Road Surface Object Detection Using Headlamp Shadow Patterns

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing autonomous driving systems face challenges in accurately detecting objects at night due to insufficient luminous performance of lighting devices, which hinders safe navigation and maneuvering.

Innovation Solution

A method utilizing a lighting device to project a light pattern on the road surface, where objects cast identifiable shadows, allowing a camera to detect these shadows and process them for object detection, potentially modifying the pattern for enhanced feature extraction using machine learning and image processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing lighting devices are used to illuminate the road at night, then the system complexity is low and no additional hardware is needed, but the object detection accuracy is insufficient due to inadequate luminous performance

Engineering Contradiction:
Improveobject detection accuracyVSAvoidluminous performance
Core Design Contradiction:
Measurement precisionVSIllumination intensity

Solution Approach 1:

The system projects a structured light pattern (grid of light pixels) onto the road surface before capturing the image. This preliminary illumination action creates distinct shadow regions that enhance the detectability of objects, allowing the processing unit to identify objects through shadow analysis even when ambient light is insufficient

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The invention changes the illumination parameters by projecting a specific light pattern with controlled intensity and distribution. The light pattern consists of multiple light pixels with adjustable luminous intensity, creating a structured illumination field that enhances shadow contrast and improves object detection capability without requiring completely new lighting hardware

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If a structured light pattern is projected to enhance object detection, then the detection accuracy improves, but the device complexity increases due to additional light modules

Engineering Contradiction:
Improveobject detection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The invention makes the existing lighting device perform multiple functions: it continues to provide general road illumination while simultaneously projecting a structured light pattern for object detection. The same lighting device that illuminates the road is also used to create the detection pattern, eliminating the need for separate projection hardware

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The existing lighting device serves itself by dual-purpose usage. The headlamp or lighting device that normally illuminates the road is repurposed to also create the structured light pattern for shadow-based object detection, making the system self-sufficient without requiring external additional components

Inventive Principle:
Principle #25Self-service

3Ease of operation

If a uniform light pattern is used, then the shadow identification is easier and processing resources are reduced, but the luminous intensity distribution is less optimized for specific detection scenarios

Engineering Contradiction:
Improveshadow identification easeVSAvoidluminous intensity distribution
Core Design Contradiction:
Ease of operationVSIllumination intensity

Solution Approach 1:

The light pattern consists of multiple discrete light pixels distributed across the illumination area, each with controllable intensity. This allows different regions to have different luminous characteristics, optimizing shadow contrast in specific areas while maintaining overall illumination efficiency and facilitating easier shadow identification in processed images

Inventive Principle:
Principle #3Local quality

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

Improves object detection accuracy and safety in autonomous driving by leveraging existing lighting devices to identify shadows, enabling safer navigation and maneuvering without additional hardware, and allowing for autonomous vehicle control decisions.

Implementation Method 1

a lighting device projects a light pattern on the road surface where the object is intended to be detected

Methodology Applied
Scientific EffectLight: Light

Implementation Method 2

In this image, acquired by the image device, the object causes a shadow

Methodology Applied
Scientific EffectShadow: Shadow

Data Source

PatentEP4356068B1Method for detecting an object in a road surface, method for autonomous driving and automotive lighting device
Publication Date: 2026.03.25 VALEO VISION SA
  • EP4356068B1 patent drawingFigure 1~2
  • EP4356068B1 patent drawingFigure 3

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 (6) on the road surface (5), acquiring an image of the projected light pattern (6), detecting a shadow (7) in the acquired image and using some features of the shadow (7) 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 (1).