Dual Sensor Localization via wFOV and High-Resolution Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Standard image localization methods face challenges in achieving high accuracy and resolution, particularly when features are far from the camera, leading to trade-offs in distance and precision, and are limited by the availability of positioning systems like GPS in certain environments.
Innovation Solution
A method involving a wide field of view (wFOV) image analysis to identify predefined features, guiding the adjustment of a high resolution image sensor to capture detailed images, and computing a high accuracy location based on the correlation between the wFOV and high resolution image sensors, which can be used to control object movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If a standard image sensor is used to capture images of distant features, then the field of view is sufficient to locate features, but the image resolution and localization accuracy deteriorate
Solution Approach 1:
The system divides the imaging task into two segments: a wFOV image sensor captures the broad scene to identify candidate features, while a separate high-resolution image sensor captures detailed images of selected features. This segmentation allows each sensor to be optimized for its specific function, resolving the contradiction between field of view and resolution.
Solution Approach 2:
The system transitions from a single two-dimensional image plane to a multi-dimensional sensing approach by incorporating both a wFOV sensor and a high-resolution sensor with different optical characteristics. This dimensional expansion in the sensing space enables simultaneous coverage of broad area and fine detail.
2Measurement precision
If a high resolution image sensor is used to capture distant features, then the image resolution improves, but the field of view becomes too narrow to locate features efficiently
Solution Approach 1:
The wFOV image sensor performs a preliminary action by capturing the broad scene and identifying candidate features before the high-resolution image sensor is activated. This preliminary localization step guides the subsequent high-resolution imaging, ensuring the narrow field of view sensor is pointed at the correct target.
Solution Approach 2:
The wFOV image sensor acts as an intermediary that bridges the gap between the broad environmental context and the detailed feature measurement. It provides the guiding information needed to position the high-resolution sensor, mediating between the two opposing requirements.
3Adaptability or versatility
If GPS positioning systems are used for location determination, then global coverage is achieved, but availability is lost in certain environments like urban canyons and indoors
Solution Approach 1:
The system replaces the GPS satellite-based electromagnetic positioning system with a visual-mechanical localization approach using image sensors and feature matching. This substitution enables operation in environments where GPS signals are blocked, such as urban canyons and indoor spaces, by using visual features as the positioning basis.
4Measurement precision
If multiple high resolution image sensors are used simultaneously to capture the entire scene, then the localization accuracy improves, but the system complexity and computational load increase significantly
Solution Approach 1:
The system segments the imaging resources into one wFOV sensor and one high-resolution sensor, rather than using multiple high-resolution sensors. This segmentation reduces hardware complexity while achieving the same goal of accurate localization through coordinated use of the two sensors.
Solution Approach 2:
Instead of capturing the entire scene with high resolution (which would require multiple sensors), the system uses partial action by having the high-resolution sensor capture only the specific region of interest identified by the wFOV sensor. This reduces the total data volume and computational requirements while maintaining localization accuracy.
Data Source
AI summary
There is provided a computer implemented method of computing a location of an object, comprising: accessing a wide field of view (wFOV) image captured by a wFOV image sensor located relative to an object, analyzing the wFOV image to identify a predefined feature, wherein the predefined feature indicates a low accuracy location of the object, capturing a high resolution image by a high resolution image sensor located relative to the object, the high resolution image depicting the predefined feature, and computing a high accuracy of location of the object according to an analysis of the predefined feature and according to a correlation between a location and orientation of the wFOV image sensor and the high resolution image sensor.