Map Update Task Prioritization Using Selective Road Image Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for collecting image data for road networks face challenges such as limited vehicle availability, high operational costs, and excessive data volume that exceeds upload and processing capabilities, making it difficult to maintain map accuracy and completeness.
Innovation Solution
A system utilizing image-capture devices in vehicles to passively collect data, combined with an image collection pipeline that applies a collection policy to selectively upload images based on factors like freshness, object detection, and segment importance, optimizing network bandwidth and back-end processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If image-capture devices passively capture images continuously while traversing road networks, then the quantity and coverage of collected image data increases, but the network bandwidth consumption and storage costs increase significantly
Solution Approach 1:
The system applies partial action by selectively collecting only a subset of captured images that meet specific criteria (new road segments, changes from historical data, high-priority segments) rather than uploading all captured images. This reduces network bandwidth consumption while maintaining sufficient data coverage for map updates.
Solution Approach 2:
The collection policy applies different selection criteria to different road segments based on their importance and characteristics. High-priority segments undergo more rigorous collection while lower-priority segments use simpler criteria, optimizing bandwidth usage according to local needs.
2Manufacturing precision
If image-capture devices upload all captured images, then the completeness and accuracy of map data improves, but the processing time and computational resources increase
Solution Approach 1:
The system processes only a partial subset of captured images that are deemed necessary based on collection policies, avoiding the computational overhead of processing all captured images while maintaining map data accuracy through targeted selection of meaningful images.
Solution Approach 2:
The collection policy is applied in advance to pre-determine which images should be collected and uploaded, allowing the system to prepare selection criteria and filters before actual image processing begins, thereby reducing real-time processing time.
3Quantity of substance
If the system collects images from all road segments uniformly, then the coverage and completeness of map data improves, but the cost and complexity of the collection system increases
Solution Approach 1:
The system implements differentiated collection strategies for different road segments based on their importance, traffic patterns, and historical data availability. This allows comprehensive coverage while simplifying the collection process for lower-priority segments and applying more rigorous processes only where necessary.
Solution Approach 2:
The collection policy framework serves multiple functions simultaneously: it filters images by quality, prioritizes segments by importance, manages bandwidth consumption, and ensures comprehensive coverage. This multi-functional approach reduces overall system complexity by consolidating multiple control mechanisms into a single policy-based system.
Data Source
AI summary
Examples disclosed herein involve a computing system configured to (i) receive image data captured by an image-capture device; (ii) based on the received image data, generate a set of map update tasks that each define a respective activity for evaluating whether to update a map; (iii) use a multi-factor prioritization scheme to prioritize the set of map update tasks; (iv) assign at least a subset of map update tasks from the set of map update tasks to one or more curators in accordance with the prioritization of the set of map update tasks; (v) receive, from a client station associated with a given curator via a network-based communication path, data defining feedback from the given curator regarding a given map update task; and (vi) update the map based on the received feedback.