Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Segmentation model training method and apparatus, road segmentation method and apparatus, and vehicle control method and apparatus

A technology for segmenting models and training methods, applied in the computer field, can solve problems such as high cost, low efficiency, and labor consumption, and achieve high accuracy, high efficiency, and less time-consuming effects

Active Publication Date: 2017-04-05
BEIJING TUSEN WEILAI TECH CO LTD
View PDF9 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method requires a lot of manual labeling work, which is time-consuming, labor-intensive, high in cost and low in efficiency.

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
  • Segmentation model training method and apparatus, road segmentation method and apparatus, and vehicle control method and apparatus
  • Segmentation model training method and apparatus, road segmentation method and apparatus, and vehicle control method and apparatus
  • Segmentation model training method and apparatus, road segmentation method and apparatus, and vehicle control method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] figure 1 , is a flowchart of the segmentation model training method provided in Embodiment 1 of the present invention, the method includes:

[0054]Step S101 : performing free region segmentation on the training sample image by using an unsupervised free region segmentation method to obtain a free region segmented image of the training sample image.

[0055] In step S101, the training sample image may be a left-eye image or a right-eye image collected by a binocular camera installed on a vehicle.

[0056] The unsupervised free area segmentation method refers to the use of an unsupervised method to segment the free area in the image (that is, the area without obstacles, such as roads, grass, etc.); the unsupervised method means that it does not need to learn the road segmentation images that are manually labeled , directly segment the free area in the training sample image according to a certain learning method.

[0057] Step S102, using the training sample image as th...

Embodiment 2

[0116] Embodiment 2 of the present invention provides a road segmentation method, and the target segmentation model used in the road segmentation method is trained by the training method provided in the foregoing embodiment 1.

[0117] see Image 6 , is a flow chart of a road segmentation method provided in Embodiment 2 of the present invention, the method includes:

[0118] Step S601: Receive an image to be segmented.

[0119] Step S602: Input the image to be segmented into a target segmentation model, and output a road region segmented image of the image to be segmented.

[0120] In Embodiment 2 of the present invention, the target segmentation model is pre-trained according to the segmentation model training method provided in Embodiment 1.

Embodiment 3

[0122] Embodiment 3 of the present invention provides a vehicle control method, such as Figure 7 As shown, the method includes:

[0123] Step S701: receiving the image of the road environment ahead captured by the camera on the vehicle;

[0124] Step S702: Input the image into the target segmentation model to obtain the road area segmentation image of the image, wherein the target segmentation model is trained by the method of Embodiment 1;

[0125] Step S703: Obtain the drivable area of ​​the road ahead according to the segmented image of the road area;

[0126] Step S704: Control the driving direction of the vehicle according to the drivable area and the vehicle position.

[0127] In practical applications, the camera installed on the vehicle can be a binocular camera or a monocular camera. The camera feeds back the image of the road environment ahead to the control device, and the control device uses the image as the input image of the built-in target segmentation model ...

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 segmentation model training method to solve the problems of low training efficiency, long time consumption, and high cost of a segmentation model in the prior art. The method includes: performing free area segmentation on a training sample image by employing an unsupervised free area segmentation method to obtain a free area segmentation image of the training sample image; performing iterative training on a preset convolution neural network by employing a self-paced learning method and by regarding the training sample image as an input image and regarding the free area segmentation image as a mark image to obtain an initial segmentation model; and training the initial segmentation model by regarding a preset standard sample image as the input image and regarding a road area image marked on the standard sample image in advance as the mark image to obtain a target segmentation model. By employing the method, the segmentation accuracy of the segmentation model obtained by training is ensured, the training speed and efficiency can be increased, and road segmentation is performed based on the target segmentation model so that the result of road segmentation is more accurate.

Description

technical field [0001] The invention relates to the field of computers, in particular to a segmentation model training method and its device, a road segmentation method and its device, a vehicle control method and its device. Background technique [0002] In the field of automatic driving or unmanned driving, road segmentation technology (road segmentation refers to segmenting the road area in the image) is one of its core technologies. The current way of road segmentation is mainly to segment the images captured by the camera through the road segmentation model to obtain the road area. [0003] At present, the training method of the road segmentation model is mainly as follows: a large number of training sample images (such as left-eye images or right-eye images collected by binocular cameras) are manually labeled to obtain the labeled images of the training sample images. The image trains a convolutional neural network to obtain a road segmentation model. This method req...

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): G06T7/11G05D1/02
CPCG05D1/0217G06T2207/20081G06T2207/20084G06T2207/30256
Inventor 王乃岩
Owner BEIJING TUSEN WEILAI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products