Spherical Depth Mapping for Moving-Object Vehicle Guidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle guidance systems, particularly for unmanned aerial vehicles, are limited by resource costs, such as processing and storage, which restrict the detection of moving objects and the processing of depth information, mainly focusing on static objects.
Innovation Solution
A system comprising an image sensor, motion and orientation sensors, and hardware-implemented processors that detect moving objects by generating visual and motion information, using optical flow adjustments to account for changes in the field of view, and generating spherical depth maps for collision avoidance and ego-motion estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system processes depth information for moving objects, then the detection capability is improved, but the processing and storage resource costs increase
Solution Approach 1:
The system segments the environment into static and dynamic components by comparing depth maps from different time points. Static objects are identified by matching depth values across frames, while only moving objects require full processing, reducing overall computational burden.
Solution Approach 2:
The system performs preliminary processing by generating depth maps and identifying static regions before detecting moving objects. By pre-processing the scene and separating static from dynamic elements, the system reduces the complexity of subsequent moving object detection.
2Reliability
If the system tracks moving objects in real-time, then the navigation capability is improved, but the processing speed requirements increase
Solution Approach 1:
The system uses periodic frame comparison at defined time intervals to detect moving objects. By processing depth maps at regular intervals rather than continuously, the system maintains navigation reliability while managing processing speed requirements.
Solution Approach 2:
The system creates simplified representations of the environment through depth maps and compares these copies over time to detect motion. This copying approach enables efficient real-time processing while maintaining accurate navigation capability.
3Measurement precision
If the system uses multiple sensors for comprehensive detection, then the detection accuracy is improved, but the device complexity increases
Solution Approach 1:
The system merges data from image sensors and depth sensors into unified depth maps. By combining multiple sensor inputs into a single processed representation, the system achieves comprehensive detection accuracy while managing device complexity through data integration.
Solution Approach 2:
The depth mapping system serves multiple functions including static object identification, moving object detection, and navigation. This multi-functionality reduces the need for separate dedicated systems, thereby managing device complexity while maintaining detection accuracy.
Data Source
AI summary
This disclosure relates to systems and methods for vehicle guidance. Stereo images may be obtained at different times using a stereo image sensor. A depth image may be determined based on an earlier obtained pair of stereo images. The depth image may be refined based on predictions of an earlier stereo image and a later obtained stereo image. Depth information for an environment around a vehicle may be obtained. The depth information may characterize distances between the vehicle and the environment around the vehicle. A spherical depth map may be generated from the depth information. Maneuver controls for the vehicle may be provided based on the spherical depth map.