Fisheye Camera Object Distance Determination via Virtual Plane Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle-mounted camera systems face challenges in accurately determining the distance of objects from the vehicle without relying on external sensors like radar or stereo cameras, which can be costly and complex.
Innovation Solution
The system employs fisheye cameras to capture 360-degree surroundings, projects images onto a virtual bowl-shaped surface, and uses a Kalman filter to determine object distance by analyzing the object's contour on virtual planes, assuming the object is on the ground plane.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If external sensors like radar or stereo cameras are used to determine object distance, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent extracts the distance measurement function from external sensors (radar, stereo cameras) and implements it using only the existing single-camera imaging system by analyzing object contours and their projection positions on virtual planes, thereby eliminating the need for additional sensors while maintaining measurement capability
Solution Approach 2:
The patent creates a virtual copy of the physical environment by projecting object contours onto virtual planes that represent different distances from the vehicle. By comparing the object's actual contour position with its projected position on multiple virtual planes at known distances, the system determines the object's actual distance without requiring physical distance measurement sensors
2Measurement precision
If external sensors like radar or stereo cameras are used to determine object distance, then measurement precision is improved, but cost increases
Solution Approach 1:
The patent makes the existing camera system multi-functional by enabling it to perform both image capture for visibility enhancement and distance measurement for safety features. The same camera hardware and processing system are used for both functions, eliminating the need for separate distance measurement sensors and reducing overall system cost
Solution Approach 2:
The imaging system serves itself by using its own captured images and processing capabilities to determine object distances. The system analyzes contours from its own images and uses virtual plane projections to calculate distances, making the system self-sufficient for both visualization and measurement functions without requiring external sensors
3Adaptability or versatility
If fisheye cameras are used to capture 360-degree surroundings, then adaptability is improved, but image distortion increases
Solution Approach 1:
The patent applies spherical projection geometry to create virtual planes that match the curved field of view of fisheye cameras. By defining virtual planes using spherical coordinate systems and projection math that accounts for the camera's wide-angle distortion characteristics, the system accurately maps distorted fisheye images to undistorted virtual plane representations, enabling precise distance measurement despite the inherent fisheye distortion
Data Source
AI summary
Technologies for determining a distance of an object from a vehicle include a computing device to identify an object captured in a fisheye image generated by a fisheye camera of the vehicle. The computing device projects a contour of the identified object on a selected virtual plane that is located outside the vehicle and selected from a predefined set of virtual planes based on a location of the identified object relative to the vehicle. The computing device identifies a bottom of the projected contour on the selected virtual plane and determines an intersection point of an imaginary line with a ground plane coincident with a plane on which the vehicle is positioned. The imaginary line passes through each of the identified bottom of the projected contour and the fisheye camera. The computing device determines a location of the identified object relative to the vehicle based on the determined intersection point and the identified bottom of the projected contour.