Video Data Stream Storage with Background Subtraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current video data storage solutions are generic and inefficient, making video analytics a time-consuming and resource-intensive process, and data transfer between storage and analytics systems consumes excessive bandwidth and resources.
Innovation Solution
A system and method that employs background subtraction in moving object detection to reduce the search space and data transfer requirements, integrating video data storage and analytics by using a distributed computing and storage system with close-coupled processing elements, where raw video streams are processed to extract object characteristics and timestamps, and the background is subtracted to facilitate efficient data transfer and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of substance
If background subtraction is applied to reduce search space, then data transfer requirements are reduced, but processing complexity increases
Solution Approach 1:
The system performs background subtraction and object characteristic extraction in advance during the video stream processing stage, before data needs to be transferred to analytics systems. This preliminary processing reduces the amount of data that requires transfer by pre-identifying and filtering out background elements, thereby resolving the contradiction between reducing data transfer requirements and managing processing complexity.
Solution Approach 2:
The system extracts only the essential object characteristics and metadata from the video streams, separating these critical information elements from the full video data. By taking out only the necessary information for analytics processing, the system reduces data transfer requirements while maintaining the essential processing functions needed for object detection and analysis.
2Measurement precision
If video analytics processing is performed on all video data, then detection accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The system applies different processing qualities to different parts of the video data. Instead of uniformly processing all video frames, it focuses computational resources on specific regions of interest where objects are detected through background subtraction. This local quality approach maintains detection accuracy for critical objects while significantly reducing overall processing time and computational resource consumption.
Solution Approach 2:
The system segments the video processing task into distinct stages: background subtraction, object characteristic extraction, and analytics processing. By dividing the processing workload into manageable segments and performing them in sequence rather than simultaneously on all data, the system maintains detection accuracy while reducing total processing time through staged computation.
3Productivity
If data is transferred between storage and analytics systems, then analytics processing can be performed, but bandwidth and storage resources are consumed excessively
Solution Approach 1:
The system performs data filtering and characteristic extraction as preliminary actions during the video stream capture and storage phase. By pre-identifying and preparing only the essential object information and metadata before storage, the system enables analytics processing without requiring excessive data transfer between storage and analytics systems, thus resolving the contradiction between maintaining analytics capability and reducing bandwidth consumption.
Solution Approach 2:
The system introduces an intermediary processing layer that sits between the storage system and analytics system. This intermediary layer processes video streams in real-time, extracting only the necessary object characteristics and metadata for analytics, thereby mediating the data flow to reduce bandwidth consumption while preserving the essential analytics processing capability.
Data Source
AI summary
Video data stream storage comprising: receiving, by at least one processor, at least one raw video stream that has at least one object, recording, in at least one memory the at least one raw video stream, extracting, by the at least one processor, at least one object characteristic of the at least one object and at least one timestamp associated with the at least one object characteristic and recording, in the at least one memory the at least one object characteristic and the at least one timestamp associated with the at least one object characteristic.