Vehicle Camera Distance Measurement Using Calibrated Visual Anchors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high cost of lidar-based systems prevents their widespread installation in vehicles, necessitating a cost-effective alternative for generating depth information in autonomous vehicles.
Innovation Solution
A method using a two-dimensional camera to obtain depth information by mapping anchors with known physical dimensions to their appearance in images, utilizing a calibration process involving a camera and an active sensor like lidar to generate a distance-to-appearance relationship, allowing for distance estimation without the need for a 3D camera.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lidar-based systems are used for depth information, then measurement precision is improved, but device cost increases significantly
Solution Approach 1:
The patent replaces expensive lidar systems with inexpensive 2D cameras to capture images. The system uses multiple 2D images taken from different positions to reconstruct 3D depth information, utilizing cheap imaging devices instead of costly active sensors.
Solution Approach 2:
The patent introduces a calibration object with known 3D coordinates as an intermediary between the 2D camera and the target scene. By capturing images of the calibration object and establishing coordinate transformations, the system enables depth measurement without direct 3D sensing hardware.
Solution Approach 3:
The patent transforms 2D image data into 3D depth information by capturing multiple images from different camera positions and performing coordinate transformations. This converts planar 2D measurements into spatial 3D measurements through mathematical reconstruction.
2Measurement precision
If 3D cameras are used for depth measurement, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the depth measurement task into multiple 2D image captures taken from different positions rather than using a single complex 3D camera. Each 2D image provides partial information that is later integrated through coordinate transformations to achieve complete 3D reconstruction.
Solution Approach 2:
The patent replaces complex 3D imaging hardware with simpler 2D camera hardware combined with computational methods. Instead of using specialized 3D sensors, the system uses standard 2D cameras with known intrinsic parameters and performs mathematical reconstruction to achieve depth measurement.
Data Source
AI summary
Systems, and method and computer readable media that store instructions for distance measurement, the method may include obtaining, from a camera of a vehicle, an image of a surroundings of the vehicle; searching, within the image, for an anchor, wherein the anchor is associated with at least one physical dimension of a known value; and when finding the anchor, determining a distance between the camera and the anchor based on, (a) the at least one physical dimension of a known value, (b) an appearance of the at least one physical dimension of a known value in the image, and (c) a distance-to-appearance relationship that maps appearances to distances, wherein the distance-to-appearance relationship is generated by a calibration process that comprises obtaining one or more calibration images of the anchor, and obtaining one or more distance measurements to the anchor.