An Augmented Reality Method for Specular and Repeated Texture Removal and Crawling Mat Application
An augmented reality, texture technology, applied in image enhancement, image data processing, image analysis and other directions, can solve problems such as low accuracy, difficult image recognition, inability to match or fast match, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0025] see figure 1 , Embodiment 1 provides an augmented reality method for removing highlights and repeated textures, the method comprising the following steps:
[0026] S101: Obtain a real-time image to obtain an original image.
[0027] S102: Segregate the highlight area in the original image obtained in step S101 by calculating the outline and position of the highlight area, and perform noise reduction and filtering processing on the highlight area that can preserve the identification features. Specifically, this step can be based on the statistical rules of color, and the highlight can be removed by using the characteristic of local smoothness of the maximum diffuse reflection chroma. This step does not necessarily preserve the original image exactly, but it can preserve enough recognizable image features.
[0028] S103: Determine whether the image after highlight removal in step S102 contains repeated texture features, if there are repeated texture features, perform st...
Embodiment 2
[0034] Embodiment 2 provides an augmented reality method for removing highlights and repetitive textures, the method comprising the following steps:
[0035] S201: Run an augmented reality program on a mobile terminal or field device.
[0036] S202: Invoke the camera to scan the crawling mat and objects on it to obtain real-time images.
[0037] S203: Determine whether the current processing device has a GPU, if so, send the original image obtained in step S202 to the GPU for processing, and execute steps S204-207; if there is no GPU, send the original image obtained in step S202 to the CPU for processing, Execute steps S204-207. That is, in order to improve the processing speed, the image is sent to the GPU for processing first.
[0038]S204: Calculate the gray value of the original image obtained in step S202, determine the highlight area (the average gray value is continuously distributed between 220 and 245) according to the gray value, and use the canny operator of Open...
Embodiment 3
[0050] see Figure 6 , Embodiment 3 provides an augmented reality system for removing highlights and repeated textures, the system comprising:
[0051] The crawling mat is a common crawling mat on which various patterns are printed.
[0052] Camera 1: used to obtain real-time images.
[0053] Image processing module 2: used to obtain the original image obtained by camera 1, separate the highlight area in the original image, and perform noise reduction and filtering processing on the highlight area that can retain the recognition features; determine whether the image contains repeated texture features after highlight removal , if there are repeated texture features, then determine the position of the texture point according to the texture feature value, perform smoothing filtering on the texture point, and send the image after texture removal to the augmented reality module 3; if there is no repeated texture feature, send the image after highlight removal to Augmented Reality...
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