Auto-Configuring Camera Region of Interest for Accurate People Counting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object tracking systems, such as cameras used for security and people counting, face challenges in accurately detecting and counting individuals due to outliers, where a person near the door is mistakenly counted as entering, leading to incorrect counts in high foot traffic areas.
Innovation Solution
The system auto-configures a region of interest (ROI) by tracking and comparing trajectories of individuals within camera frames, identifying common trajectories with shared start and end points not initially captured in the ROI, and updates the ROI to encompass these common trajectories, ensuring accurate counting by focusing on relevant areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a fixed ROI is used for object tracking, then the system structure is simple and easy to implement, but the measurement precision deteriorates due to outliers being incorrectly counted in high foot traffic areas
Solution Approach 1:
The patent applies the dynamics principle by transforming the static ROI into a dynamic one that automatically adjusts its boundaries based on real-time trajectory analysis. The system continuously monitors object movement patterns and reconfigures the ROI to follow common trajectories, thereby maintaining high tracking accuracy in high foot traffic environments without requiring manual intervention or complex fixed configurations
Solution Approach 2:
The patent implements self-service by enabling the ROI to automatically configure itself through trajectory analysis without external intervention. The system autonomously identifies common movement patterns, determines optimal ROI boundaries, and applies these configurations automatically, eliminating the need for manual setup or complex external control mechanisms while improving measurement precision
2Measurement precision
If the ROI is expanded to capture all possible trajectories, then the measurement precision improves by capturing all entries, but the reliability deteriorates by including false positives from people not actually entering
Solution Approach 1:
The patent applies local quality by making different regions of the camera view serve different functions. Instead of uniformly expanding the ROI to capture all possible trajectories, the system identifies and focuses computational resources on specific local areas where common trajectories occur. The ROI is dynamically configured to cover only the relevant local regions where actual entries happen, thereby maintaining high detection accuracy while excluding false positives from areas where people merely pass by
Solution Approach 2:
The patent implements taking out by extracting and isolating the essential trajectory information from the complex scene. Through trajectory analysis, the system identifies and extracts common movement patterns that represent actual entries, separating them from spurious movements. The ROI is then configured to cover only these extracted essential trajectories, thereby improving reliability by excluding false positives while maintaining precision for actual entries
Data Source
AI summary
Disclosed herein are apparatuses and methods for auto-configuring a region of interest (ROI) associated with a camera. In one implementation, a method comprises receiving image frames from a camera installed in the environment, wherein the ROI is located within the view of the image frames. The method includes tracking a plurality of persons in the image frames and determining a respective trajectory of movement for each person of the plurality of persons. The method further includes comparing each of the respective trajectories to one another and identifying, based on the comparing, a common trajectory shared by more than one person of the plurality of persons, wherein the common trajectory is not fully encompassed in the ROI. The method additionally includes updating the ROI to encompass the common trajectory, and includes configuring the updated ROI to be associated with new image frames from the camera.