Privacy-Preserving Person Identification Using Depth Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current person identification methods are inadequate in uncontrolled environments, failing to accurately identify individuals at a distance, with varying orientations, or when partially occluded, and they often compromise privacy by exposing unnecessary personal information. Additionally, existing technologies struggle to objectively measure mental perceptions like fatigue and intent.
Innovation Solution
The system uses depth data from sensors to segment and identify individuals by isolating body portions and determining features such as static and dynamic measurements, allowing for robust identification even when partial or incomplete data is available, while protecting privacy by not using visual images. It employs machine learning techniques like Convolutional Neural Networks to classify and quantify mental perceptions and intentions based on physical attributes and movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If facial recognition or fingerprint recognition is used, then accurate identification can be achieved within specific operational parameters, but the system becomes non-functional outside these strict conditions (e.g., varying lighting, distance, orientation)
Solution Approach 1:
The system uses multiple sensor modalities (depth sensors, motion sensors, thermal sensors) that can function across diverse environmental conditions. Each sensor type captures different aspects of human presence and behavior, allowing the system to identify persons whether they are facing the camera, in low light, or at varying distances - making the identification system universally applicable across operational conditions that would fail traditional single-modality systems
2Measurement precision
If visual data of a person's face or body is collected for identification, then identification accuracy improves, but privacy is compromised by exposing unnecessary personal information (clothing, reading material, etc.)
Solution Approach 1:
The system extracts only the specific features necessary for identification and mental state detection from the sensor data, while deliberately excluding or anonymizing other personal information. Depth data and motion patterns are processed to derive identification features without capturing or storing visual images that would reveal clothing, appearance details, or what the person is reading or viewing - thus extracting useful information while leaving private information out
3Ease of operation
If gait or silhouette-based identification is used, then identification can occur at a distance, but the system becomes prone to failure when occlusion or specific field-of-view requirements are not met
Solution Approach 1:
The system merges multiple sensor data streams including depth information, thermal patterns, and motion capture data to create a composite identification signature. This combination allows the system to reliably identify persons at a distance while being resilient to partial occlusions - if one data stream is blocked or degraded, other streams compensate to maintain identification success, thereby merging multiple weak signals into a robust identification capability
Data Source
AI summary
The disclosed technology enables, among other things, the identification of persons and the characterization of mental perceptions (e.g., pain, fatigue, mood) and/or intent (e.g., to perform an action) for medical, safety, home care, and other purposes. Of significance are applications that require long-term patient monitoring, such as tracking disease progression (e.g., multiple sclerosis), or monitoring treatment or rehabilitation efficacy. Therefore, longitudinal data must be acquired over time for the person's identity and other characteristics (e.g., pain level, usage of a cane). However, conventional methods of person identification (e.g., photography) acquire unnecessary personal information, resulting in privacy concerns. The disclosed technology allows measurements to be performed while protecting privacy and functions with partial or incomplete measurements, making it robust to real-world (noisy, uncontrolled) settings, such as in a person's home (whether living alone or with others).