Vehicle Sensor Occlusion Detection for Mirage and Wet Road Confusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle sensors face challenges in accurately detecting road surfaces and objects due to environmental conditions such as mirage phenomena caused by temperature gradients, leading to misidentification of water on the road or objects, which can affect vehicle operations.
Innovation Solution
A system that uses a processor and memory to identify environment features like sky, road surface, and road shoulder based on map data and sensor data, determines low confidence areas, and receives polarimetric images to differentiate between mirage phenomena, wet road surfaces, and sky, using semantic segmentation and polarimetric image analysis to actuate vehicle actuators accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If vehicle sensors are used to detect road surfaces and objects, then vehicle operation control is enabled, but misidentification of water on road or objects occurs due to mirage phenomena
Solution Approach 1:
The patent transitions from 2D image analysis to 3D point cloud data analysis using LiDAR technology. By utilizing three-dimensional spatial information and depth data, the system can accurately distinguish between actual water pools on the road and mirage phenomena, resolving the identification accuracy problem caused by limited 2D visual information
Solution Approach 2:
The patent introduces a point cloud processing system as an intermediary between the sensor data and the vehicle control system. This intermediary layer processes and validates the detected features using multiple data sources including LiDAR point clouds, comparing them against expected road surface characteristics to filter out false detections caused by mirages before transmitting control commands
2Measurement precision
If semantic segmentation is used to identify environment features, then feature classification is improved, but low confidence areas remain where mirage phenomena occur
Solution Approach 1:
The patent combines multiple detection methods and data sources including semantic segmentation results, LiDAR point cloud analysis, polarization camera data, and environmental sensor information. By merging these complementary approaches, the system achieves higher confidence in feature identification even in challenging conditions where individual methods may produce low confidence results
Solution Approach 2:
The patent implements a feedback mechanism where the system continuously monitors detection confidence levels and adjusts its processing accordingly. When low confidence areas are detected, the system activates additional verification processes using point cloud data and other sensors to resolve ambiguities before finalizing the detection result
3Measurement precision
If polarimetric images are used to differentiate mirage phenomena, then detection accuracy is improved, but system complexity increases
Solution Approach 1:
The patent segments the detection task into multiple specialized components: standard cameras for general imaging, polarization cameras for detecting optical anomalies, LiDAR for 3D structure, and dedicated processing modules for each sensor type. This segmentation allows each component to be optimized for its specific function while working together to solve the overall detection problem
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
The system effectively identifies and differentiates between mirage phenomena, wet road surfaces, and sky, enabling accurate vehicle operation by determining occluded volumes and adjusting vehicle speed based on detected conditions, thereby improving safety and reliability in challenging weather conditions.
Implementation Method 1
a polarimetric camera sensor (102) having a field of view overlapping the field of view of the vehicle camera sensor (102) providing the image with the identified low-confidence area (106). The computer (108) may be programmed to receive the polarimetric image from the polarimetric camera sensor (102)
Implementation Method 2
Weather conditions such as rain or high ambient temperature may affect sensor data
Implementation Method 3
environmental conditions such as a temperature gradient above a road surface may cause a mirage phenomenon
Data Source
AI summary
A system for detecting a road surface includes a processor programmed to identify, in a vehicle sensor field of view, environment features including a sky, a road surface, a road shoulder, based on map data and data received from the one or more vehicle sensors, upon determining a low confidence in identifying an area of the field of view to be a road surface or sky, to receive a polarimetric image, and to determine, based on the received polarimetric image, whether the identified area is a mirage phenomenon, a wet road surface, or the sky. The low confidence is determined upon determining that a road surface has a vanishing edge, a road lane marker is missing, or an anomalous object is present.