Image-Assisted Material Classification for Multipath-Aware Mobile Dimensioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Depth sensors in mobile devices capture point clouds of objects that include artifacts due to multipath reflections, leading to inaccurate object dimensioning.
Innovation Solution
A method and device that utilize a depth sensor and camera to capture simultaneous point clouds and images, identify adjacent surface materials, assess reflection intensities, and adjust handling actions based on multipath artifact detection to ensure accurate dimensioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If depth sensor captures point cloud data, then object dimensioning is enabled, but measurement precision deteriorates due to multipath reflection artifacts
Solution Approach 1:
The system performs preliminary material identification of adjacent surfaces using image data before processing depth data. By pre-identifying materials and their reflection characteristics, the system can predict and suppress multipath artifacts before they corrupt the dimensioning measurements, thus improving measurement precision
Solution Approach 2:
The system introduces an intermediary processing layer that uses camera images to identify materials and determine reflection intensities. This intermediary information mediates between the raw depth sensor data and the final dimensioning results, allowing the system to detect and suppress artifacts caused by multipath reflections from high-reflectivity surfaces
2Reliability
If material identification and reflection assessment are performed, then artifact suppression improves, but device complexity increases
Solution Approach 1:
The system merges the camera and depth sensor into a unified processing pipeline, where image data from the camera is used to identify materials and assess reflection intensities that directly inform the artifact suppression applied to depth data. This combining of multiple data sources into a coordinated processing flow improves reliability without proportionally increasing complexity
Solution Approach 2:
The system uses the camera's image data to automatically identify materials and determine reflection characteristics without requiring external input or manual configuration. This self-service approach allows the system to adapt to different environments and surfaces autonomously, improving reliability while keeping the interface simple
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
Accurately determines object dimensions by suppressing dimensioning when multipath artifacts are detected, improving measurement precision and reducing distortion.
Implementation Method 1
Depth sensors such as time-of-flight (ToF) sensors can be deployed in mobile devices such as handheld computers, and employed to capture point clouds of objects
Implementation Method 2
Point clouds generated by ToF sensors, however, may include artifacts caused by multipath reflections received at the sensor
Data Source
AI summary
A method in a computing device includes: capturing sensor data depicting a target object and an adjacent surface; detecting, from the sensor data, a first surface of the target object; identifying, from the sensor data, a material type of the adjacent surface; for a sample point on the first surface of the target object, determining a reflection intensity from the adjacent surface based on the material type determined from the sensor data; and selecting, based on the reflection intensity, a handling action from (i) determining an attribute of the target object and (ii) suppressing the determination of an attribute of the target object.