Lane-Based Collision Object Detection Using Sub-Area Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle collision detection systems struggle to efficiently recognize and classify collision objects or discontinuities in a lane using image data, particularly when objects are of varying sizes and in the presence of noise.
Innovation Solution
The system uses a computing unit to detect the lane as an observation area, analyze partial areas, and classify non-lane objects as collision objects or discontinuities based on their size, determined by the number of adjacent sub-areas, and a dynamically defined threshold related to vehicle speed, image resolution, and noise levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all objects in the lane are detected and classified as collision objects or discontinuities, then the reliability of collision detection is improved, but the computing time and processing complexity increase
Solution Approach 1:
The image is divided into multiple sub-areas, and the detection process is segmented into sequential steps: first detecting the lane, then detecting non-lane objects, determining their size, and finally classifying them. This segmentation allows the system to process only relevant areas with appropriate computational effort for each task.
Solution Approach 2:
The patent applies partial action by implementing a size threshold criterion - only objects with sufficient size (determined by number of adjacent sub-areas) are classified as collision objects or discontinuities. Smaller objects are excluded from further processing, reducing computing time while maintaining reliable detection of relevant objects.
2Productivity
If a size threshold is applied to filter objects, then the processing efficiency is improved, but small collision objects may be missed
Solution Approach 1:
The size threshold is not fixed but dynamically adapted based on image resolution and vehicle speed. As image resolution changes or vehicle speed varies, the threshold adjusts accordingly, ensuring that small but relevant collision objects are not missed while maintaining processing efficiency across different operating conditions.
Solution Approach 2:
The patent changes the parameter of size threshold based on image resolution and vehicle speed. When image resolution is higher or vehicle speed is lower, smaller objects can be detected. This parameter adaptation maintains detection accuracy across varying conditions while preserving processing efficiency.
3Measurement precision
If the image resolution is increased to detect smaller objects, then the detection precision is improved, but the data processing load increases
Solution Approach 1:
The high-resolution image is segmented into sub-areas, and processing is performed selectively on regions containing detected objects rather than the entire image. This reduces the effective data volume processed while maintaining high detection precision for objects that matter.
Solution Approach 2:
The patent extracts only the relevant information (objects meeting size criteria) from the high-resolution image for further processing and classification. By taking out only the necessary data elements, the system maintains high detection precision while reducing the quantity of data that requires intensive processing.
4Adaptability or versatility
If dynamic threshold adjustment based on vehicle speed and image resolution is implemented, then the adaptability is improved, but the system complexity increases
Solution Approach 1:
The system adapts to different conditions by changing the size threshold parameter based on vehicle speed and image resolution. This single parameter adjustment provides versatility across varying operating conditions without requiring complex system architecture changes or multiple detection algorithms.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
Method for detecting collision objects (1) or discontinuities in an image, which image (2) is recorded by a camera (13), which vehicle (10) is moving on a lane (3), wherein the lane (3) is detected as the observation area (4) in the image by means of a processing unit, wherein objects outside the lane are detected by the processing unit by area-by-area scanning (5) of the observation area (4), wherein in the processing unit an object outside the lane is classified as a collision object (1) or as a discontinuity if this object outside the lane is detected in a number of adjacent or neighboring sub-areas greater than or equal to a threshold value, or in the processing unit an object outside the lane is classified as neither a collision object nor a discontinuity.if this object outside the lane is detected in a number of adjacent or neighboring sub-areas below a threshold value, which threshold value is set by the user or set by the processing unit.