Vehicle Guidance Using Spherical Depth Maps for Moving Object Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle guidance systems, particularly for unmanned aerial vehicles, face limitations in detecting and navigating around moving objects due to resource constraints such as processing and storage requirements.
Innovation Solution
A system comprising an image sensor, a motion and orientation sensor, and hardware-implemented processors, which detects moving objects by predicting the vehicle's path and the objects' locations, determining potential intersections, and adjusting optical flow to account for changes in the field of view.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system processes depth information for the environment to detect moving objects, then the detection capability improves, but the processing and storage resource costs increase
Solution Approach 1:
The system segments the environment into static and dynamic components by comparing current sensor data with predicted data, processing only the dynamic portions that contain moving objects rather than the entire environment, thereby reducing overall processing and storage requirements while maintaining detection capability
Solution Approach 2:
The system performs preliminary processing by generating predicted static environment data before actual detection, allowing it to subtract this prediction from current sensor data and only process the residuals containing moving objects, thus reducing computational resources needed for full environment processing
2Use of energy by moving object
If the system identifies only static objects to conserve resources, then processing costs decrease, but the ability to detect moving objects is lost
Solution Approach 1:
The system dynamically adjusts its detection approach by using optical flow analysis to identify regions with motion, allowing it to focus processing resources only on areas where moving objects are present rather than uniformly processing the entire field of view, thus balancing resource usage with moving object detection capability
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.