Structured Light Road Obstacle Detection for Night Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving systems face challenges in accurately detecting obstacles on a road surface at night due to insufficient luminous performance of lighting devices, which hinders effective obstacle perception and navigation.
Innovation Solution
A method using a lighting device that projects a light pattern with dark and lighted square pixel groups, similar to a QR code, and a camera to capture the deformed pattern caused by obstacles, combined with a processing unit to analyze the deformation and provide object information, enhancing luminous intensity or color for improved detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a camera is used to detect objects on the road surface, then object detection capability is provided, but the detection accuracy is insufficient to distinguish between actual obstacles (stones, debris) and road surface markings (arrows, characters)
Solution Approach 1:
The detection system is segmented into multiple specialized sensors: a camera for capturing images, a light receiving device for detecting reflected light intensity, and a depth sensing device for measuring distance. Each sensor captures a different aspect of the target, and their data are integrated to achieve accurate discrimination between obstacles and markings.
Solution Approach 2:
A projection device projects structured light patterns (such as grid patterns or coded patterns) onto the road surface as an intermediary. The reflected light from these patterns provides additional information that helps distinguish actual obstacles from road markings by analyzing how the light interacts with different surface features.
2Measurement precision
If multiple sensors are used to improve detection accuracy, then discrimination capability between obstacles and markings is enhanced, but the device complexity and cost increase
Solution Approach 1:
The system uses a single light source that serves multiple functions: it provides illumination for the camera to capture images and simultaneously creates the structured light patterns for depth and surface analysis. The same light source enables both passive imaging and active light projection, reducing the need for separate components.
Solution Approach 2:
Multiple detection functions are merged into an integrated sensor system where the camera, light receiving device, and depth sensing device share common optical paths and processing electronics. This consolidation reduces overall system complexity while maintaining the capabilities of individual sensors.
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
Enhances safety and accuracy in obstacle detection during night autonomous driving by quickly identifying object features and enabling appropriate vehicle maneuvers to avoid collisions.
Implementation Method 1
a light receiving device that receives reflected light from the object and generates light intensity distribution information of the object
Implementation Method 2
a depth sensing device that detects an object at different depths from the projection device to generate depth information of the object
Data Source
Figure 1
Figure 2
AI summary
The present invention refers to a method for detecting an object in a road surface, the method comprising the steps of projecting a light pattern on the road surface, acquiring an image of the projected light pattern, detecting a shadow in the acquired image and using some features of the shadow to obtain information about features of an object. The invention also provides a method for autonomous driving using this object detection and an automotive lighting device.