Developing thermal infrared de-ghost and multi-level nested conglutinated segmentation algorithm for detection of rice seed setting rate

Abstract

The seed setting rate (SSR) of rice is not only a key component of yield, but also an important parameter in rice phenotypic analysis. Fast and accurate detection of SSR is of great significance for yield prediction. The purpose of this research was to detect the SSR of rice quickly and automatically. A thermal infrared–visible light dual imaging system was built to obtain thermal infrared images and RGB images of rice grains. This paper proposed image registration method, thermal infrared de-ghost method and multi-layer nested conglutinated segmentation algorithm to detect SSR. Compared with the detection accuracy of three deep learning models (Faster RCNN 96.43%, SSD 81.84%, YOLO V3 96.75%) and image registration methods (80.83%), the highest SSR detection accuracy (97.66%) was achieved by fusing thermal infrared de-ghost and multi-layer nested conglutinated segmentation algorithm. This method has the advantages of simple structure, high efficiency and competitive results, and has great potential in detecting seed setting rate.