Polarization Road Plane Mapping for Autonomous Local Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods using polarized images cannot recognize distances to objects, making it impossible to directly generate a local map for autonomous movement of mobile objects.
Innovation Solution
An information processing apparatus that detects the normal direction of a plane constituting a movement-enabling region using polarized images, identifies a point on this plane, and reconstructs the plane to generate an environmental map, enabling the creation of a local map for autonomous navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If normal direction information is obtained from polarized images, then the normal direction of surfaces can be detected, but distance information cannot be obtained
Solution Approach 1:
The patent combines normal direction information from polarized images with depth map information from other sensors (such as stereo cameras or time-of-flight sensors) to create a comprehensive local map. The normal vectors from polarized images are integrated with depth data, merging two different types of information to achieve both surface orientation and distance recognition simultaneously.
2Measurement precision
If only normal direction information from polarized images is used, then surface orientation can be recognized, but a complete local map cannot be generated
Solution Approach 1:
The patent uses depth map information as an intermediary element that bridges the gap between normal direction detection and local map generation. The depth map serves as a mediator that provides distance information, which when combined with normal direction vectors, enables the construction of a complete three-dimensional local map without requiring polarized images alone to perform this function.
3Loss of information
If polarized images are used for object recognition, then normal directions can be obtained, but three-dimensional position information cannot be derived
Solution Approach 1:
The patent transitions from two-dimensional normal direction vectors obtained from polarized images to three-dimensional position information by integrating with depth map data. This dimensionality change allows the system to utilize the orientation information from polarized images while adding the third dimension of depth information from the depth map, achieving complete three-dimensional spatial understanding.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables the recognition of a plane in a three-dimensional space, allowing for the generation of a local map and facilitating autonomous movement by integrating distance measurements with normal direction information from polarized images.
Implementation Method 1
a polarization camera configured to acquire polarized images in multiple polarizing directions
Data Source
AI summary
An information processing apparatus capable of detecting a plane constituting a movement-enabling region. A normal direction of a plane constituting a road surface is detected on the basis of polarized images in multiple polarizing directions acquired by a polarization camera. A laser ranging sensor measures a distance to a point on the road surface so as to measure a position of the point. The plane constituting the road surface is identified on the basis of information regarding the normal direction of the plane constituting the road surface and information regarding the position of the point on the road surface.