Video Tracking Apparatus Prioritizing Collation by Feature Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional object tracking systems face increased calculation burdens as the number of persons in a video image and person information grows, leading to delayed processing and inefficient collation.
Innovation Solution
An information processing apparatus determines tracking information targets based on feature amounts, calculating a degree of confirmation to prioritize collation processing on persons with significant feature changes, thereby reducing unnecessary collations and calculation loads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If collation processing is performed on all detected persons in real-time video tracking, then tracking accuracy is maintained, but calculation amount increases and processing delay occurs
Solution Approach 1:
The patent segments the set of all detected persons into multiple subsets based on spatial regions (e.g., foreground/background, different zones in the video frame). Collation processing is then performed selectively on specific segments rather than uniformly on all persons, reducing overall calculation load while maintaining tracking accuracy for priority targets
Solution Approach 2:
The patent applies different collation processing strategies to different persons based on their local characteristics. Persons in critical regions or with higher tracking priority receive full collation processing, while others receive reduced or skipped processing, optimizing the balance between accuracy and processing speed
2Quantity of substance
If the number of persons and person information increases, then tracking coverage is improved, but calculation amount of collation processing increases
Solution Approach 1:
The patent performs preliminary filtering and prioritization of persons before collation processing. By pre-identifying which persons require collation based on simple criteria (e.g., motion detection, region of interest), the system reduces the number of persons that undergo expensive collation processing, thereby managing complexity as the number of tracked persons increases
Data Source
AI summary
An information processing apparatus determines tracking information that is a target of collation processing for performing association with person information from among a plurality of items of tracking information corresponding to a plurality of persons detected from a video image frame based on a feature amount of each of the plurality of persons, and executes collation processing in which person information to be associated with the tracking information that is a target of the collation processing is identified based on a similarity between a feature amount of a person corresponding to a tracking information determined to be a target of the collation processing and a plurality of feature amounts stored in association with a plurality of items of person information in a storage device.