Field collaborative recognition method and experiment for thermal infrared imaging of damaged potatoes

Abstract

If damaged potatoes are detected promptly during harvest, the spread of potato decay in potato storage warehouses is reduced and timely loss control is achieved. Therefore, damaged potatoes must be identified and removed during harvest. A field collaborative recognition method for thermal infrared imaging of damaged potatoes is proposed in this work. An experimental device was developed to detect and identify three commonly damaged potatoes using this method. First, a heat transfer model for damaged potatoes based on the field synergy theory was established and heat transfer analysis was conducted. The reason for the temperature difference between the damaged and intact parts of potatoes was the difference in convective heat transfer intensity between the two and the hot air, as well as the thermal properties of the potato skin and flesh. Then, the surface temperature distribution of the damaged potato under various hot air inlet angles was obtained using finite element simulation tests. According to the imaging effect of the thermal image, the optimal inlet angle was determined to be 90° vertically. Finally, the operating parameters of the potato-screening device were optimized and analyzed. The optimal parameter combination obtained is as follows: The conveyor belt speed was 0.37 m/s, the hot air speed was 3.5 m/s, and the hot air temperature was 45 °C. Actual experiments were conducted on this device. The experimental results indicated that the accuracy, precision, recall, and F-score evaluation values of detecting damaged potatoes were 96%, 94.6%, 97.6%, and 0.961 respectively. The potato thermal infrared damage detection method can meet the technical requirements of grading detection during potato harvest.

Plant phenotyping relevance

熱赤外画像を用いてジャガイモの損傷状態を検出する装置・手法を開発し、実験で性能評価しており、植物状態の取得が中心的です。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.