Multi-Mode Optical Sensing with NIR Pulses for Drone Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current object detection systems face challenges in real-time detection and recognition due to environmental conditions like low lighting and object-background similarity, and existing solutions fail to effectively detect drones in various environments, especially when they operate in wireless silence or in noisy conditions with small cross-sectional areas.
Innovation Solution
A system utilizing a red, green, blue (RGB) image sensor and a co-located near-infrared (NIR) image sensor, combined with a NIR laser to emit pulses, processes multiple image types to generate multi-mode images, which are analyzed by a machine learning model to enhance object recognition, particularly identifying retro-reflecting objects like drones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radar-based solutions are used for drone detection, then detection capability is provided, but detection range is reduced due to small cross-sectional area of drones and false alarms increase in noisy environments
Solution Approach 1:
The patent combines multiple sensing modalities (visible light camera, infrared sensor, and radar) into a single integrated detection system. The processor receives and processes signals from all three sensors simultaneously, merging their detection capabilities to overcome the limitations of each individual sensor. This combination allows the system to detect drones with small cross-sectional areas while maintaining accurate detection range and reducing false alarms through multi-source verification.
Solution Approach 2:
The detection system is designed with multi-functionality by incorporating sensors that can operate across different environmental conditions and detection scenarios. The visible light camera provides high-resolution imaging for identification, the infrared sensor detects thermal signatures and operates in low-light conditions, and radar provides detection capability in various weather conditions. This universal approach enables reliable drone detection across diverse environments without being limited to a single sensing modality.
2Productivity
If visual means (cameras) are used for object detection, then real-time detection is achieved, but detection accuracy deteriorates under poor environmental conditions such as low lighting and visibility
Solution Approach 1:
The system merges visible light imaging with infrared sensing capabilities, allowing the detection system to maintain real-time operation while adapting to poor environmental conditions. The infrared sensor complements the visible light camera by providing detection capability in low-light and obscured conditions, ensuring that real-time detection accuracy is maintained across varying environmental conditions through multi-sensor fusion.
Solution Approach 2:
The system changes the operational parameters by switching between or combining different sensing modalities based on environmental conditions. When visible light conditions are poor, the system increases reliance on infrared detection parameters. The processor dynamically adjusts which sensor data is prioritized and how multi-sensor inputs are weighted, changing detection parameters adaptively to maintain accuracy under varying lighting and visibility conditions while preserving real-time detection capability.
3Reliability
If multiple sensors are integrated to improve detection reliability, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The system segments the detection function into distinct modular components, with each sensor (visible light camera, infrared sensor, radar) handling specific detection tasks. The processor is designed to receive and process signals from these segmented sensor modules independently before integrating their outputs. This segmentation allows for manageable system architecture where each sensor can be optimized for its specific function while the overall system achieves high detection reliability through coordinated operation of the modular components.
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 improves object detection accuracy and reduces false alarms by correlating multi-modal sensor data, enabling precise identification of objects even in low visibility conditions and distinguishing between different objects based on retro-reflection characteristics.
Implementation Method 1
The multiple NIR pulse-enhanced images include reflections of NIR pulses from objects in the FOV
Implementation Method 2
a co-located, near infrared (NIR) image sensor (configured to generate NIR images including the field of view)
Data Source
AI summary
A system provided includes an RGB image sensor; a near infrared (NIR) image sensor, an NIR pulse laser, and a processor performing steps of capturing one or more RGB images of a field of view (FOV) and multiple NIR images from a plurality of NIR exposures of reflections of NIR pulses from the same FOV. The system further provides generating a multi-mode image, wherein each pixel of the multi-mode image has a set of values derived from corresponding pixels in multiple images, where the multiple images include at least one of the one or more RGB images, at least one of the multiple NIR non pulse images, and an NIR pulse-only image, a retro-reflector image, a distance image, and a velocity image.