Machine vision-based super hybrid rice bunch seeding quantity detection method and device

Abstract

The invention relates to a super hybrid rice seeding tray seeding bunch seeding quantity detection method and a device. The detection device comprises a camera, a computer and an infrared photoelectric sensor module. When a rice seeding tray after seeded is detected to arrive at a shooting region via a conveyor belt, the infrared photoelectric sensor module outputs level signals to the computer; the computer controls the camera to shoot a seeding tray image; the computer carries out binarization processing on the seeding tray image, a projection method is used to position a seeding tray detection region and seeding bunches, a communication region and appearance feature parameters thereof are extracted, main components of the appearance feature parameters are analyzed so as to reduce dimension, a BP neural network for detecting the particle number in the seed communication region is built, and the BP neural network is finally adopted to detect the seeding quantity of the seeding tray. The appearance features of the seed communication region are combined with the BP neural network for detecting seeding quantity of seeding bunches, the seeding quantity can be precisely detected according to the bunch number detection idea, and a foundation is laid for research on a precise seed breeding and constant-quantity seeding device for the super hybrid rice.

Description

Technical field [0001] The invention relates to a method and device for detecting the seeding amount of super hybrid rice seedling trays after sowing, in particular to a method and device for detecting the seeding amount of super hybrid rice based on machine vision. Background technique [0002] Super hybrid rice has been widely used in my country because of its significant increase in yield. Because of its super tillering ability, it is required to insert 1-2 plants per hole, and rely on the tillering ability to increase the effective number of panicles and increase the yield. According to the growth characteristics of super hybrid rice, seedling raising usually requires low seeding rate and precise seedling raising to ensure 2-3 grains per hole. Because rice seeds need to be germinated and then planted, the sprout length, seed water content and seed shape and size will change during the sowing period, which will affect the seeding performance. Current precision seeding techniqu...

AI Technical Summary

Problems solved by technology

Because rice seeds need to be sown after germination, the length of seed buds, seed water content and seed shape and size will all change during sowing, which will affect the sowing performance. The current precision sowing technology and means are difficult to meet the above requirements

Images