Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Road green belt trimming task automatic generation method based on neural network and CIM

A neural network and green belt technology, applied in botanical equipment and methods, details involving image stitching, image data processing, etc., can solve problems such as affecting the city appearance, high labor intensity for observers, inaccurate information, etc. Inaccuracy and omission, reducing the breeding of pests, the effect of strong generalization ability

Inactive Publication Date: 2020-11-17
郑州迈拓信息技术有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] If the urban green belt is not pruned in time when it grows naturally, the phenomenon of closed canopy and dense branches will often appear, which will not only affect the city appearance, but also affect people's traffic
At present, the pruning period of the green belt needs to be judged manually, and the use of manual observation, on the one hand, the labor intensity of the observers is high, on the other hand, due to factors such as tight manpower, high cost, and human cognition, it will lead to inaccurate information and omissions. phenomenon occurs

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Road green belt trimming task automatic generation method based on neural network and CIM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0025] Construct the CIM (city information model) of the road area, that is, based on the city information data, establish an organic synthesis of the three-dimensional urban space model and urban information; the CIM of the road area mainly includes the perception information of the camera and the corresponding geographical location information and information about the current environment.

[0026] The acquisition of RGB images of green belts is realized through multiple cameras beside the road. The image acquisition range of all cameras must cover the total area of ​​urban road green belts, and the images collected by two adjacent cameras must overlap within a certain range, which is convenient Subsequent image stitching operations.

[0027] Each camera collects continuous multi-frame images of the area where it is located. It should be noted that the resolution, refresh rate, etc. of all cameras use the same settings.

[0028] The projection transformation operation is pe...

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

No PUM Login to View More

Abstract

The invention provides a road green belt trimming task automatic generation method based on a neural network and a CIM, and the method comprises the steps: carrying out the collection of an RGB imageof a green belt through a road camera, transmitting the RGB image to a semantic segmentation network, outputting a semantic segmentation image, taking the semantic segmentation image as a mask, carrying out the trimming operation of the RGB image, and obtaining a green belt image; and performing post-processing on the green belt image to obtain a texture feature map, sending the texture feature map to a texture classification network, outputting a texture clutter level of the green belt after processing, storing an output result of the texture classification network in a CIM, and generating acorresponding green belt trimming task according to the output clutter level. According to the method, the messy situation of the road green belt can be objectively and accurately judged, and a greenbelt trimming task is automatically generated to remind related department managers to trim the green belt in time.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and smart cities, in particular to a method for automatically generating road green belt pruning tasks based on neural networks and CIM. Background technique [0002] If the urban green belt is not pruned in time when it grows naturally, the phenomenon of closed canopy and dense branches will often appear, which not only affects the city appearance, but also affects people's traffic. At present, the pruning period of the green belt needs to be judged manually, and the use of manual observation, on the one hand, the labor intensity of the observers is high, on the other hand, due to factors such as tight manpower, high cost, and human cognition, it will lead to inaccurate information and omissions. phenomenon occurs. Contents of the invention [0003] In order to solve the above problems, the present invention proposes a method for automatic generation of road green belt pruning tasks bas...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/40G06T7/11G06K9/62A01G3/00
CPCG06T3/4038G06T7/11A01G3/00G06T2200/32G06T2207/10004G06T2207/10024G06T2207/20024G06T2207/20081G06T2207/20084G06F18/241
Inventor 张瑞根陈素娜
Owner 郑州迈拓信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products