Marker-Based Position Detection for Accurate 3D Target Orientation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing position detection systems for work machines lack accuracy in specifying the position of detection targets using learned models.
Innovation Solution
A position detection system that includes marks on the detection target, an imaging device, a measurement device, and a controller to calculate the position and attitude of the detection target based on marker information and three-dimensional shape data, with correction and estimation mechanisms to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If image recognition using a learned model is used to specify the position of a detection target, then the system can operate without physical markers, but the position detection accuracy deteriorates
Solution Approach 1:
The patent combines multiple detection approaches by integrating both learned model-based image recognition and physical marker recognition systems. The system merges the advantages of both methods: the versatility of markerless operation with the precision of marker-based detection, achieving both adaptability and measurement accuracy simultaneously
Solution Approach 2:
The patent introduces markers as intermediary objects that bridge the gap between the detection system and the detection target. These markers serve as reliable reference points that enhance position detection accuracy while maintaining the overall markerless system architecture, acting as mediators between the imaging device and the cargo bed
2Measurement precision
If multiple marks are provided on the detection target to improve position detection accuracy, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent segments the position detection task into multiple independent components: marker detection, marker position calculation, and cargo bed position derivation. By dividing the detection target into multiple marked regions and processing each independently, the system achieves high measurement precision while managing device complexity through modular processing steps
Solution Approach 2:
The patent changes the parameter of mark quantity from one to multiple, and simultaneously changes the processing parameter from direct image recognition to coordinate-based calculation. This parameter transformation allows the system to improve measurement precision through multiple marks while reducing the computational complexity by using straightforward geometric calculations rather than complex image analysis
3Measurement precision
If the position is calculated based on multiple marks and three-dimensional shape information, then the position detection accuracy improves, but the calculation complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-storing the three-dimensional shape information of the cargo bed and pre-defining the spatial relationships between marks and the cargo bed. This advance preparation allows the system to achieve high position detection accuracy during operation without performing complex real-time calculations, as the necessary geometric data is already prepared and stored
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate detection of the position and attitude of the detection target, improving operational precision and robustness in various types of dump trucks.
Implementation Method 1
an imaging device, arranged to view the markers and generate image data representative of the relative positions of the markers
Implementation Method 2
a measurement device configured to measure a distance to the at least one detection target
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A position detection system includes: a mark (71) provided on a detection target (27); an imaging device (4) that images the detection target (27) so as to include the mark (71); an acquisition unit that acquires a position and an attitude of the mark (71) from imaging information that is information related to the mark (71) imaged; a storage device (13) that stores information on a three-dimensional shape of the detection target (27); and a detection target calculation unit that calculates a position and an attitude of the detection target (27) based on mark related information that is information related to acquired position and attitude of the mark (71) and stored information on the three-dimensional shape of the detection target (27).