Filterless Computer Vision Cameras for HMD IR Laser Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional mixed-reality systems face challenges in detecting infrared laser light due to the high cost, bulkiness, and power consumption of existing low light and thermal sensing sensors, which are limited by high dark current and read noise, especially in environments below starlight lighting levels.
Innovation Solution
Incorporating a computer vision camera without an IR light filter and a machine learning algorithm in a head-mounted device to detect IR laser light, and compensating for parallax using thermal imaging and depth maps to generate an overlaid image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional low light or thermal sensors are used for IR laser detection, then detection capability is improved, but cost, size, and power consumption increase significantly
Solution Approach 1:
The patent makes the existing computer vision camera perform multiple functions: it continues to capture visible light images for normal computer vision tasks while simultaneously detecting IR laser light by removing the IR filter. This eliminates the need for separate dedicated IR sensors, reducing cost and device complexity while maintaining detection capability.
Solution Approach 2:
The patent extracts and removes the IR light filter from the camera optical path, which was previously blocking IR wavelengths. By taking out this filtering element, the existing camera sensor gains the ability to detect IR laser light without requiring additional specialized sensors.
2Measurement precision
If conventional low light or thermal sensors are used for IR laser detection, then detection capability is improved, but power consumption increases
Solution Approach 1:
The patent makes the existing computer vision camera perform multiple functions: it continues to capture visible light images for normal computer vision tasks while simultaneously detecting IR laser light by removing the IR filter. This eliminates the need for separate dedicated IR sensors, reducing cost and device complexity while maintaining detection capability.
Solution Approach 2:
The patent extracts and removes the IR light filter from the camera optical path, which was previously blocking IR wavelengths. By taking out this filtering element, the existing camera sensor gains the ability to detect IR laser light without requiring additional specialized sensors.
3Device complexity
If standard computer vision cameras with IR filters are used, then cost is reduced, but IR laser detection capability is lost
Solution Approach 1:
The patent extracts and removes the IR light filter from the camera optical path, which was previously blocking IR wavelengths. By taking out this filtering element, the existing camera sensor gains the ability to detect IR laser light without requiring additional specialized sensors.
Solution Approach 2:
The patent changes the optical parameters of the camera system by removing the IR filter, thereby altering the spectral response of the camera to include IR wavelengths. This parameter change enables the same low-cost camera hardware to detect IR laser light.
4Measurement precision
If thermal imaging is used for accurate IR detection, then measurement precision is improved, but device size and complexity increase
Solution Approach 1:
The patent makes the existing computer vision camera perform multiple functions: it continues to capture visible light images for normal computer vision tasks while simultaneously detecting IR laser light by removing the IR filter. This eliminates the need for separate dedicated IR sensors, reducing cost and device complexity while maintaining detection capability.
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 reduces hardware costs, size, and power consumption while effectively detecting IR laser light, enhancing the user's perception of environmental conditions without adding bulk or power to the system.
Implementation Method 1
a sensor of the at least one computer vision camera is operable to detect IR light
Implementation Method 2
The HMD generates a first image of an environment using the computer vision camera. The first image is fed as input to a machine learning (ML) algorithm. The ML algorithm identifies collimated IR light that is detected by the sensor of the computer vision camera
Implementation Method 3
The HMD generates a second image of the environment using a thermal imaging camera
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A head-mounted device (HMD) is structured to include at least one computer vision camera that omits an IR light filter. Consequently, this computer vision's sensor is able to detect IR light, including IR laser light, in the environment. The HMD is configured to generate an image of the environment using the computer vision camera. This image is then fed as input into a machine learning (ML) algorithm that identifies IR laser light, which is detected by the sensor and which is recorded in the image. The HMD then visually displays a notification comprising information corresponding to the detected IR laser light.