algorithm for target detection
Precision agriculture is an important trend in future agricultural development, among which agricultural informatization is a development direction vigorously advocated at present

Summary

Introduction

Precision agriculture is an important trend in future agricultural development, among which agricultural informatization is a development direction vigorously advocated at present. The information acquisition technology of micro-UAV has the characteristics of easy platform construction, low operation and maintenance cost, small size, light weight, simple operation, high flexibility and short operation cycle It can make up for the shortcomings of the existing aerospace, aviation remote sensing and ground remote sensing systems and improve the ground crop monitoring system [12]. In order to solve the above problems, this research applies a new concept of deep learning, namely a point-supervised convolutional neural network, to rice ear statistics. Combining the idea of point supervision with image segmentation, the rice ear counting model of the convolutional neural network is obtained after training. It is tested on a 300-size test set.

Experiment Field and Data Acquisition

Image Preprocessing

Implementation and Evaluation Index

Method