System, method and medium for information gain and display
A technology of information gain and object information, applied in the field of AR scene application, can solve problems such as large computing and storage resources, inability to guarantee real-time performance and correlation between frames, and achieve the effect of solving correlation problems
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0046] The system for information gain and display according to the present invention includes: a sensor: used to continuously acquire scene information, and transmit the acquired information to the mobile computing unit; the mobile computing unit: screen the acquired information, Comparing and calculating to obtain the 3D position and attitude of the object; data exchange unit: responsible for the data exchange between the mobile terminal and the cloud, uploading the salient image and time stamp from the mobile terminal to the cloud computing unit, and downloading the results of cloud computing to the mobile terminal ; Cloud computing unit: take images as input, output feature vectors through neural network training, and then obtain corresponding object information based on retrieval methods; rendering display unit: render object information to corresponding 3D position and displayed on the display device.
[0047] The sensors include single or multiple color cameras, monochr...
Embodiment 2
[0062] Embodiment 2 is a preferred example of Embodiment 1.
[0063] The system for information gain and display provided according to the present invention includes:
[0064] Sensor: Used to continuously acquire scene information, which can be a combination of single or multiple color cameras, monochrome cameras, depth cameras, radars, etc., and the acquired information is transmitted to the mobile terminal computing unit.
[0065] Mobile computing unit, including:
[0066] (1) Information preprocessing
[0067] If the information acquired by the sensor does not meet the input requirements of the neural network, it needs to be preprocessed through steps such as noise reduction, optimization, and formatting, and then passed to the saliency detection neural network.
[0068] (2) Significance detection unit
[0069] A saliency detection unit can be,
[0070] A. There are a large number of categories, with label boxes, but the label category can be a detection neural network ...
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