Vehicle Obstacle Detection Using Cylindrical Images and TTC Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing optical detecting devices struggle to perform collision evaluation when a complete image of the detection subject is not captured by the camera.
Innovation Solution
The device includes an image converting portion that converts fisheye images into circular cylindrical images, a detection subject candidate image detecting portion for pattern matching, an optical flow calculating portion, outlier removing portions, a TTC calculating portion, a tracking portion, and a collision evaluating portion to assess the risk of collision even with incomplete image capture.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pattern matching is used to detect moving objects, then detection accuracy is improved, but the system cannot detect objects when a complete image is not captured
Solution Approach 1:
The system performs preliminary detection using pattern matching on captured images to identify candidate detection subjects. When a complete image is not available, the system has already established candidate objects from previous frames that can be tracked and evaluated for collision risk, enabling detection in incomplete image states.
Solution Approach 2:
The system transitions from relying solely on spatial image completeness to incorporating the time dimension through frame-by-frame tracking. By detecting candidates in one frame and tracking them across subsequent frames, the system can maintain detection capability even when individual frames are incomplete, effectively adding temporal dimensionality to the detection process.
2Measurement precision
If optical flow calculation is performed on the entire image, then motion detection accuracy is improved, but processing load increases
Solution Approach 1:
The system segments the optical flow calculation process by applying it only to regions containing detected candidate objects rather than the entire image. The optical flow calculating portion focuses computational resources on specific detection subject candidate images and their surrounding regions, significantly reducing processing load while maintaining motion detection accuracy for relevant objects.
Solution Approach 2:
The system applies different processing quality levels to different image regions. High-precision optical flow calculation is applied locally to regions containing detection candidates, while other regions receive minimal or no processing. This local quality approach maintains accuracy where needed while reducing overall computational burden.
3Measurement precision
If pattern matching is performed on all detected objects, then detection completeness is improved, but processing time increases
Solution Approach 1:
The system extracts only the essential pattern matching process for detecting candidate objects, separating it from subsequent tracking and collision evaluation processes. By taking out the pattern matching step as a distinct, efficient operation that identifies candidates without requiring complete analysis of all image features, the system achieves detection completeness while reducing overall processing time.
Data Source
AI summary
An obstacle detecting device includes: an image converting portion for converting, into a circular cylindrical image, an image captured by a camera installed on a vehicle; a detection subject candidate image detecting portion for detecting a detection subject candidate image through pattern matching; an optical flow calculating portion for calculating an optical flow; an outlier removing portion for removing an optical flow that is not a detection subject; a TTC calculating portion for calculating a TTC (TTCX, TTCY); a tracking portion for generating a region of the detection subject on the circular cylindrical image by tracking the detection subject candidate; and a collision evaluating portion for evaluating whether or not there is the risk of a collision, wherein the optical flow calculating portion calculates the optical flow based on the detection subject candidate image and the region.