Industrial robot vision image recognition method and system based on survival confrontation
An industrial robot and visual image technology, applied in image feedback, image enhancement, image analysis, etc., can solve the problem of low efficiency of interference-free images, and achieve the effect of overcoming difficult acquisition, high efficiency, and avoiding processing
Pending Publication Date: 2020-08-18
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In order to solve the above-mentioned problems in the prior art, that is, the inability of the prior art to deal with different types of interference and the low efficiency caused by the processing of non-interference images, the present invention provides a visual image recognition method for industrial robots based on survival confrontation, The visual image recognition method includes:
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0056] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, not to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.
[0057] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.
[0058] The present invention provides a visual image recognition method for industrial robots based on survival confrontation. This method first classifies image interference types based on deep convolutional neural networks, and then calls the trained generative confrontation networ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the field of robot vision image processing, particularly relates to an industrial robot vision image recognition method, system and device based on survival confrontation, which aim to solve the problems that in the prior art, different types of interference cannot be processed, and the efficiency is low due to the fact that interference-free images are processed. The method comprises the following steps of carrying out template matching on an obtained industrial robot vision image and a template image corresponding to each workpiece, directly outputting a matched recognition result in the case of matching, and carrying out classification according to an interference type through a classification network in the case of non-matching, calling an image reduction subnetwork corresponding to the interference type to generate a restored image, and carrying out template matching on the restored image and each target image, and outputting a matched recognition result.According to the method, the corresponding image reduction subnetwork is trained for different types of interference, a clearer non-interference image can be generated, image matching is directly carried out on the clearer image, the image recognition precision is high, the efficiency is high, and few system resources are occupied.
Description
technical field [0001] The invention belongs to the field of robot visual image processing, and in particular relates to an industrial robot visual image recognition method, system and device based on survival confrontation. Background technique [0002] Today, with the rapid development of robots, industrial robots are more and more widely used in manufacturing. Robotic operations play an important role in automated production processes in areas such as automobile and auto parts manufacturing, machining, electrical and electronic production, rubber and plastic manufacturing, food processing, wood and furniture manufacturing. Robotic gripping of industrial parts is a common task in automated production in manufacturing. At present, visual guidance and positioning technology has become the main means for industrial robots to obtain information about the surrounding environment. [0003] Changes in ambient light and various noises in industrial environments, such as Gaussian...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T7/73G06T1/00
CPCG06T7/74G06T1/0014G06T2207/30164G06T2207/20081G06T2207/20084
Inventor 李玉苹蒋应元聂祥丽乔红
Owner INST OF AUTOMATION CHINESE ACAD OF SCI