AR Depth Thermal Fusion for Forensic Object Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current imaging technologies, such as thermal and depth imaging, are underutilized in forensic and disaster relief applications due to limitations in accuracy, size, and feasibility for mobile and augmented reality-based deployments, particularly in combining thermal and depth imaging for robust fusion and synergistic effects in object recognition and environmental reconstruction.

Innovation Solution

The development of mobile and augmented reality-based systems that fuse thermal and depth imaging channels using sophisticated software algorithms, enabling wearable devices to capture and process both image types for improved object recognition, environmental reconstruction, and personal authentication, with a cloud-based fusion service employing artificial intelligence and deep learning for feature extraction and semantic labeling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If thermal imaging is used for forensic and disaster relief applications, then object recognition and environmental reconstruction capabilities are improved, but device size and cost remain prohibitive for mobile and wearable deployments

Engineering Contradiction:
Improveobject recognition accuracyVSAvoiddevice size
Core Design Contradiction:
Measurement precisionVSWeight of moving object

Solution Approach 1:

The patent combines thermal imaging devices with mobile computing platforms and augmented reality displays to create an integrated system. The thermal camera captures images that are processed and displayed through AR glasses, merging the thermal sensing capability with portable computing and display technologies to achieve compact form factor while maintaining forensic application capabilities

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system integrates multiple functions into a single wearable platform: thermal imaging for object detection, depth imaging for spatial context, augmented reality display for real-time visualization, and mobile computing for data processing. This multi-functional integration eliminates the need for separate bulky devices while providing comprehensive forensic analysis capabilities

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

2Adaptability or versatility

If depth imaging devices are integrated into mobile and wearable systems, then environmental reconstruction and spatial awareness are improved, but device complexity and computational requirements increase

Engineering Contradiction:
Improveenvironmental reconstruction capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent uses cloud-based processing services as an intermediary between the wearable device and the final analysis. Depth and thermal images are captured locally on the mobile device, transmitted to cloud servers for sophisticated fusion processing and environmental reconstruction, then results are fed back to the AR display. This divides computational complexity between portable and remote systems

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system combines depth imaging data with thermal imaging data to create a multi-dimensional representation of the environment. By fusing these different modalities in both spatial and temporal dimensions, the system achieves comprehensive environmental reconstruction while managing computational complexity through selective processing

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Measurement precision

If thermal and depth imaging channels are fused using traditional algorithms, then image processing speed is maintained, but alignment accuracy degrades due to complex scene edges and overlapping thermal signatures

Engineering Contradiction:
Improveimage alignment accuracyVSAvoidimage processing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent creates synthetic training data by rendering fake thermal images from 3D models and depth maps. These synthetic thermal images are then used to train deep neural networks to perform thermal-depth alignment. This copying approach allows the system to learn accurate alignment relationships without processing actual complex thermal images in real-time

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system performs preliminary training of the deep neural network alignment model using synthetic data before actual use. Once trained, the neural network can quickly process real thermal and depth images to achieve accurate alignment. This preliminary training action enables fast and accurate processing during actual forensic applications

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11481979B2Mobile and augmented reality based depth and thermal fusion scan
Publication Date: 2022.10.25 THE REGENTS OF THE UNIVERSITY OF COLORADO
  • US11481979B2 patent drawing
  • US11481979B2 patent drawing
  • US11481979B2 patent drawing

AI summary

Systems and methods are described for mobile and augmented reality-based depth and thermal fusion scan imaging. Some embodiments of the present technology use sophisticated techniques to fuse information from both thermal and depth imaging channels together to achieve synergistic effects for object recognition and personal identification. Hence, the techniques used in various embodiments provide a much better solution for, say, first responders, disaster relief agents, search and rescue, and law enforcement officials to gather more detailed forensic data. Some embodiments provide a series of unique features including small size, wearable devices, and ability to feed fused depth and thermal streams into AR glasses. In addition, some embodiments use a two-layer architecture for performing device local fusion and cloud-based platform for integration of data from multiple devices and cross-scene analysis and reconstruction.