Fruit yield estimation method and system based on space and ground information acquisition cooperative processing

Abstract

The invention provides a fruit yield estimation method based on space and ground information acquisition cooperative processing. The method comprises the following steps: S10, acquiring a fruit tree video sequence through ground equipment; S20, carrying out fruit detection and positioning based on a result obtained in the step S10; S30, carrying out fruit multi-target tracking counting based on a result obtained in the step S20, and obtaining a preliminary yield estimation result; S40, collecting fruit tree images from the air; S50, performing fruit tree crown segmentation and positioning on the fruit tree graph obtained in the step S40; S60, constructing a crown shielding model based on results obtained in the step S30 and the step S50; and S70, completing final yield estimation. The invention also correspondingly provides a fruit yield estimation system based on space and ground information acquisition cooperative processing. According to the invention, high-precision fruit yield estimation can be carried out on the fruit yield of a dense orchard scene.

Description

technical field [0001] The invention belongs to the field of target recognition technology and smart agriculture technology, and in particular relates to a fruit yield estimation method and system based on space and ground information collection and collaborative processing. Background technique [0002] With the rapid development of computer vision and smart agriculture, fruit detection technology has become a research hotspot. This technology has important practical significance for the realization of fruit production statistics, automatic fruit picking and orchard automatic management. Marketing strategy plays a vital role. Accurately counting the output of the orchard before harvesting the fruit will help managers rationally allocate labor according to the distribution of fruits in the park at this stage. Intelligent production. [0003] In recent years, deep learning technology has gradually replaced traditional computer vision technology and has become the mainstream...

AI Technical Summary

Problems solved by technology

The results show that the yield estimation method based on the video sequence is more accurate than the yield estimation method using a single fruit tree image. Growing inside the canopy, it is difficult for cameras or human eyes to observe from the outside of the fruit tree, and this technology does not take into account the influence of fruits growing inside the dense leaves, so there will still be large errors in the final yield estimation results

Images