Face-and-Body Feature Matching for Continuous Person Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing techniques struggle to effectively track individuals who are not initially identifiable through facial recognition, particularly in surveillance scenarios where faces are obscured or not captured clearly.
Innovation Solution
An information processing system that utilizes both facial feature information and additional person region feature information, such as body characteristics, to identify and track individuals across multiple images, allowing for continuous tracking even when facial recognition fails.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If only facial feature information is used for person identification, then the identification process is simple and fast, but the reliability of identification drops when faces are obscured or not captured clearly
Solution Approach 1:
The patent segments the person recognition task into two distinct phases: initial identification using facial features, and continuous tracking using body region features. This segmentation allows the system to use the simplest effective method for each phase, improving overall reliability without unnecessary complexity.
Solution Approach 2:
The system performs preliminary identification using facial features when available, then pre-processes and stores body region feature information in advance. This preliminary action ensures that when facial recognition fails, the tracking can continue immediately using pre-prepared body feature data, enhancing reliability.
2Reliability
If facial recognition is used for initial identification, then the identification accuracy is high when faces are visible, but the system fails to track individuals whose faces are obscured
Solution Approach 1:
The patent introduces body region feature information as an intermediary when facial recognition fails. The system extracts and stores body features (size, shape, clothing characteristics) that serve as alternative identification information, preventing loss of tracking capability when faces are obscured.
Solution Approach 2:
The system dynamically changes the identification parameters being used - switching from facial feature parameters to body region feature parameters when facial recognition is not possible. This parameter substitution ensures continuous tracking without information loss.
3Reliability
If the system stores and processes additional body region feature information, then the ability to track unidentifiable persons improves, but the data processing complexity and storage requirements increase
Solution Approach 1:
The patent segments feature extraction into facial features and body region features, processing only the necessary body features (size, shape, clothing) rather than all possible characteristics. This selective segmentation reduces data complexity while maintaining tracking reliability.
Solution Approach 2:
The system extracts only the essential body region features needed for tracking (overall size, shape, prominent clothing characteristics) rather than exhaustive detail. This partial action provides sufficient reliability for continuous tracking without the burden of processing excessive data.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An information processing apparatus (100) includes a collation unit (102) that collates first feature information extracted from a person included in a first image (20) with first registered feature information stored in a storage unit (110), and a registration unit (104) that stores, in a case where the first feature information is unable to be extracted from the person or a collation result in the collation unit (102) indicates a mismatch, second feature information extracted from the person in the storage unit (110) as second registered feature information, in which the collation unit (102) collates second feature information extracted from a person included in a second image (22) with the second registered feature information stored in the storage unit (110), and thus specifies the person corresponding to the second registered feature information in the second image (22).