3D TOF Z-Plane Detection for Accurate Box Dimensioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing time-of-flight (TOF) imaging systems struggle with aligning their angular orientation to the natural 'up' and 'down' directions in man-made environments, leading to inefficiencies in measuring box dimensions, which are often time-consuming and limited to specific lighting conditions.
Innovation Solution
A method and system for identifying Z-planes in an environment using a TOF sensor, reducing unknown extrinsic camera calibration parameters from six to three by determining roll and pitch angles, and filtering TOF data to enhance accuracy under various lighting conditions, enabling precise box dimensioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual alignment with the environment is required for box dimensioning, then measurement accuracy can be maintained, but the operation becomes time-consuming and cumbersome
Solution Approach 1:
The system automatically identifies Z-planes and performs coordinate system transformation without requiring manual user alignment or intervention. The TOF imaging system self-calibrates by detecting horizontal surfaces and computing basis vectors, eliminating the need for users to manually align the device while maintaining measurement accuracy.
2Adaptability or versatility
If TOF imaging is used in outdoor or varying lighting conditions, then versatility is improved, but sunlight noise and lighting vulnerabilities increase
Solution Approach 1:
The system converts the harmful effect of sunlight noise into a beneficial filtering opportunity. By detecting Z-planes and computing basis vectors from the TOF data, the system creates a reference frame that allows it to distinguish between valid surface reflections and sunlight interference, effectively using the noise problem to improve robustness through adaptive filtering.
Solution Approach 2:
The system changes the operational parameters by transforming the coordinate system based on identified Z-planes. This parameter transformation allows the system to maintain accurate measurements regardless of lighting conditions, as the basis vectors are computed from the actual scene geometry rather than being fixed or assumed.
3Measurement precision
If fixed frames of reference are used for dimensioning, then measurement consistency is maintained, but the system becomes limited to specific settings
Solution Approach 1:
The system transitions from a fixed, static reference frame to a dynamic reference frame that automatically adapts to the current environment. By continuously identifying Z-planes and computing basis vectors from the actual scene, the coordinate system transforms to match the environment's orientation, enabling consistent measurements across diverse settings without requiring predefined configurations.
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
Facilitates efficient and accurate measurement of box dimensions in diverse lighting conditions, reducing noise interference and simplifying the alignment process, thus enhancing usability and precision in box dimensioning applications.
Implementation Method 1
three-dimensional time-of-flight imaging
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
A sensor system that obtains and processes time-of-flight data (TOF) is provided. A TOF sensor obtains raw data describing various surfaces. A processor applies an averaging filter to the raw data to smooth the raw data for increasing signal-to-noise ratio (SNR) of flat surfaces represented in the raw data, performs a depth compute process on the raw data, as filtered, to generate distance data, generates a point cloud based on the distance data, and identifies the Z-planes in the point cloud.