A method for semantic segmentation of surface panoramic image
A panoramic image and semantic segmentation technology, applied in the field of computer vision recognition, can solve the problems of poor target segmentation effect and slow speed in small areas, and achieve the effect of real-time semantic segmentation, avoiding gradient decay, and fast segmentation.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0038] A method for semantic segmentation of water surface panoramic images, comprising:
[0039]Input the panoramic image of the water surface to be tested into the convolutional neural network for real-time semantic segmentation, and obtain the segmentation result of the panoramic image of the water surface;
[0040] Such as figure 2 As shown in (a), the traditional convolutional neural network uses a convolution with a length and a width of 3, and the size of the traditional convolution kernel is 3*3. The present invention uses two sizes of 3*1 and 1*3 respectively. The convolution kernel, such as figure 2 As shown in (b), the convolutional neural network sets skip connections every 4 convolutional layers.
[0041] When the number of input convolutional layer channels is c1 and the number of output volume base layer channels is c2, the calculation amount of traditional convolution is:
[0042] 3*3*c1*c2=9*c1*c2
[0043] The convolution calculation amount of the presen...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com