LIDAR Object Classification Using Temporal Reflection Signatures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current LIDAR systems for autonomous vehicles face challenges in accurately identifying and classifying objects, especially under varying environmental conditions like rain, fog, darkness, and bright light, due to limitations in illumination power and error-prone distance-based object identification methods.
Innovation Solution
The system improves object identification and classification by using temporal distortions in reflection signals to detect surface angles and reflectivity fingerprints, allowing for more precise classification of objects based on spatial and reflectivity relationships, including license plate detection, using a processor to control light sources and sensors to scan and analyze the environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Length of stationary object
If LIDAR illumination power is increased to detect far-away objects, then detection range is improved, but eye safety is compromised
Solution Approach 1:
The patent changes the wavelength parameter of the LIDAR system to 1550 nm, which is absorbed by the cornea and lens rather than reaching the retina. This parameter change allows higher illumination power to be used safely, thereby extending detection range without compromising eye safety
2Device complexity
If object identification is based solely on distance information from reflected pulses, then system complexity is reduced, but identification accuracy deteriorates
Solution Approach 1:
The patent adds temporal dimension to object identification by analyzing temporal distortions in reflected pulses. Instead of relying solely on distance information, the system measures surface angles and reflectivity fingerprints through temporal analysis, creating a multi-dimensional identification approach that significantly improves accuracy
3Measurement precision
If multiple detection parameters are analyzed to improve object classification, then identification accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary analysis of temporal distortions during the scanning process itself. By extracting surface angle and reflectivity information from the temporal characteristics of reflected pulses in real-time, the system prepares classification data during data acquisition, reducing the need for extensive post-processing and minimizing overall processing time
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 and efficiency of object detection and classification, enabling reliable navigation in diverse conditions by utilizing temporal distortions and reflectivity patterns, improving the system's ability to identify vehicles and other objects with higher precision.
Implementation Method 1
A laser is one example of a light source that can be used in a LIDAR system
Implementation Method 2
measuring distances to objects by illuminating objects with light and measuring the reflected pulses with a sensor
Implementation Method 3
detect, based on time of flight in the received signals, portions of the particular object in the field of view that are similarly spaced from the light source
Data Source
AI summary
A vehicle-assistance system for classifying objects in a vehicle's surroundings. The system includes: at least one memory configured to store classification information for classifying a plurality of objects; and at least one processor configured to receive a plurality of detection results associated with light detection and ranging system (LIDAR) detection results, each detection result including location information, and further information indicative of at least two of the following detection characteristics: object surface reflectivity; temporal spreading of signal reflected from the object; object surface physical composition; ambient illumination measured at a LIDAR dead time; difference in detection information from a previous frame; and confidence level associated with another detection characteristic. The at least one processor is also configured to: access the classification information; and based on the classification information and the detection results, classify an object in the vehicle's surroundings.