Camera-to-Reference Distance Measurement Using Classified Corners
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for measuring distance between a camera and a reference object using a smartphone are inaccurate due to short focal lengths, image distortion, and partial obscuration, requiring complex computing and high user training.
Innovation Solution
A method involving the detection of corners in an image pattern with predetermined classes, forming combinations of corners to locate reference points, and measuring distance based on these points rather than image borders, using a simple setup like a smartphone and a mirror.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a smartphone camera with short focal length is used for distance measurement, then the device complexity is reduced and ease of operation is improved, but the measurement precision deteriorates because the reference object image becomes small and occupies only a few pixels
Solution Approach 1:
The reference object is segmented into multiple corners with different orientations (classified into 4 classes based on orientation). By detecting and classifying these corner segments independently, the system can accurately identify the reference object's position and dimensions even when the overall image is small or partially obscured, thereby maintaining measurement precision with simple smartphone cameras
Solution Approach 2:
The approach transitions from measuring continuous image borders to detecting discrete corner points in the image plane. This dimensional shift from continuous to discrete measurement allows for more robust distance calculation using the formula: distance = (reference object size × camera focal length) / imaged reference object size, even with limited pixel resolution
2Ease of operation
If direct image border measurement is used for distance calculation, then the measurement process is simplified, but the reliability deteriorates due to image distortion and partial obscuration by hands or objects
Solution Approach 1:
The reference object detection is segmented into corner identification and classification steps. By focusing on detecting specific corner patterns (classifying corners into 4 orientation classes) rather than attempting to measure continuous borders, the system achieves reliable detection even when parts of the image are obscured or distorted
Solution Approach 2:
The method uses a predefined reference object pattern with known corner arrangements as a template. By comparing detected corner patterns against this known reference pattern, the system can reliably identify the reference object and calculate distance measurements without being affected by image quality issues
3Reliability
If complex algorithms are used to handle image distortion and obscuration, then the measurement reliability is improved, but the computing time increases
Solution Approach 1:
The detection algorithm is segmented into efficient steps: corner detection using established algorithms, classification of corners into 4 orientation classes, and pattern matching against predefined reference patterns. This segmented approach achieves reliable detection without requiring complex computational methods to handle distortion and obscuration
Solution Approach 2:
The system detects and classifies corners that are sufficient for identification rather than attempting to process or correct all image quality issues. By focusing computational effort on detecting the essential corner patterns needed for distance measurement rather than performing comprehensive image correction, the system achieves reliable results with reduced computing time
Data Source
AI summary
A method for measuring a distance separating a camera from a reference object including a predetermined number of corners arranged in a pattern and at least two reference points separated by a reference length. The method includes acquiring an image including the reference object with the camera, detecting corners in the image, attributing a class to each corner, based on an orientation of the corner, detecting the reference object in the image based on the corners and attributed classes, placing the reference points in the image based on the corners of the reference object and measuring an imaged length separating the reference points, and comparing the reference length to the imaged length and obtaining the distance separating the camera from the reference object.