Object Detection Apparatus Horizontal Edge Disparity Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current object detection systems using stereo cameras struggle to accurately detect objects, particularly vehicles, due to low precision in detecting disparity at horizontal edges, leading to incorrect recognition of multiple objects as a single entity.
Innovation Solution
An object detection apparatus and method that generates a disparity image and uses a map generator to create a frequency profile of disparity values, an isolated area detector to identify isolated areas, and an object detector to divide these areas and detect objects based on the profile, improving the detection of horizontal edges and preventing multiple vehicles from being recognized as a single object.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If block matching method is used to detect disparity, then disparity at vertical edges is detected with high precision, but disparity at horizontal edges is detected with low precision
Solution Approach 1:
The patent segments the disparity detection process into multiple stages: first detecting edges using block matching, then separately detecting horizontal edges using template matching, and finally integrating these results. This segmentation allows each method to operate optimally on its strength while compensating for weaknesses through combination.
Solution Approach 2:
The patent merges block matching results with template matching results to create a comprehensive edge detection system. By combining the high-precision vertical edge detection capability of block matching with the horizontal edge detection capability of template matching, the system achieves adaptability to both edge directions while maintaining precision.
2Adaptability or versatility
If stereo imaging is used to detect objects, then three dimensional space detection is enabled, but multiple objects may be recognized as a single object due to horizontal edge detection failures
Solution Approach 1:
The patent segments the object detection process into multiple stages: disparity image generation, edge detection (both vertical and horizontal), and object recognition. This segmentation allows the system to address horizontal edge detection failures by adding a dedicated template matching stage that specifically targets horizontal edges, thereby improving overall object detection precision while maintaining three-dimensional capability.
3Productivity
If block matching method is used for disparity detection, then processing speed is maintained, but detection accuracy for box-shaped objects is reduced
Solution Approach 1:
The patent applies partial action by using template matching only for horizontal edge detection rather than applying it to the entire image. This selective application maintains processing efficiency while improving accuracy for box-shaped objects. The template matching is applied partially to the regions where horizontal edges are expected, balancing processing speed and recognition accuracy.
Data Source
AI summary
An object detection apparatus mountable to a moveable apparatus for detecting an object existing outside the moveable apparatus by capturing a plurality of images using a plurality of imaging devices mounted to the moveable apparatus and generating a disparity image from the captured images includes a map generator to generate a map indicating a frequency profile of disparity values correlating a horizontal direction distance of the object with respect to a movement direction of the moveable apparatus, and a distance to the object in the movement direction of the moveable apparatus based on the disparity image, an isolated area detection unit to detect an isolated area based on the frequency profile, an isolated area divider to divide the isolated area into two or more isolated areas based on the frequency profile in the isolated area, and an object detector to detect an object based on the divided isolated area.