Vehicle Surroundings Monitoring via Grid-Based Stationary Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle radar systems face challenges in accurately detecting stationary objects due to varying signal characteristics and overlapping detection areas, leading to false detections and missed detections.
Innovation Solution
The system employs a grid map with dynamically set threshold values and occupancy probability parameters, using radar sensors to map stationary objects and update the grid map based on vehicle behavior, and expands the mapping area to compensate for signal variations, thereby improving detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radar signals are transmitted with predefined frame periods to detect outside objects, then the system can operate continuously to monitor the environment, but detection accuracy deteriorates due to varying signal characteristics and overlapping detection areas
Solution Approach 1:
The detection area is divided into multiple grid cells, with each cell having its own occupancy probability parameter. This segmentation allows independent threshold setting for each grid cell based on local signal characteristics, resolving the contradiction between continuous monitoring and detection accuracy by treating different spatial regions differently.
Solution Approach 2:
The system sets threshold values and occupancy probability parameters dynamically for each grid cell based on local conditions such as detection area overlap and signal characteristics. This local quality approach ensures that each region is evaluated with appropriate criteria, improving detection precision while maintaining continuous environmental monitoring.
2Ease of operation
If the radar system uses fixed threshold values for object detection, then the system operation is simple, but false detections and missed detections increase due to varying signal characteristics
Solution Approach 1:
The system dynamically adjusts threshold values and occupancy probability parameters based on vehicle behavior (acceleration, deceleration, steering) and detection conditions. This dynamic adaptation maintains detection reliability across varying operating conditions while automating the complexity, so the system remains easy to operate without requiring manual threshold tuning.
Solution Approach 2:
The system changes detection parameters (threshold values, occupancy probability) based on signal characteristics and detection area properties. By automatically adjusting these parameters according to local conditions, the system maintains high detection reliability without requiring complex manual configuration, preserving ease of operation.
3Area of stationary object
If the detection area is expanded to cover more regions, then the monitoring coverage is improved, but the complexity of processing overlapping detection areas increases
Solution Approach 1:
The expanded detection area is segmented into discrete grid cells, each processed independently with its own occupancy probability calculation. This segmentation reduces processing complexity by breaking down the large detection area into manageable units, while still maintaining comprehensive monitoring coverage across all regions.
Solution Approach 2:
The system applies detection processing to all grid cells within the detection area, including those with partial overlap. By processing each cell independently with appropriate threshold adjustments, the system handles the excessive coverage area without proportionally increasing complexity, as each cell is processed with standardized procedures.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy of stationary object detection by adapting to different signal characteristics and vehicle movements, reducing false positives and negatives, and ensuring reliable monitoring of the vehicle's surroundings.
Implementation Method 1
A radar for a vehicle refers to a device that detects an outside object within a detection area when the vehicle travels
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
An apparatus for monitoring the surrounding environment of a vehicle may include: a sensor unit including a plurality of detection sensors configured to detect an object outside the vehicle according to frames with a predefined period; and a control unit configured to extract a stationary object among outside objects detected through the sensor unit by using behavior information of the vehicle, map the extracted stationary object to a preset grid map, add occupancy information to each of grids constituting the grid map depending on whether the stationary object is mapped to the grid map, calculate an occupancy probability parameter indicating the probability that the stationary object will be located at each of the grids, from the occupancy information added to the grids within the grid map in a plurality of frames, and monitor the surrounding environment of the vehicle on the basis of the calculated occupancy probability parameter.