Handheld Log Measurement via Image Stitching and Ellipse Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for automatically counting and measuring logs using images captured with handheld devices face challenges such as variations in illumination, viewpoint, scale, log size and shape, texture, blurring, shadows, and distractors, which lead to inaccurate results due to the limited processing power of mobile devices and lack of internet connectivity in remote locations.
Innovation Solution
A computer-based system configured with an image stitching subsystem, contour detection subsystem, log detection subsystem, and results generation subsystem on a handheld device that creates a working image, detects the log stack contour, fits ellipses to log faces, and generates results such as log count, volume, and diameter, using neural networks for segmentation and feature transformation to handle image variations and limited processing capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If simple models are used to estimate log volume by assuming perfect cylinders, then the calculation is simpler, but the accuracy of measurement is significantly reduced
Solution Approach 1:
The log stack is segmented into individual log components, with each log detected and measured separately using ellipse fitting. This allows accurate measurement of irregular log shapes while maintaining computational efficiency through component-wise processing rather than treating the entire stack as a single complex object.
Solution Approach 2:
The system transforms the measurement approach by changing from assuming perfect cylindrical shapes to using ellipse parameters (major axis, minor axis, orientation) that can accurately represent irregular log cross-sections. This parameter transformation enables accurate measurement of real-world log variations without requiring complex 3D modeling.
2Power
If cloud-based processing is used to handle complex image analysis, then the processing power is sufficient, but it becomes impractical due to limited or nonexistent internet bandwidth at remote log stack locations
Solution Approach 1:
The core image processing algorithms (image stitching, contour detection, ellipse fitting) are extracted from cloud-based environments and implemented directly on the mobile device. This extraction enables complex image analysis to be performed locally without requiring internet connectivity, making the system adaptable to remote locations while maintaining sufficient processing power through optimized mobile device utilization.
Solution Approach 2:
The system introduces an on-device processing intermediary layer that bridges the gap between limited mobile processing power and the need for complex image analysis. This intermediary performs critical processing functions locally, reducing or eliminating the need for cloud-based processing and enabling operation in remote locations with limited or no internet connectivity.
3Productivity
If automated analysis is implemented to count logs, then productivity increases, but the system becomes sensitive to various image variations such as illumination, viewpoint, scale, and distractors
Solution Approach 1:
The system performs preliminary image stitching and preprocessing operations before the actual log detection and counting. By preparing a consolidated working image that corrects perspective distortions and aligns multiple views in advance, the system reduces the impact of viewpoint variations and illumination differences during the critical detection phase, thereby improving reliability while maintaining automated productivity.
Solution Approach 2:
The system incorporates feedback mechanisms through iterative optimization of detection parameters and validation of detected log features. By continuously refining detection results based on geometric constraints and consistency checks, the system maintains high reliability in automated counting despite variations in image quality, distractors, and environmental conditions.
Data Source
AI summary
A computer-based system (e.g., a handheld device) is configured to detect, count, and measure logs in a stack. A user captures one or more images of the stack. Where multiple images are captured, the system creates a working image by stitching together portions of the image. The system identifies a contour indicating the outline of the stack in the working image and fits ellipses to the log faces in the working image. Information such as the number of logs, the volume of wood in the stack, and the average log diameter may be made available for presentation to the user.