Sensor Data Filtering for Stationary Roadside Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated driving vehicles face challenges in efficiently detecting, tracking, and estimating stationary roadside objects like guardrails due to the overwhelming amount of data generated by vehicle-mounted sensors, which requires effective data filtering and processing to provide accurate information for navigation and safety.
Innovation Solution
A method that consolidates, classifies, and pre-sorts sensor data points from multiple vehicle-mounted sensors to identify stationary objects on either side of the road, applying data fitting algorithms to estimate their size, shape, and location, thereby reducing data complexity and enhancing object tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data from multiple vehicle-mounted sensors is processed directly without filtering, then complete object detection information is available, but data processing complexity and computational load increase significantly
Solution Approach 1:
The patent applies preliminary action by performing consolidation, classification, and pre-sorting of sensor data points before applying data fitting algorithms. This filtering process reduces the data volume and complexity upfront, making subsequent processing more efficient while maintaining detection accuracy for stationary roadside objects
Solution Approach 2:
The patent segments the processing of sensor data by separating data points into different categories (stationary vs. moving objects) and organizing them into structured formats. This segmentation allows the system to handle different types of objects with appropriate processing methods, reducing overall computational complexity
2Measurement precision
If all sensor data points are processed through data fitting algorithms, then accurate object estimation is achieved, but processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary consolidation and classification of data points before applying data fitting algorithms. By pre-organizing the data and identifying stationary objects in advance, the system reduces the amount of data that requires computationally intensive fitting operations, thereby maintaining accuracy while reducing processing time
Solution Approach 2:
The patent applies partial action by selectively applying data fitting algorithms only to consolidated data points that represent stationary roadside objects, rather than processing all sensor data points. This selective approach maintains measurement precision for critical objects while reducing overall processing time
3Productivity
If sensor data is filtered to reduce data volume, then processing efficiency improves, but risk of losing important object information increases
Solution Approach 1:
The patent performs preliminary consolidation that groups multiple data points representing the same object into single consolidated data points. This consolidation reduces data volume while preserving object information by maintaining representative characteristics of the original data points
Solution Approach 2:
The patent implements feedback mechanisms that allow the system to evaluate and adjust the filtering process. By monitoring detection results and processing efficiency, the system can optimize the filtering parameters to maintain information completeness while achieving processing efficiency goals
Data Source
AI summary
A system and method for selectively reducing or filtering data provided by one or more vehicle mounted sensors before using that data to detect, track and/or estimate a stationary object located along the side of a road, such as a guardrail or barrier. According to one example, the method reduces the amount of data by consolidating, classifying and pre-sorting data points from several forward looking radar sensors before using those data points to determine if a stationary roadside object is present. If the method determines that a stationary roadside object is present, then the reduced or filtered data points can be applied to a data fitting algorithm in order to estimate the size, shape and/or other parameters of the object. In one example, the output of the present method is provided to automated or autonomous driving systems.