Optical Flow Field Selection for Relative Movement Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the movement of a device relative to an object using digital image sequences face inaccuracies and high computational requirements, especially in estimating scaling changes and collision time, due to faulty assumptions and limited computing capacity in embedded systems.
Innovation Solution
The method computes optical flow fields from image pairs at different time intervals and selects suitable partial flow fields based on criteria such as overlap, signal-to-noise ratio, and quality measures to improve accuracy and reliability, focusing on a region of interest (ROI) to estimate the change in scale and movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If optical flow fields are computed from entire images to estimate scaling changes, then measurement precision is improved, but device complexity and computing power requirements increase
Solution Approach 1:
The patent divides the image into multiple regions of interest (ROIs) focused on the object of interest, computing optical flow fields only for these segmented regions rather than the entire image. This segmentation approach maintains measurement precision for the target object while significantly reducing the computational complexity and data processing burden.
Solution Approach 2:
The patent applies local quality by concentrating computational resources on specific local regions where the object of interest is detected, rather than uniformly processing the entire image. This allows high-precision optical flow estimation in the relevant regions while avoiding unnecessary computations in irrelevant areas, thus reducing overall device complexity.
2Measurement precision
If optical flow fields are computed at multiple time intervals to improve accuracy, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent performs preliminary object detection and region of interest identification before computing optical flow fields. By pre-identifying where the object of interest is located and defining the relevant ROIs, the system can then compute optical flow only for these pre-selected regions at multiple time intervals, improving accuracy without proportionally increasing processing time.
Solution Approach 2:
The patent computes optical flow fields at multiple time intervals only for the partial regions of interest rather than the entire image. This partial action approach provides sufficient accuracy for scaling change estimation while avoiding the excessive time consumption that would result from processing the complete image at all time intervals.
3Measurement precision
If movement segmentation is performed to select appropriate flow fields, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the image into regions of interest based on object detection, and then computes optical flow fields only for these segmented regions. This segmentation approach simplifies the movement segmentation process by pre-defining the relevant areas, reducing the computational intensity required for flow field selection while maintaining measurement precision.
Solution Approach 2:
The patent performs movement segmentation and optical flow computation only for the partial regions where the object of interest is detected, rather than analyzing the entire image. This partial action reduces the computational intensity and device complexity while still providing reliable flow field selection for the target object.
Data Source
AI summary
A method for determining a movement of a device relative to at least one object based a digital image sequence of the object recorded from the location of the device. The method includes computing a plurality of optical flow fields from image pairs of the digital image sequence; finding the position of an object in a partial image region in the most current image in each case and assigning the partial image region to the object; forming a plurality of partial optical flow fields from the plurality of optical flow fields; selecting a partial flow fields from the plurality of partial flow fields in accordance with at least one criterion to facilitate the estimation of a change in scale of the object; and estimating the change in scale for the at least one object using the assigned partial image region based on the selected partial flow field.