Pot seedling disease monitoring-seedling removing system and method for semi-automatic transplanter

Abstract

The invention provides a pot seedling disease monitoring and seedling removing system and method of a semi-automatic transplanter, and belongs to the field of agricultural robots. The pot seedling disease monitoring and seedling removing system comprises a pot seedling panoramic information head-up obtaining device and a light and simple retractable bad seedling removing device, and the pot seedling panoramic information head-up obtaining device is used for dynamically and reliably capturing panoramic information of falling pot seedlings; through layer-by-layer deep learning training of multi-part multi-disease complex characteristics, self-input and layer-by-layer comparison of pot seedling RGB images to a multi-layer classification linear image solidification template, accurate and rapiddiagnosis of diseased seedlings in the free falling process of pot seedlings is achieved, and therefore the intelligent operation level of the field semi-automatic transplanter is effectively improved.

Description

technical field [0001] The invention relates to the field of agricultural robots, in particular to a seedling disease monitoring-picking system and method for a semi-automatic transplanter. Background technique [0002] In recent years, the planting machinery used in our country is mainly semi-automatic. In the transplanting operation of potted seedlings in the field, the growth of diseased seedlings after transplanting is poor and the bacteria are transmitted and infected with each other, which affects the output and causes waste. Most of the existing field seedling detection technologies for semi-automatic transplanters in the field are based on installing photoelectric, electromagnetic and other on-off sensor feedback devices in the seedling cups, and the on-off signals trigger feedback on the presence or absence of pot seedlings in the seedling cups and counting functions , but its detection index is single, and it is impossible to diagnose diseased seedlings; the curren...

AI Technical Summary

Problems solved by technology

[0002] In recent years, the planting machinery used in my country is mainly semi-automatic. In the transplanting operation of pot seedlings in the field, the growth of diseased seedlings after transplanting is poor and the bacteria are transmitted and infected with each other, which affects the yield and causes waste.

Most of the existing field seedling detection technologies for semi-automatic transplanters in the field are based on installing photoelectric, electromagnetic and other on-off sensor feedback devices in the seedling cups, and the on-off signals trigger feedback on the presence or absence of pot seedlings in the seedling cups and counting functions , but its detection index is single, and it is impossible to diagnose diseased seedlings; the current proposal is to install a high-speed camera directly above the seedling cup at the seedling fall point to look down to obtain the image information of potted seedlings, and to detect the presence or absence of potted seedlings and the spread of leaves. The spatial interference and field of view occlusion of the seedling throwing operation are prominent problems, and it is impossible to realize the complete measurement and disease spot detection of the seedlings in the seedling cup from the top view

Due to the high speed and high frequency of semi-automatic transplanting in the field, farmers cannot check the quality of pot seedlings one by one. Therefore, an efficient and intelligent pot seedling information detection system is urgently needed to ensure the quality of transplanting.

Images