Vehicle Sensor Timing Control for Occlusion-Aware 3D Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Street-level images often suffer from obstructed views due to obstacles like vegetation, vehicles, and pedestrians, which can result in incomplete 3D models when used for scene reconstruction.
Innovation Solution
A method and system for controlling sensors on a moving vehicle to capture data based on determined timing characteristics, including rate of capture and trigger locations, to overcome obstacles and ensure comprehensive data collection, using image and location sensors mounted on a vehicle to identify targets of interest and classify occluders.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If street-level images are captured at a fixed rate, then the capture system is simple to operate, but obstacles like vegetation and vehicles obstruct views and create incomplete 3D models
Solution Approach 1:
The patent implements dynamic capture rate adjustment based on detected obstacles and target importance. The system transitions from fixed-rate capture to variable-rate capture, increasing capture frequency when obstacles are detected and decreasing it when views are clear, thereby improving 3D model completeness while managing system complexity through adaptive control
Solution Approach 2:
The system uses feedback from obstacle detection algorithms and 3D model completeness assessment to continuously adjust capture parameters. Sensors detect obstacles in real-time, and this information feeds back to modify capture rates, creating a closed-loop system that improves reliability through continuous optimization
2Reliability
If the sensor capture rate is increased to overcome obstacles, then more complete data is captured, but energy consumption and data processing requirements increase
Solution Approach 1:
The patent applies different capture rates to different spatial regions and targets based on their importance and occlusion status. Critical targets with heavy occlusion receive higher capture rates, while clear targets use lower rates, optimizing energy usage by concentrating resources where most needed rather than uniformly across all sensors
Solution Approach 2:
The system dynamically changes capture parameters (frame rate, resolution, trigger locations) based on real-time conditions. When obstacles are detected, parameters are adjusted to capture more frequent or higher-quality data; when conditions are favorable, parameters are relaxed to reduce energy consumption and processing load
3Manufacturing precision
If all captured data is processed to create 3D models, then model accuracy is maximized, but processing time and computational resources increase
Solution Approach 1:
The patent extracts and processes only the most valuable captured data for 3D model construction. By identifying critical targets and occluded regions, the system selectively processes data from these areas while discarding or storing less important data, thereby maintaining model accuracy while significantly reducing processing time and computational resource requirements
Solution Approach 2:
The system applies partial processing to the full dataset by focusing computational resources on critical portions of the scene. Rather than uniformly processing all captured images at maximum quality, it applies enhanced processing only where needed to achieve sufficient model accuracy, reducing overall processing time while maintaining essential model fidelity
Data Source
AI summary
The disclosure provides for a method of controlling one or more sensors on a moving vehicle that is executable by one or more computing devices. The one or more computing devices may detect a first surface at a first location and a second surface at a second location using the one or more sensors. The second surface may be classified as a target of interest. Then the one or more computing devices may determine one or more timing characteristics of the one or more sensors based on a pose or motion of the one or more sensors relative to the first location of the first surface and the second location of the second surface. Then, the one or more computing devices may control the one or more sensors to capture data according to the determined one or more timing characteristics.