Swarm Vehicle Imaging for Near Real-Time HD Map Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for capturing street level intelligence at a city scale are either expensive or ineffective, with systems like Google Street View requiring costly equipment and data collected through volunteers often becoming stale quickly.
Innovation Solution
A street level intelligence platform comprising mapper vehicles with active data capture systems, including LiDAR and imaging devices, and swarm vehicles with passive data capture systems, which combine data using feature extraction and merging processes to create a real-time intelligence application with a user interface for fleet management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive equipment like LiDAR and active data capture systems are deployed, then measurement precision and data quality improve, but device complexity and cost increase
Solution Approach 1:
The system divides the fleet into two segments: mapper vehicles equipped with expensive active data capture systems (LiDAR, panoramic cameras) for high-precision baseline mapping, and swarm vehicles with simple passive capture systems (smartphones) for frequent updates. This segmentation allows each segment to use equipment appropriate to its function, reducing overall system complexity while maintaining high data quality where needed.
Solution Approach 2:
The system merges data from two different capture systems (active LiDAR/panoramic camera systems from mappers and passive smartphone cameras from swarms) through feature extraction and matching. This combining allows the system to achieve high measurement precision by using the accurate baseline from mappers while incorporating frequent updates from the simpler swarm system.
2Measurement precision
If dedicated mapper vehicles with active data capture systems are used, then data accuracy improves, but productivity and data freshness decrease due to lower fleet density
Solution Approach 1:
The system segments the data collection function between mapper vehicles that ensure accuracy through active capture systems and swarm vehicles that ensure freshness through their numbers and frequency. The swarm fleet's collective coverage compensates for the lower individual mapper density, maintaining both accuracy and freshness simultaneously.
Solution Approach 2:
The swarm vehicles create copies of the baseline map data captured by mappers, using their passive capture systems to record the same geographic areas. These copies are then used to update and refresh the master map, ensuring data freshness while maintaining the accuracy established by the mapper vehicles.
3Device complexity
If volunteer-based crowd sourcing is used, then device complexity and cost decrease, but measurement precision and data reliability worsen
Solution Approach 1:
The system introduces mapper vehicles with active data capture systems as an intermediary that creates a verified baseline map. This baseline serves as a reference against which swarm vehicle data is validated, ensuring that even though swarm vehicles use simple smartphone cameras, the final data maintains high reliability through the intermediary verification process.
Solution Approach 2:
The system implements feedback through feature matching between mapper and swarm data. The mapper data provides ground truth that validates and corrects swarm captures, creating a feedback loop that ensures measurement precision is maintained even though the primary data collection uses simple passive systems.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The solution provides cost-effective, real-time street level intelligence by combining data from active and passive systems, enhancing data accuracy and freshness, and enabling efficient fleet management while reducing operational costs.
Implementation Method 1
a LiDAR device, and at least one imaging device configured to actively capture data
Data Source
AI summary
Described are street level intelligence platforms, systems, and methods that can include a fleet of swarm vehicles having imaging devices. Images captured by the imaging devices can be used to produce and/or be integrated into maps of the area to produce high-definition maps in near real-time. Such maps may provide enhanced street level intelligence useful for fleet management, navigation, traffic monitoring, and/or so forth.