Check patentability & draft patents in minutes with Patsnap Eureka AI!

Padding method for convolutional neural network

A convolutional neural network, filling method technology, applied in the field of machine-readable storage media, can solve the problem of not providing input data and so on

Pending Publication Date: 2020-09-15
ROBERT BOSCH GMBH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, if the input data array maps a ring of surrounding information (as in the case of at least partially autonomous robots, for example), the known filling methods do not offer the possibility to deal specifically with this type of input data

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
  • Padding method for convolutional neural network
  • Padding method for convolutional neural network
  • Padding method for convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] Figure 1a Data 10 showing a two-dimensional concentric configuration. For example, this concentrically configured data 10 is associated with surroundings data which were recorded concentrically to the object, in particular an at least partially automated vehicle. In order to process the concentrically structured data 10, it must be unfolded. Such as Figure 1a As shown, the concentrically configured data 10 has the shape of a hollow cylinder with the object concentrically arranged in the center of the hollow cylinder.

[0057] In order to expand the concentrically structured data 10 , these are separated at a separation point 11 and expanded into a data array 20 . In this way, the real relevant data 21 , 26 arranged at the separation point 11 are arranged on two opposite sides of the data array 20 .

[0058] Figure 1b Data 10 shows a one-dimensional concentric configuration. The expansion of data 10 for this concentric configuration corresponds to Figure 1a 10 Em...

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 padding method for a convolutional neural network, in particular for concentrically configured data. The method includes receiving concentrically configured data of an object, the concentrically configured data correlating with an image, which was recorded concentrically to the object, deconvolving the concentrically configured data to form a data array, including real-coherent data on opposite sides of the data array, carrying out a convolution operation by using ring padding, in the case of ring padding, the real-coherent data of one side of the data array being utilized for padding the real-coherent data of a side of the data array opposite thereto, and / or vice versa.

Description

technical field [0001] The invention relates to a padding method for a convolutional neural network, a device, a computer program and a machine-readable storage medium. Background technique [0002] Convolutional neural networks, also known as folded neural networks (faltende neuronale Netzwerk), are considered to be one of the most efficient tools for image processing or video processing. [0003] Image data and other physical observations from the robot's surroundings are important sources of information when controlling an at least partially autonomous robot, in particular an at least partially autonomous vehicle. Use artificial neural networks (such as convolutional neural networks) to classify which objects are present in the robot's surrounding environment from this very high-dimensional data. [0004] Modern convolutional neural networks have different layers (so-called convolutional layers). An output data array is generated from an input data array (for example im...

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): G06T1/60G06T1/40G06N3/063G06V10/764
CPCG06T1/60G06T1/20G06N3/063G06N3/045G06N3/08G06V20/10G06V10/82G06V10/764G05D1/0246G05D1/0088
Inventor G·韦尔凯K·I·基什P·克勒希-绍博
Owner ROBERT BOSCH GMBH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com