Motion Estimation Averaged Cost Surface Block Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion estimation techniques for vehicle-side cameras struggle in adverse environmental conditions such as low-light or adverse weather, leading to corrupted video frames and inaccurate motion vectors due to noise, motion blur, and other artefacts, which degrade the block matching quality and produce a large number of outliers.
Innovation Solution
A method that determines cost surfaces for each block in a first image and its corresponding search region in a second image, calculates an averaged cost surface to reduce fluctuations, and derives motion vectors from this surface, allowing for reliable block matching operations even in challenging conditions. This method involves defining search regions based on predicted camera ego-motion and using a sliding window to weight individual cost surfaces, ensuring accurate motion estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If block matching algorithms are used for motion estimation in adverse environmental conditions, then the method is simple and computationally efficient, but the accuracy of motion vectors deteriorates due to noise, motion blur, and artefacts
Solution Approach 1:
The patent combines multiple individual cost surfaces into a single averaged cost surface by aggregating cost values from multiple blocks. This merging process smooths out local fluctuations and noise, making the global minimum more distinguishable and improving motion vector accuracy in adverse conditions while maintaining the simplicity of the block matching approach
Solution Approach 2:
The patent creates multiple copies of cost surface calculations for different blocks and then averages them. By computing cost surfaces for multiple blocks and combining them, the method produces a more reliable averaged cost surface that reduces the impact of noise and artefacts on motion estimation
2Productivity
If block matching is performed in adverse environmental conditions, then the process can be completed, but the quality of block matching deteriorates leading to a large number of outliers
Solution Approach 1:
The patent merges cost surface information from multiple blocks to create an averaged cost surface. This combination increases the reliability of motion estimation by reducing the impact of noise and artefacts that cause outliers in individual block matching operations
Solution Approach 2:
The patent applies different processing to different parts of the cost surface by calculating individual cost surfaces for multiple blocks and then averaging them. This local processing approach allows the method to maintain productivity while improving overall reliability through selective aggregation of cost information
Data Source
Figure 1
Figure 2
Figure 3a~3b
AI summary
The invention relates to a method for motion estimation between two images of an environmental region (9) of a motor vehicle (1) captured by a camera (4) of the motor vehicle (1), wherein the following steps are performed: a) determining at least two image areas of a first image as at least two first blocks (B) in the first image, b) for each first block (B), defining a respective search region in a second image for searching the respective search region in the second image for a second block (B) corresponding to the respective first block (B); c) determining a cost surface (18) for each first blocks (B) and its respective search region; d) determining an averaged cost surface (19) for one of the at least two first blocks (B) based on the cost surfaces (18); d) identifying a motion vector (v) for the one of the first blocks (B) describing a motion of a location of the first block (B) in the first image and the corresponding second block (B) in the second image. The invention also relates to a computing device (3), a driver assistance system (2) as well as a motor vehicle (1).