Stereo Camera Obstacle Detection Using Feature Point Triangulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing obstacle detection systems using stereo cameras face challenges in processing images in real-time due to complex algorithms, which can impact driver and pedestrian safety.
Innovation Solution
An obstacle detecting apparatus that extracts feature points from stereo camera images, calculates triangles using Delaunay triangulation, and determines normal directions to detect obstacles based on the camera's photographing direction, reducing computational load and improving detection speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a complex algorithm is used to detect objects near the vehicle using a stereo camera, then the detection accuracy is improved, but the processing time increases and real-time processing becomes difficult
Solution Approach 1:
The patent segments the image processing task by extracting only feature points (edges, corners, contours) rather than processing all pixels. The block matching algorithm is applied only to these extracted feature points, dividing the computational workload into selective processing steps that maintain detection accuracy while reducing overall processing time
Solution Approach 2:
The patent extracts only the essential elements (feature points with high similarity values) from the complete image data. By taking out and processing only these critical feature points rather than the entire image, the system achieves real-time processing capability while maintaining the accuracy needed for safe obstacle detection
2Measurement precision
If a complex algorithm is used to detect objects near the vehicle using a stereo camera, then the detection accuracy is improved, but the system complexity increases
Solution Approach 1:
The patent divides the complex object detection task into separate, manageable stages: feature point extraction, similarity calculation, block matching, and triangle formation. Each stage processes only the necessary data from the previous stage, reducing overall algorithm complexity while maintaining detection accuracy through systematic progression
Solution Approach 2:
The patent extracts and processes only the most relevant information (feature points with similarity >= reference value) from the complete image data. This selective extraction simplifies the algorithm by eliminating unnecessary processing of irrelevant pixels while preserving the critical information needed for accurate obstacle detection
Data Source
AI summary
The present invention relates to an obstacle detecting apparatus and an obstacle detecting method and an exemplary embodiment of the present invention provides an obstacle detecting apparatus, including: a stereo camera which photographs a front of a vehicle to generate a left image and a right image; an image matching unit which applies a block matching algorithm to the left image and the right image to extract a plurality of feature points having a similarity which is equal to or larger than a reference value and calculate a coordinate and a depth of the plurality of extracted feature points; a plane calculating unit which connects every three feature points of the plurality of feature points to calculate a plurality of triangles, based on the coordinate and the depth of the plurality of feature points; a normal calculating unit which calculates directions of normal of the plurality of triangles, based on the coordinate and the depth of three feature points corresponding to vertexes of the plurality of triangles; and an obstacle detecting unit which detects an obstacle in front of the vehicle based on a result of comparing a photographing direction of the stereo camera with the normal directions of the plurality of triangles.