People Counting via Multi-Sensor Face Rectangle Grouping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Audience measurement systems face inaccuracies in counting people due to undetected faces, false positives, and double counting when using multiple image sensors, leading to unreliable media exposure data.
Innovation Solution
The system analyzes images over a period, uses grouping algorithms to eliminate transient detections, conditions frames to eliminate static false positives, and manages overlapping fields of view to prevent double counting, while increasing frame rate by focusing face detection on active segments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple image sensors are used to capture images of the environment, then the coverage area and detection capability are improved, but false positives and double counting increase
Solution Approach 1:
The patent combines data from multiple image sensors by identifying overlapping detection regions and merging the detected face data. The system determines whether detected faces in overlapping regions belong to the same person and consolidates the count, preventing double counting while maintaining the expanded coverage area provided by multiple sensors.
2Measurement precision
If face detection is performed on all segments of images, then detection thoroughness is improved, but processing time and computational load increase
Solution Approach 1:
The patent divides the image into multiple segments and identifies only those segments containing active elements (such as faces or regions with changes between frames). By focusing processing only on these active segments rather than the entire image, the system maintains thorough detection capability while significantly reducing computational load and processing time.
3Measurement precision
If grouping algorithms are used to eliminate transient detections, then people tally accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent applies grouping algorithms that consolidate transient detections by examining patterns across multiple frames before finalizing the count. By performing preliminary grouping and validation operations, the system eliminates false detections while maintaining manageable computational complexity through efficient algorithms that leverage temporal consistency.
Data Source
AI summary
Example apparatus disclosed herein include a memory and a processor to execute instructions to identify a first set of face rectangles and a second set of face rectangles in a frame pair of image data corresponding to a media environment, the first set of face rectangles corresponding to a first image sensor and the second set of face rectangles corresponding to a second image sensor, remove first face rectangles from the first set of face rectangles and the second set of face rectangles when the first face rectangles are determined to correspond to false positive face detections, group second face rectangles that remain in the first set of face rectangles and the second set of face rectangles after removal of the first face rectangles to form groups of face rectangles, and generate a count of people identified in the media environment based on a number of the groups.