Shelf Positioning via Visual Key Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for positioning lifting shelves in automated warehousing and logistics systems suffer from inaccuracies due to reliance on depth information from LiDAR, solid-state radar, and RGBD cameras, which only reflect geometric characteristics of parallel plates.
Innovation Solution
A method involving image data acquisition through an image acquisition module in movable equipment, followed by processing through a key point detection network to extract position information of shelf key points in an image coordinate system, and then determining the relative pose of these key points relative to the movable equipment without requiring depth information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If depth information collection devices (LiDAR, solid-state radar, RGBD cameras) are used to position the lifting shelf, then the positioning function is achieved, but the positioning accuracy is poor due to only reflecting geometric characteristics of parallel plates
Solution Approach 1:
The patent replaces traditional depth information collection devices (LiDAR, solid-state radar, RGBD cameras) with a two-dimensional image acquisition device. Instead of relying on depth data that only captures geometric characteristics, the system uses 2D images processed through a key point detection network to extract visual semantic features, thereby achieving more accurate shelf positioning without depth information
Solution Approach 2:
The patent creates a virtual representation of the shelf by detecting key points (corners and edges) in the 2D image and constructing a key point model. This virtual key point model captures the essential geometric and semantic information needed for positioning, replacing the need for direct depth measurement while maintaining positioning functionality
2Measurement precision
If multiple depth information devices are deployed to improve positioning accuracy, then measurement precision may improve, but device complexity and hardware costs increase
Solution Approach 1:
The patent extracts only the essential visual features needed for positioning from the image data, using a key point detection network to identify corner and edge points. This extraction approach eliminates the need for complex depth sensing hardware while retaining the critical information required for accurate shelf positioning
Solution Approach 2:
The patent uses a simple, inexpensive 2D image acquisition device instead of expensive depth information devices like LiDAR and solid-state radar. The system achieves positioning functionality through processing affordable 2D images rather than relying on costly specialized hardware, thereby reducing overall system cost and complexity
Data Source
AI summary
The present application provides a shelf positioning method, a shelf connecting method and device, equipment and a medium. The method comprises the following steps: acquiring image data, in the environment where a movable equipment is located, through an image acquisition module in the movable equipment; inputting the image data into a key point detection network to extract first position information of shelf key points in an image coordinate system from the image data through the key point detection network; and determining relative pose of the shelf key points relative to the movable equipment according to the first position information and a conversion relationship between the image coordinate system and a vehicle body coordinate system. In this method, visual semantic features of a shelf are extracted from the image data of the environment where the movable equipment is located through the key point detection network, and the a relative pose of the shelf relative to the movable equipment is determined based on the visual semantic features, which makes the detection of the position of the shelf more accurate, improves the accuracy of shelf positioning, expands the application range of shelf positioning and reduces the hardware cost of shelf positioning.