Multi-Sensor Object Detection Fusion for Vehicle Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems face challenges in accurately and reliably detecting external objects using sensor data, particularly in varying conditions.
Innovation Solution
A vehicle control apparatus and method that utilizes multiple sensors to obtain data, which is then processed using neural network models to accurately detect external objects. The system selects and combines data from different sensors based on reliability and distance criteria to improve detection accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple sensors are used to detect external objects, then detection reliability is improved, but device complexity increases
Solution Approach 1:
The patent combines data from multiple sensors (LiDAR, camera, radar) through data fusion techniques to detect external objects. The processor integrates sensor data, selects relevant features, and generates fused detection results, achieving improved reliability while managing system complexity through systematic data integration
Solution Approach 2:
The detection process is divided into distinct stages: individual sensor data acquisition, feature extraction from each sensor, selective feature selection based on reliability metrics, and final fusion. This segmentation allows each component to be optimized independently while maintaining overall system reliability
2Measurement precision
If neural network models are used to process sensor data, then detection accuracy is improved, but processing time increases
Solution Approach 1:
The system applies partial processing by selecting only the most reliable and relevant features from sensor data before feeding them to neural network models. The processor evaluates data reliability metrics and selects subsets of features, reducing the input dimensionality and processing time while maintaining detection accuracy
Solution Approach 2:
The system performs preliminary feature extraction and reliability assessment before neural network processing. By pre-processing sensor data to identify and select high-quality features in advance, the system reduces the computational burden on neural networks and accelerates overall processing time
3Measurement precision
If data from multiple sensors is combined, then detection accuracy under various conditions is improved, but data processing complexity increases
Solution Approach 1:
The system applies different processing strategies to different sensor data based on their individual characteristics and reliability. Each sensor's data is processed according to its specific quality metrics, with selective feature extraction tailored to each sensor type, rather than applying uniform processing to all data
Solution Approach 2:
The system dynamically adjusts processing parameters based on data reliability metrics and environmental conditions. The processor selects features and adjusts fusion weights according to measured data quality, enabling adaptive processing that maintains accuracy while managing complexity through parameter optimization
Data Source
AI summary
A vehicle control apparatus includes a first sensor, a second sensor, a processor, and a memory storing first and second neural network models. The processor is configured to obtain first object data for predicting information related to the external object based on entering the first sensor data into the first neural network model, obtain second object data for predicting information related to the external object based on entering the second sensor data into the first neural network model the first object data or the second object data as input data to be entered into the second neural network model, and output data including a final location of the external object or a final type of the external object based on entering the input data into the second neural network model.