Passenger Counting Using Hiding-Area Tracking in Crowded Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately count the number of individuals entering or leaving a vehicle, especially when the interior is crowded, as multiple persons may overlap and obscure others, leading to incorrect counting due to hidden individuals.
Innovation Solution
A counting device that tracks individuals in time-series images, determines if their positions are within a hiding determination area, and counts them based on duration outside this area, correcting the count by accounting for enterers and leavers using head and trunk detection and tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If simple person detection is used in crowded vehicle interiors, then detection speed is improved, but counting accuracy deteriorates due to hidden persons
Solution Approach 1:
The system performs preliminary tracking of detected persons across multiple images before final counting. By maintaining track information and determining whether persons are in hiding determination areas beforehand, the system can accurately count only those not hidden by others, resolving the contradiction between fast detection and accurate counting in crowded scenes
Solution Approach 2:
The system introduces a hiding determination area as an intermediary concept to distinguish between visible and hidden persons. This intermediary region allows the system to filter out falsely detected persons who are actually hidden behind others, enabling accurate counting while maintaining detection speed through efficient tracking algorithms
2Measurement precision
If multiple cameras are used to capture different angles, then counting accuracy is improved, but device complexity increases
Solution Approach 1:
The system segments the counting task into distinct functional modules: person detection, tracking across images, hiding determination, and final counting. This segmentation allows a single camera system to perform complex counting accurately by dividing the problem into manageable steps, avoiding the need for multiple cameras while maintaining high accuracy
3Loss of time
If real-time counting is performed, then response time is improved, but counting accuracy deteriorates due to hidden persons in crowded areas
Solution Approach 1:
The system continuously tracks detected persons across all captured images rather than performing one-time detection. This continuous tracking enables real-time counting while maintaining accuracy by determining whether persons remain in hiding determination areas throughout the observation period, ensuring both speed and precision
Data Source
AI summary
A counting device includes a processor configured to: detect one or more persons in a predetermined region from each of a plurality of time-series images, track, for each of the one or more detected persons, the person in one or more images representing the person among the plurality of images, determine whether the position in the images of each of the one or more detected persons is within a hiding determination area in a region in the images corresponding to the predetermined region, based on the result of tracking, and count, when duration during which the position in the images of any of the one or more detected persons is outside the hiding determination area is not less than a predetermined time threshold, the number of the one or more persons represented in an image during the duration as the number of those remaining in the predetermined region.