Parallel Feature Extraction for VSLAM Location Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing location estimation systems using Visual Simultaneous Localization and Mapping (VSLAM) face a low update frequency of location information due to the sequential processing of feature value extraction and location estimation, which limits the frequency at which location information can be acquired.
Innovation Solution
The system performs feature value extraction processing in parallel with location estimation processing by utilizing multiple threads and adjusting the number of threads based on processing times and input images, allowing for simultaneous execution of these processes, thereby increasing the update frequency of location information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If feature value extraction processing and location estimation processing are performed sequentially, then processing accuracy is maintained, but the update frequency of location information becomes low
Solution Approach 1:
The feature value extraction processing is performed in advance on the next input image while the location estimation processing is still being performed on the current input image. This preliminary extraction of feature values allows the system to be ready for the next location estimation cycle, thereby increasing the update frequency without compromising processing accuracy.
2Productivity
If feature value extraction processing is performed on every input image, then location information update frequency increases, but processing load increases
Solution Approach 1:
The system performs feature value extraction processing on the next input image in parallel with location estimation processing on the current image. This partial parallel execution allows the system to prepare for the next update cycle without fully completing all processing tasks simultaneously, thereby increasing update frequency while managing processing load through controlled parallelism.
Data Source
AI summary
An exemplary aspect is a location estimation system, including: a feature value extraction processing unit that performs feature value extraction processing for extracting a feature value from an input image; and a location estimation processing unit that compares the extracted feature value with map information and performs location estimation processing for estimating a self-location based on a result of the comparison. While the location estimation processing unit is performing the location estimation processing corresponding to an input image input at a predetermined timing, the feature value extraction processing unit performs the feature value extraction processing on an input image input at a timing after the predetermined timing.