Night viewing image noise reduction method for apple harvesting robot

Abstract

The invention discloses a night viewing image noise reduction method for an apple harvesting robot. The image noise reduction method for the apple harvesting robot comprises the steps that two night viewing images are collected consecutively with the same sampling position and the same angle through a camera in artificial light source, qualitative and quantitative analysis on noise containing in the night viewing images is conducted through a difference image method, and the noise type is judged that most of the noise is gaussian noise, and partial impulse noise is accompanied; according to the characteristics of the contained noise, firstly, the impulse noise and partial gaussian noise are removed through the use of a small valve soft threshold de-noising algorithm, and a lower gaussian noise image is acquired; maximum separation between image source signal and noise signal is conducted through the use of an independent component analysis method, and at that moment, the acquired image source signal contains partial gaussian noise; finally, noise reduction treatment is conducted on the image source signal through the use of the small valve soft threshold de-noising algorithm, and relative clean low-noise image is acquired. The night viewing image noise reduction method for the apple harvesting robot has the advantages that noise reduction function on the night viewing image is realized, preparation is made for the recognition of the night viewing image, and a foundation is laid for the further accomplishment of the night work of the apple harvesting robot.

Description

technical field [0001] The invention belongs to the field of agricultural machinery and relates to a night vision image processing method for a fruit and vegetable picking robot working at night. Background technique [0002] Since the fruit and vegetable picking robot came out in the 1960s, it has attracted the attention of many scholars at home and abroad, and now it has made great progress. However, most of the current research is based on picking under natural light during the day. In order to further reduce the workload of agricultural laborers, improve picking efficiency, ensure that apples are picked in time during the ripening period, and reduce economic losses, try to put forward the idea of ​​an apple picking robot working around the clock , that is, work at night to maximize the effectiveness of the fruit and vegetable picking robot. [0003] At present, there are relatively few studies on the night operation of picking robots, and the main test of night operatio...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a night vision image noise reduction method for an apple picking robot to solve the problem that the night vision image contains large noise due to insufficient light and low temperature

Images