3D Scene Mapping with Passive-Active Distance Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle technologies rely on expensive and hazardous LiDAR systems for generating 3D-maps, which are not feasible for mass production due to high costs and potential safety risks, and result in limited resolution due to crosstalk from multiple laser beams.
Innovation Solution
A system that generates 3D-maps using a combination of active and passive measurements, where passive image processing reduces the need for extensive laser scanning, allowing for high-resolution mapping with fewer and lower-energy laser beams, thereby minimizing exposure and crosstalk.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Length of stationary object
If LiDAR systems transmit high-energy laser beams to measure maximum range, then measurement range is improved, but safety risks to pedestrians and passengers increase
Solution Approach 1:
The system dynamically adjusts laser beam energy levels based on detected object types and distances. Passive measurements use low-energy beams for nearby objects to reduce safety risks, while active measurements use higher energy only when necessary for maximum range detection. This parameter adaptation resolves the contradiction between measurement range and safety.
Solution Approach 2:
The system performs passive measurements for all detected objects using low-energy beams, and selectively performs active measurements only for specific cases requiring maximum range detection. This partial application of high-energy beams reduces overall safety risks while maintaining measurement capability when needed.
2Area of stationary object
If LiDAR systems scan the entire environment with multiple laser beams, then complete 3D-map coverage is improved, but crosstalk between beams increases
Solution Approach 1:
The system segments the scene into regions requiring passive measurements and regions requiring active measurements. By dividing the measurement task and applying different measurement strategies to different segments, the system reduces beam crosstalk while maintaining comprehensive coverage.
Solution Approach 2:
The system introduces an intermediate passive measurement step before active measurement. This intermediary process identifies objects and their approximate locations, allowing active beams to be targeted more precisely and reducing the likelihood of crosstalk between simultaneous beams.
3Loss of information
If LiDAR systems use high numbers of laser beams for comprehensive scanning, then measurement completeness is improved, but energy consumption increases
Solution Approach 1:
The system implements periodic passive measurements at regular intervals to maintain measurement completeness. Active measurements are performed periodically only when changes in the scene warrant updated data, reducing overall energy consumption while preserving information completeness.
Solution Approach 2:
The system uses passive measurements to self-identify objects and their locations, eliminating the need for continuous active scanning. This self-service approach maintains measurement completeness by having the system monitor itself for changes, triggering active measurements only when necessary.
4Speed
If LiDAR systems transmit frequent high-energy laser beams, then real-time measurement capability is improved, but hazardous conditions for pedestrians increase
Solution Approach 1:
The system dynamically adjusts measurement frequency and energy levels based on real-time scene analysis. For stationary objects or areas with no detected changes, measurement frequency is reduced to minimize hazardous exposure. For moving objects or areas with detected changes, the system increases measurement frequency while maintaining appropriate energy levels to preserve real-time capability.
Solution Approach 2:
The system uses feedback from passive measurements to determine when active measurements are necessary. This feedback mechanism allows the system to maintain real-time measurement capability by triggering active measurements only when scene changes warrant them, rather than continuous high-energy scanning.
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
This approach enables cost-effective, high-resolution 3D-map generation with reduced energy consumption and safety risks, allowing for more efficient and widespread adoption of autonomous vehicles.
Implementation Method 1
acquire an image of a scene with a passive sensor
Implementation Method 2
perform active measurements in specific directions with an active sensor
Implementation Method 3
measuring a distance from some or all the classified objects
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
A method and apparatus for generating 3D-maps for acquiring three-dimensional (3D) maps are presented. The method includes analyzing at least one image acquired by a passive sensor to identify a plurality of objects in the at least one image; classifying the plurality of objects; determining, based on the classification, whether to passively measure a distance to each of the plurality of objects; passively measuring the distance to at least one of the plurality of objects based on the determination; actively measuring a distance to some of the plurality of objects, wherein the distance to one of the same of the plurality of objects is actively measured when the distance to the object cannot be passively measured; and generating a 3D map of a scene based on the distance measured to each of the plurality of objects.