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

Real-time segmentation system and method based on hybrid expansion network

A network and convolution technology, applied in the field of computer vision, can solve problems such as difficulty in meeting segmentation requirements, insufficient information extraction capabilities, and decreased accuracy performance, and achieve the effects of improving accuracy, improving capture capabilities, and expanding receptive fields

Pending Publication Date: 2020-12-18
HUNAN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these real-time models have problems such as insufficient information extraction ability and loss of detailed information, resulting in a decrease in accuracy performance, and it is difficult to meet the segmentation requirements for complex road conditions in practical applications.

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
  • Real-time segmentation system and method based on hybrid expansion network
  • Real-time segmentation system and method based on hybrid expansion network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Attached below figure 1 The preferred embodiment of the present invention is further described, and the present invention includes a lightweight backbone network MobileNet v2, a hybrid hollow convolution module;

[0023] The hybrid atrous convolution module consists of a lightweight spatial pyramid attention module and a global information enhancement module;

[0024] The described lightweight hybrid hole module achieves a comprehensive trade-off between accuracy and high efficiency (e.g., execution speed, memory footprint, or computational complexity) through multi-scale information and effective attention mechanism;

[0025] like figure 1 As shown, given an input, it is first fed into our backbone network to obtain semantic features. For high-resolution data sets, the output step size (OS) of the encoder is reasonably set to 8, which is a technique commonly used by people in the field to reduce the image size, so that the feature map can be down-sampled to 1 / 8 of th...

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 relates to a real-time segmentation system and method based on a hybrid expansion network, and belongs to the field of computer vision. The system comprises a backbone network MobileNetv2 and a lightweight hybrid hole convolution module. The lightweight hybrid hole convolution module realizes comprehensive balance in the aspects of accuracy and high efficiency through multi-scale information and an effective attention mechanism; the lightweight hybrid hole convolution module mainly comprises a depth separable attention module and a hybrid multi-scale module; the depth separableattention module is of a single-layer hybrid convolution design. In one aspect, the system may enhance the expression of information by increasing the depth of the network. On the other hand, the depth separable convolution performs convolution integral deconvolution on each channel, thereby reducing the parameter size and the calculation cost.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a real-time segmentation system and method based on a hybrid expansion network. Background technique [0002] At present, various sensors apply image segmentation technology, which has the ability to perceive the environment, and can segment and recognize various information in the picture. The sensor determines the follow-up work through the perception of the surrounding scene. The image segmentation model applied by it is usually divided into two types: , one is an end-to-end semantic segmentation model, and the other is a real-time segmentation model. [0003] In order to improve the accuracy of segmented images, previous end-to-end methods often design more complex semantic segmentation structures, such as multi-scale, dense connection strategies, etc. Chen et al. proposed the DeepLab series, mainly proposing a pyramid pooling module (ASPP) that uses expanded convolutions with...

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): G06K9/34G06N3/04
CPCG06V10/267G06N3/045
Inventor 蒋斌何建凯杨超
Owner HUNAN UNIV
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