Substation inspection robot image semantic analysis system and method
A patrol inspection robot and semantic analysis technology, applied to manipulators, program-controlled manipulators, manufacturing tools, etc., can solve problems such as heavy workload, subjective judgment of inspection and detection points, and data analysis delay, etc., to improve operation safe effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0055] Example 1
[0056] This embodiment discloses a robot image semantic analysis system based on embedded AI technology, including: an embedded AI analysis module, and a multi-degree-of-freedom robotic arm, an inspection camera, a binocular, and a multi-degree-of-freedom robotic arm connected to the embedded AI analysis module. Vision cameras, 3D lidars, inertial navigation sensors, robotic industrial computers, and multi-degree-of-freedom camera platforms; among them, the binocular vision camera is located at the front end of the robot, and the inspection camera is located at the end of the robotic arm through the multi-degree-of-freedom camera platform. The industrial computer is connected to the robot motion platform. It can realize the data access and synchronous acquisition of multiple sensors such as vision, laser, GPS, inertial navigation, etc., so as to realize the panoramic perception of the robot itself and the surrounding environment. Among them, the binocular v...
Example Embodiment
[0098] Embodiment 2
[0099] This embodiment provides a method for analyzing image semantics of a substation inspection robot, and the method includes the following steps:
[0100] Real-time acquisition of binocular image data, inspection image data and 3D point cloud data of the current environment;
[0101] Obtain the spatial distribution of objects in the current environment based on binocular image data and 3D point cloud data;
[0102] According to the spatial distribution of objects in the current environment, determine whether there is a passable unknown area, if so, control the robot to move to the passable unknown area, and execute the map construction; if not, the map construction ends;
[0103] The performing map construction includes: obtaining spatial distribution of objects in the current environment based on binocular image data; obtaining semantic information of objects in the current environment based on inspection image data; according to the spatial locatio...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap