Detection of Miss-Seeding of Sweet Corn in a Plug Tray Using a Residual Attention Network

Abstract

With the promotion of artificial intelligence in agriculture and the popularization of plug tray seedling-raising technology, seedling raising and transplanting have become the most popular planting modes. Miss-seeding is one of the most serious problems affecting seedling raising and transplanting. It not only affects the germination rate of seeds but also reduces the utilization rate of the plug tray. The experimental analysis of traditional machine vision-based miss-seeding showed that because of uneven lighting, the plug tray was wrongly identified as a seed under bright light, but the seeds in the dark were not easy to identify. When using the seeding area to identify seeds and noise, sweet corn seeds in a small area can be easily screened out. This paper proposes a method using the ResNet network with an attention mechanism to solve the above-mentioned problems. In this paper, the captured image was segmented into the images of a single plug tray, and a residual attention network was built; the detection scheme of miss-seeding was also converted into a dichotomous picture recognition task. This paper demonstrates that the residual attention network can effectively recognize and detect the seed images of sweet corn with very high accuracy. The results of the experiment showed that the average accuracy of this recognition model was 98%. The feature visualization method was used to analyze the features, further proving the effectiveness of the classification method of plug tray seedlings.

Development of Seeding Rate Monitoring System Applicable to a Mechanical Pot-Seeding Machine

“…The seeding rate monitoring system consisted of a camera station, on-board computer, monitor, alarm bell, conveyor, and motor controller and is based on the structure of a commercial mechanical pot-seeding machine. Diverse image processing techniques such as changing brightness In previous related studies, the SRRs of monitoring systems developed for rice, corn, green onion, tomato and chickpea were 94.67%, 97.50%, 99%, 93%, and 94%, respectively [13][14][15][16][17][18]. Furthermore, in related studies [19], when detecting overlapping corn and mung bean seeds, accuracies of 91% and 83% were shown.…”

“…Gao et al [15] developed a green onion seed monitoring system with 99% detection accuracy by using a detection algorithm and applying RGB, HSV, and hue-saturation-lightness color space conversions. Gao et al [16] developed a deep learning-based corn seed detection system with a residual attention network for minimizing the misrecognition of seeds; the average detection accuracy was 98%. Yan et al [17] developed a deep-learning model applying "You Only Look Once" Version 5x to identify missing tomato seeds and demonstrated an average detection accuracy of 93%.…”