Stereo Camera Automatic Range Finding Depth Histogram
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional stereo cameras for people-flow tracing require manual calibration and have low computation performance due to high data processing demands, leading to increased complexity and reduced lifespan.
Innovation Solution
A stereo camera with an automatic range finding method that uses an image sensor and operating processor to acquire disparity-map videos, generate depth histograms, select relevant pixel groups, and apply coarse-to-fine computation to calculate distance to a reference plane, reducing manual adjustment time and computation load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual calibration is performed to set camera parameters accurately, then measurement precision is improved, but device complexity and installation time increase
Solution Approach 1:
The system performs automatic calibration using the reference plane and depth histogram analysis, eliminating the need for manual parameter setting. The camera automatically determines calibration parameters through self-calibration algorithms that process disparity-map videos and generate depth histograms, thereby improving ease of installation while maintaining measurement precision.
Solution Approach 2:
The calibration process is performed automatically during system initialization or setup phase using predefined reference planes. By pre-calibrating the system with known reference geometries and storing calibration parameters, the complex manual calibration process is replaced with a automated preliminary action that simplifies subsequent operations.
2Measurement precision
If full-resolution disparity-map video is processed for people-flow tracing, then analysis accuracy is improved, but computation performance deteriorates
Solution Approach 1:
The disparity-map video processing is divided into multiple stages: first generating a depth histogram to identify relevant depth ranges, then selectively processing only the pixel groups that fall within these ranges. This segmentation approach filters out unnecessary computational work while preserving accuracy for relevant regions, thereby improving computation performance without sacrificing analysis accuracy.
Solution Approach 2:
Instead of processing the entire disparity-map video at full resolution, the system applies partial action by focusing computational resources only on selected pixel groups that are most relevant to people-flow tracing. This selective processing reduces the overall computation load while maintaining sufficient accuracy for the intended application.
3Loss of information
If large amounts of data are processed for people-flow tracing, then analysis completeness is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary analysis by generating depth histograms and identifying significant pixel groups before conducting full people-flow tracing. This preliminary action pre-processes the data to extract key features and filter out irrelevant information, thereby reducing the time required for subsequent detailed analysis while maintaining data completeness.
Solution Approach 2:
The system extracts only the most relevant information from the disparity-map video by analyzing depth histograms and selecting significant pixel groups. By taking out and focusing on the essential data elements rather than processing all data equally, the system reduces processing time while preserving the completeness of critical people-flow information.
Data Source
AI summary
An automatic range finding method is applied to measure a distance between a stereo camera and a reference plane. The automatic range finding method includes acquiring a disparity-map video by the stereo camera facing the reference plane, analyzing the disparity-map video to generate a depth histogram, selecting a pixel group having an amount greater than a threshold from the depth histogram, calculating the distance between the stereo camera and the reference plane by weight transformation of the pixel group, and applying a coarse-to-fine computation for the disparity-map video.