DVS Sensor Subject Sameness Detection for Cloud Server Load Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As the number of network cameras increases, the traffic of redundant video data obtained by shooting the same subject leads to increased loads and conflicts in cloud servers, potentially resulting in incorrect data processing.
Innovation Solution
A data processing device and method that control data transfer of image frame data based on determining the sameness of subjects using Dynamic Vision Sensor (DVS) data, which outputs temporal luminance changes as event data, allowing for frame-based control of data transfer and transmission only when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of network cameras is increased to improve monitoring coverage, then the monitoring capability is improved, but the network traffic and processing load on cloud servers increase
Solution Approach 1:
The patent extracts only the essential information from video data by using DVS sensors to detect temporal luminance changes and generate event data. This event data contains only the necessary information about subject movements and changes, eliminating redundant static background information. By transmitting only this extracted essential data to the cloud server, network traffic is significantly reduced while maintaining monitoring coverage with multiple cameras.
2Loss of information
If all image frame data from multiple cameras is transmitted to the cloud server, then complete data is available for processing, but the processing load and conflicts in cloud servers increase
Solution Approach 1:
The system extracts only relevant temporal changes from complete video frames using DVS sensors, converting full-frame data into compact event data that represents only meaningful changes. This extraction process maintains all necessary information for subject recognition and tracking while removing redundant static information, thereby reducing cloud server processing load without compromising data completeness for analysis.
Solution Approach 2:
Instead of transmitting complete image frames and then processing them to extract useful information, the system inverts the approach by first detecting temporal changes with DVS sensors and generating event data that directly represents meaningful information. This inversion eliminates the need to process and filter large amounts of redundant frame data in the cloud, significantly improving processing efficiency while maintaining data completeness.
3Loss of information
If redundant video data from multiple cameras shooting the same subject is transmitted, then all camera perspectives are preserved, but network bandwidth and server resources are wasted
Solution Approach 1:
The system extracts temporal luminance change information from video data using DVS sensors, which naturally filters out static background information and focuses only on dynamic elements. When multiple cameras capture the same subject, the DVS event data from each camera captures the temporal changes specific to that camera's perspective. This extraction approach preserves essential perspective information about subject movements while eliminating redundant static information, reducing network bandwidth consumption without losing critical observational data.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach reduces network traffic and processing loads on cloud servers by selectively transmitting image frame data, ensuring efficient and accurate recognition processing.
Implementation Method 1
sensors that output temporal luminance changes in optical signals as event data
Data Source
AI summary
The present disclosure relates to a data processing device and method, and a data processing system, capable of reducing application loads in a cloud server by controlling sensor data flowing over a network.A sensor data monitor controls, based on a result of determining a sameness of subjects using DVS data output from DVS sensors that output temporal luminance changes in optical signals as event data, data transfer of image frame data in which the subjects have been shot on a frame basis. The present disclosure can be applied in, for example, an image network system or the like that transmits image frame data shot on a frame basis.