Composite Image Search for Moving Object Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image search techniques for surveillance cameras struggle to accurately identify images of a moving object, especially when captured from different angles or with varying attire, leading to missed results despite matching the same person.
Innovation Solution
An information processing system that includes a processor, storage device, and display device, which executes a similarity search using feature values such as hue and shape, and updates the display to show images with high similarity, even when images are captured from different angles or with different attire, by treating multiple images as search queries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single image is used as a search query, then the search process is simple and fast, but the search coverage is limited and images of the same person captured from different angles or with different attire are missed
Solution Approach 1:
The patent combines multiple images of the same moving object into a single composite image that integrates features from different angles and conditions. This composite image is then used as the search query, allowing the system to maintain fast search performance while achieving comprehensive coverage that captures images of the same person regardless of angle or attire changes.
Solution Approach 2:
The system performs preliminary processing to create a composite image before the actual similarity search is executed. This pre-processing step consolidates multiple views and conditions into a single representative image, enabling the subsequent search to be both fast and comprehensive without requiring multiple separate search operations.
2Reliability
If multiple images are used as search queries to improve coverage, then more comprehensive search results are obtained, but the search complexity and processing time increase
Solution Approach 1:
Instead of performing separate similarity searches with multiple images, the patent merges multiple images into a single composite image that encapsulates features from all source images. This approach maintains search process simplicity while achieving the comprehensive coverage that would otherwise require multiple complex search operations.
3Measurement precision
If traditional similarity search based on feature values is used, then images with identical features are found, but images of the same person with different attire or from different angles are not detected
Solution Approach 1:
The patent creates a composite image that merges visual features from multiple images of the same person taken under different conditions (different angles, different attire). This composite image contains a broader range of feature variations, enabling the similarity search to identify images of the same person even when attire or angle differs, thereby improving person identification accuracy while maintaining feature matching precision.
Data Source
AI summary
Provided is an information processing system, including a processor, a storage device and a display device. The storage device stores images captured by imaging devices. If an image of a moving object is selected as a search query, then the processor executes a similarity search on the images stored in the storage device, with the selected image as the search query. The display device displays images attained as results of the similarity search. If an image of a moving object is added as a search query, then the processor executes a similarity search with all selected images as search queries. The display device updates images to be displayed such that images attained as results of the similarity search performed with all the selected images as the search queries are displayed.