Granary grain pile volume measuring and calculating method based on binocular camera

Abstract

The invention discloses a granary grain pile volume measuring and calculating method based on a binocular camera. The method comprises the following steps: setting binocular cameras, taking a grain pile of a granary as the center, setting three binocular cameras on the periphery of the grain pile in a triangular arrangement mode, wherein the height of the binocular cameras is larger than that of the grain pile, the view angle of the binocular cameras completely covers the grain pile, and the grain pile is located in the center of the view field of the binocular cameras; using RGBD images collected by the three binocular cameras as input data at the same time, and performing grain heap feature point detection, coordinate system conversion and distance calculation of the grain heap respectively; and estimating the geometrical shape of the grain heap, and calculating the volume of the grain heap by using a pre-established grain heap geometrical model. According to the invention, early warning can be carried out for the storage capacity of the granary, physical constraints of manual measurement and mechanical sensor measurement are avoided, the defects of poor universality and low flexibility are improved, the measurement efficiency is improved, online estimation of the operation flow of the harvester is realized, and direct economic loss is avoided.

Description

technical field [0001] The invention relates to testing and measuring technology, in particular to a binocular camera-based method for measuring and calculating the volume of granary grain piles. Background technique [0002] In order to improve the monitoring ability of my country's combine harvester grain granary, it is necessary to focus on solving the problem of dynamic detection of grain output. In the prior art, the detection of grain loading in granaries is mainly based on mechanical sensors, including scales, ultrasonic sensors, three-dimensional laser scanning sensors, pressure sensors, etc., and the grain loading is calculated according to the established model. The above methods generally have problems such as complex measurement process, poor measurement accuracy, lack of flexibility and universality. Existing mechanical, acoustic, optical, and electronic sensors generally have defects such as high failure rate, poor stability, and poor ability to withstand hars...

AI Technical Summary

Problems solved by technology

The above methods generally have problems such as complex measurement process, poor measurement accuracy, lack of flexibility and versatility, etc.

Existing mechanical, acoustic, optical, and electronic sensors generally have defects such as high failure rate, poor stability, and poor resistance to harsh environments.

Images