Monitoring System Image Selection Architecture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Monitoring systems face increased calculation costs due to processing requirements for extracting and collating object images, as they typically perform extensive processing on all taken images or composite images, leading to resource inefficiencies.
Innovation Solution
A monitoring system architecture that divides the selection of best shot images into two steps between a monitoring terminal and a server, where the terminal performs initial selection with lower computational resources and transmits only the best images to the server for further processing, reducing the terminal's calculation load and transmission volume.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If characteristic extraction is performed for all taken images, then collation accuracy is improved, but calculation cost of the monitoring terminal is increased
Solution Approach 1:
The patent segments the image processing task into two parts: the monitoring terminal performs only object detection and transmits detected object images to a server, while the server performs the computationally intensive characteristic extraction and collation processing. This segmentation reduces the calculation burden on the terminal while maintaining collation accuracy through server-side processing.
2Measurement precision
If all taken images are used for collation processing, then collation accuracy is improved, but calculation cost of the monitoring terminal is increased
Solution Approach 1:
The patent extracts only the necessary object images from the full set of taken images based on detection results, and transmits only these extracted images to the server for collation. This extraction approach maintains collation accuracy by focusing on relevant images while reducing the terminal's calculation cost by avoiding processing of all images.
3Measurement precision
If image composition is performed using all taken images, then collation accuracy is improved, but calculation cost of the monitoring terminal is increased
Solution Approach 1:
The patent segments the image composition task by having the terminal compose images only from detected object regions and transmit these composed images to the server. The server then performs final image composition if needed. This segmentation maintains collation accuracy while significantly reducing the terminal's calculation cost.
Data Source
AI summary
According to one embodiment, a monitoring system includes a monitoring terminal and a server. The monitoring terminal includes a detector, a tracking unit, a first selector, and a transmitter. The server includes a receiver, a second selector, a collation unit, and an output unit. The receiver receives a first best shot images from the monitoring terminal. The second selector performs second selection processing, as part of a predetermined selection processing other than a first selection processing, of selecting a second best shot image suitable for collation with a predetermined image from among the first best shot images. The collation unit performs collation processing of collating the second best shot image with the predetermined image. The output unit outputs a result of the collation processing.