Radar-Camera Object Fusion Filtering for Erroneous Detections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object detection systems using radar and camera sensors are prone to erroneous fusion object outputs due to erroneous detection by the radar, which cannot be effectively prevented by existing technologies.
Innovation Solution
An object detection device that includes a radar erroneous detection determination unit to identify potentially erroneous radar detections, a fusion processing unit to integrate reliable sensor data, and a radar erroneous detection removal unit to eliminate erroneous fusion objects, ensuring accurate object detection by validating data from both radar and a second sensor.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor fusion technology is used to combine radar and camera information for object detection, then detection accuracy is improved, but erroneous detection from radar can cause erroneous fusion object output
Solution Approach 1:
The system performs preliminary detection by both radar and camera before fusion. The radar detects objects in advance and the camera captures images, allowing the system to prepare for potential fusion while maintaining the ability to verify detections before final output, thus preventing erroneous fusion object output.
Solution Approach 2:
The system uses feedback mechanisms where the camera detection results are used to verify radar detections. When the camera fails to detect an object that radar has detected, the system receives feedback to adjust radar parameters or filter out potential erroneous detections, improving reliability while maintaining detection accuracy.
2Area of stationary object
If radar detection is used for long-distance object detection, then detection range is extended, but erroneous detection occurs more frequently
Solution Approach 1:
The system merges radar detection results with camera detection results. The radar provides long-distance detection capability while the camera provides verification. By combining both detection methods, the system extends effective detection range while improving reliability through mutual verification, reducing erroneous detections at long distances.
Data Source
AI summary
This object detection device includes: a radar erroneous detection determination unit which sets, as true, a radar erroneous detection suspicion flag for radar detected object information determined to be suspected as erroneous detection; a fusion processing unit which outputs fusion object information on the basis of second sensor detected object information and the radar detected object information acquired from the radar erroneous detection determination unit; and a radar erroneous detection removal unit which removes fusion object information determined to be suspected as erroneous detection. When a fusion object is determined to be an object detected by only a radar, the fusion processing unit sets a single-sensor detection flag for the fusion object information, as true. The radar erroneous detection removal unit removes the fusion object information for which the radar erroneous detection suspicion flag is true and the single-sensor detection flag is true.