3D Measurement Accuracy with Moving Object Exclusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional three-dimensional measurement techniques suffer from accuracy deterioration when other moving objects are present in captured images due to their movement, affecting the position and direction information used in image analysis.
Innovation Solution
A measurement device equipped with processing circuitry that acquires and analyzes images from a moving object, identifies moving object regions, estimates the position and posture of the image capturing unit, and performs three-dimensional measurement using corresponding points in non-moving object regions, thereby isolating and excluding moving objects from the measurement process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional three-dimensional measurement techniques are used with images captured in time series, then measurement capability is provided, but measurement precision deteriorates when other moving objects are present in the captured images
Solution Approach 1:
The patent segments the captured images by identifying and separating moving object regions from non-moving object regions. The processing circuitry divides the image data into distinct segments: regions containing other moving objects and regions containing stationary objects, allowing different processing approaches for each segment to eliminate measurement errors caused by moving objects.
Solution Approach 2:
The patent extracts and removes the harmful influence of moving objects from the measurement process. By identifying moving object regions and excluding them from three-dimensional measurement calculations, the system extracts only the necessary non-moving object regions for accurate measurement, effectively taking out the source of measurement errors.
2Area of stationary object
If all regions in captured images are used for three-dimensional measurement, then measurement coverage is maximized, but measurement precision deteriorates due to position changes of moving objects
Solution Approach 1:
The patent applies segmentation to divide the total measurement area into valid measurement regions (non-moving objects) and invalid regions (moving objects). This allows the system to maintain extensive measurement coverage by including all stationary objects while simultaneously ensuring high precision by excluding moving objects that would introduce errors.
Solution Approach 2:
The patent applies different quality standards to different regions of the captured images. Non-moving object regions are processed with high-precision three-dimensional measurement algorithms, while moving object regions are identified and excluded from measurement calculations. This local differentiation ensures that each region is processed according to its characteristics, maximizing overall measurement quality.
Data Source
AI summary
According to an embodiment, a measurement device includes a processing circuitry. A plurality of images are captured in time series by an image capturing unit installed in a moving object. The processing circuitry identifies a region in which other moving object moving in surroundings of the moving object is present for each of the images, based on position and direction information of the moving object, and moving object information of the other moving object. The processing circuitry estimates position and posture of the image capturing unit based on the images. The processing circuitry searches for sets of corresponding points among non-moving object regions in the respective images. The processing circuitry performs 3D measurement based on the position and posture of the image capturing unit and the sets of the corresponding points.