Reference State Adaptation for Accurate Crowded-Space Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing state determination techniques fail to accurately account for varying reference states based on the situation of the imaged space, leading to inaccurate determinations of abnormal states in crowded environments.
Innovation Solution
A reference state deciding device that calculates object and imaged space features from past and current image data to determine a suitable reference state for state determination, using correlation and co-occurrence analysis to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a reference state is previously set in a fixed manner, then the state determination can be performed with a simple process, but the accuracy of determination decreases depending on the situation of the space being imaged
Solution Approach 1:
The reference state is changed from a fixed predetermined value to a dynamic value that automatically adapts to different situations. The system calculates the reference state based on the actual imaged space characteristics (such as crowd density, movement patterns, and spatial distribution) observed in the surveillance footage, allowing the reference state to dynamically adjust to match the current situation being monitored.
Solution Approach 2:
The system changes the parameters used to define the reference state from static predetermined values to values derived from actual image data analysis. By extracting features such as crowd density, movement speed, and spatial distribution from the imaged space, the system adjusts the reference state parameters to reflect the actual conditions, thereby improving determination accuracy.
2Measurement precision
If a reference state is decided in accordance with the situation of the imaged space, then the accuracy of state determination is improved, but the complexity of the determination process increases
Solution Approach 1:
The system performs self-service by automatically calculating and adjusting the reference state based on the imaged space characteristics without requiring manual intervention. The algorithm autonomously extracts features from the surveillance images, computes the appropriate reference state parameters, and applies them to the state determination process, thereby managing the increased complexity through automation.
Solution Approach 2:
The system implements feedback by continuously monitoring the imaged space characteristics and using this information to adjust the reference state. The calculated reference state is fed back into the state determination process, creating a closed-loop system that automatically adapts to changing conditions while maintaining determination accuracy.
3Ease of manufacture
If a fixed reference state is used for all situations, then the system can be implemented with simple preprocessing, but it cannot appropriately decide a reference state for state determination in varying conditions
Solution Approach 1:
The reference state transitions from a static fixed value to a dynamic adaptive value that changes according to the situation. The system dynamically calculates the reference state by analyzing imaged space characteristics such as crowd density, movement patterns, and spatial distribution, enabling the system to adapt to varying conditions while maintaining implementation feasibility through automated processing.
Data Source
AI summary
A reference state deciding device (10) according to the present disclosure includes a feature calculation unit (11) that calculates an object feature related to a target object of state determination included in a real space and an imaged space feature related to the real space on the basis of past image data of the real space imaged in the past and target image data of the real space imaged at the time of the state determination, and a reference state deciding unit (12) that decides a reference state to be used for the state determination on the basis of a relation between the object feature and the imaged space feature calculated from the past image data and the target image data.