Picking robot unstructured road recognition method based on semantic segmentation
A picking robot and unstructured technology, applied in the field of robotics, can solve problems such as high computer hardware requirements, winding road shapes, and lighting conditions, and achieve the effects of increasing processing efficiency, accelerating convergence, and reducing the difficulty of training
Pending Publication Date: 2022-04-12
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
It solves the problems that traditional unstructured road recognition is easily affected by lighting conditions, road boundaries are blurred, and the road shape is winding. Disadvantages such as high hardware requirements
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
[0042] The embodiments of the present invention will be described below with reference to the specific examples of the present invention, and those skilled in the art can easily understand other advantages and efficacy of the present invention. The present invention can also be implemented or applied by other embodiments, and various details in this specification may also be based on different viewpoints and applications without departing from the spirit of the invention. It should be noted that the illustrations provided in the following examples will be described only by way of illustration, and in the case of unlamating, the following embodiments and embodiments may be combined with each other.
[0043] The drawings are for exemplary description, which is intended to be schematic diagrams, rather than experiencing, is not understood to limit the invention; in order to better illustrate an embodiment of the invention, there will be omitted, To zoom in, it does not represent the ...
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 relates to a picking robot unstructured road recognition method based on semantic segmentation, and belongs to the field of robots. The method comprises the following steps: firstly, acquiring an unstructured road image through an RGB color camera, secondly, extracting road feature information by taking Moilentv2 as a backbone network, sending the road feature information into a pyramid pooling module of PSPnet to carry out regional pooling to obtain feature maps of different sizes, then carrying out multi-scale feature information fusion on the feature maps through bilinear difference up-sampling operation, and finally, carrying out multi-scale feature information fusion on the feature maps. Performing feature optimization through discarding, and finally inputting into a prediction classification layer to obtain a final prediction result.
Description
Technical field [0001] The present invention belongs to the field of robot, involving a non-structured road recognition method based on semantic segmentation. Background technique [0002] Non-structured road recognition techniques are mainly used in the field of smart mobile robots. As early as the 1970s, some developed countries have taken the lead in starting a non-structured road research. Compared to intelligent mobile robots, intelligent agricultural robots have poor work environment and more complicated, with ambiguity, unevenness, multi-objective. In order to realize the safety of agricultural robots, autonomous movements, the development of new non-structured road recognition technologies began to be published by major research institutions. [0003] Traditional non-structural road recognition technology, such as a non-structuring road recognition method based on color, texture, shape, etc., is the disadvantage that the external color, texture, and shape of the non-struc...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06V20/10G06K9/62G06N3/04G06V10/40G06V10/80G06V10/764
Inventor 郑太雄张红江明哲杨新琴
Owner CHONGQING UNIV OF POSTS & TELECOMM