Multi-Sensor Object Detection via Feature Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object detection systems in autonomous vehicles face challenges in accurately detecting objects in varying environmental conditions due to the limitations of single-sensor data, such as image data from cameras or point cloud data from LiDAR/RADAR sensors.
Innovation Solution
A method and apparatus that utilize a feature-type selection model to determine the most suitable feature type for object detection by combining data from different sensors, such as cameras and LiDAR/RADAR sensors, to enhance detection accuracy across different environmental conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If single-sensor data is used for object detection, then the system complexity is reduced, but the detection accuracy deteriorates in varying environmental conditions
Solution Approach 1:
The patent combines data from multiple sensors (camera and LiDAR/RADAR) to perform object detection. The feature extraction unit extracts features from both sensor types, and the feature-type selection model selects the most appropriate features by considering both camera image data and LiDAR/RADAR point cloud data, thereby improving detection accuracy through multi-sensor fusion.
Solution Approach 2:
The patent dynamically selects the most suitable feature type for object detection by inputting extracted features into a feature-type selection model. The model outputs selection data that dynamically determines whether to use camera features, LiDAR/RADAR features, or both, allowing the system to adapt to varying environmental conditions and optimize detection accuracy in real-time.
2Measurement precision
If multiple sensors are combined for object detection, then the detection accuracy is improved, but the device complexity increases
Solution Approach 1:
The patent extracts features from sensor data using a feature extraction unit, then inputs these extracted features into a feature-type selection model. This extraction and selection process manages complexity by processing only the most relevant features rather than raw sensor data, reducing computational burden while maintaining high detection accuracy through multi-sensor fusion.
3Adaptability or versatility
If feature selection is performed based on environmental conditions, then the adaptability is improved, but the processing time increases
Solution Approach 1:
The patent performs preliminary feature extraction from both camera and LiDAR/RADAR sensors before the actual object detection. The extracted features are then fed into the feature-type selection model which pre-determines the optimal feature combination based on environmental conditions, allowing for efficient real-time decision-making without significant processing delays.
Data Source
AI summary
An object detection method and an object detection apparatus for detecting an object based on multi-features are provided. The object detection method includes: obtaining first-sensor data from a first sensor and obtaining second-sensor data from a second sensor, wherein the first sensor is a different type of sensor than the second sensor; extracting a first feature from the first-sensor data and extracting a second feature from the second-sensor data; determining a target feature-type by inputting the first and second features to a feature-type selection model which, based thereon, predicts the target feature-type; determining a target feature to be used for object detection according to the determined target feature-type; and determining an object detection result based on the determined target feature.