Optical Camera Stationary Object Detection False Positive Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional object avoidance systems in vehicles rely on costly radar or sonar sensors, and existing optical cameras, while capable of reducing costs, often result in false positive object identification, necessitating accurate and efficient stationary object detection using vehicular optical cameras.
Innovation Solution
A computer-implemented method and system that determines points of interest in images from a moving vehicle's optical camera, identifies multi-matches, distinguishes between stationary and moving objects, and initiates collision avoidance only for confirmed stationary objects, using components like point of interest identification, matching, motion determination, and collision avoidance modules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If optical cameras are used instead of radar or sonar sensors, then cost is reduced, but false positive object identification increases
Solution Approach 1:
The system segments the detection process into multiple independent stages: point of interest identification, multi-match verification across multiple images, and motion determination. This segmentation allows each stage to filter candidates progressively, reducing false positives while maintaining cost-effectiveness of optical camera usage.
Solution Approach 2:
The system implements feedback mechanisms where detection results from one image are used to verify and refine detections in subsequent images. The multi-match process compares points of interest across multiple frames, and motion determination uses feedback from previous frames to distinguish stationary objects from moving ones, thereby reducing false positives.
2Measurement precision
If multiple images are analyzed to reduce false positives, then detection accuracy improves, but processing time increases
Solution Approach 1:
The system performs preliminary point of interest identification in each image before conducting the more computationally intensive multi-match verification. By pre-identifying potential points of interest and only verifying those candidates across multiple images, the system reduces overall processing time while maintaining high detection accuracy.
Solution Approach 2:
The system applies partial action by performing multi-match verification and motion determination only on identified points of interest rather than processing entire images. This selective approach significantly reduces computational load and processing time while maintaining high detection accuracy for relevant objects.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method can comprise determining, by a system operatively coupled to a processor, points of interest comprising image coordinates in a set of images captured by an optical camera of a moving vehicle, determining, by the system, whether a multi-match exists in the set of images, in response to determining that the multi-match does not exist, rejecting, by the system, the points of interest, in response to determining that the multi-match exists, determining, by the system, whether the points of interest represent a false-positive determination of a stationary object, in response to determining that the points of interest are in motion and correspond to a false-positive, rejecting, by the system, the points of interest, and in response to determining that the points of interest are stationary and do not correspond to a false-positive, initiating, by the system, collision avoidance to avoid a stationary object corresponding to the points of interest.