Motion Vector Detection Merging Depth and Image Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion vector detection methods struggle to accurately detect motion vectors in images with large brightness changes or flat/dark portions, leading to incorrect detection even with previously predicted vectors.
Innovation Solution
A motion vector detection apparatus comprising a first unit that detects vectors based on self-motion data and depth image data, a second unit that detects vectors based on captured image data, and a merging unit that combines these vectors using predicted errors and reliability calculations, enhancing accuracy by merging candidate vectors with previously detected vectors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If motion vector detection is performed using only captured image data, then the detection process is simple, but detection accuracy deteriorates in regions with large brightness changes or flat/dark portions
Solution Approach 1:
The patent merges motion vector detection results from two different approaches: (1) detection based on captured image data alone, and (2) detection based on depth image data and self-motion information. By combining these multiple detection results through a merging unit that calculates reliability degrees, the system achieves higher detection accuracy in challenging regions while managing complexity through systematic integration.
2Measurement precision
If multiple motion vector detection methods are combined, then detection accuracy improves, but processing complexity increases
Solution Approach 1:
The patent introduces a merging unit as an intermediary component that systematically combines motion vector detection results from multiple sources. This merging unit calculates reliability degrees for each detection result and performs weighted merging, providing a structured approach that manages processing complexity while achieving improved detection accuracy through multi-source integration.
Solution Approach 2:
The system dynamically adjusts processing parameters including reliability degree calculations and merging weights based on image characteristics and detection conditions. By changing parameters adaptively rather than using fixed processing, the system optimizes the balance between accuracy improvement and complexity management for different imaging scenarios.
3Reliability
If motion vector detection relies on image features alone, then processing is straightforward, but reliability deteriorates in flat or dark image regions
Solution Approach 1:
The merging unit acts as an intermediary that integrates depth image information and self-motion data with captured image data. This intermediary component calculates reliability degrees by considering multiple information sources, thereby improving detection reliability in flat or dark regions where traditional image-feature-based methods fail, while maintaining structured processing through the merging mechanism.
Data Source
AI summary
Provided is a first motion vector detection unit that detects a motion vector on a basis of self-motion data and depth image data. A second motion vector detection unit that detects a motion vector on a basis of captured image data. A motion vector merging unit that merges the motion vector detected by the first motion vector detection unit with the motion vector detected by the second motion vector detection unit.