Flexible Container Architecture for Scalable Digital Image Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current digital image analysis systems are inflexible, unreliable, and limited in scalability, often requiring significant updates or replacements for modifying image analysis tasks, which can lead to downtime, vulnerabilities, and performance issues when handling multiple concurrent image streams from multiple cameras.

Innovation Solution

A flexible computer architecture combining containers, a distributed messaging platform, and an on-premises computing cluster with cloud integration, allowing for dynamic scaling and easy model adjustments, enabling fault-tolerant and scalable digital image analysis across various applications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a traditional digital image analysis system is used, then the system structure is simple, but the system is inflexible and requires significant updates or replacements for modifying image analysis tasks

Engineering Contradiction:

Improveflexibility of image analysis tasksVSAvoidsystem architecture complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system is divided into independent containers (image analysis container, post-processing container, output container) that can be individually modified, updated, or replaced without affecting the entire system. Each container performs a specific function in the image analysis pipeline, allowing flexible task modification through container orchestration rather than system-wide updates.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system employs dynamic container orchestration that allows runtime adjustments to image analysis tasks. Containers can be started, stopped, scaled, or reconfigured based on changing requirements, enabling the system to adapt to different image analysis tasks without requiring structural changes or downtime.

Inventive Principle:

Principle #15Dynamics

2Reliability

If traditional image analysis systems are used, then the software structure is simple, but significant updates or replacements are needed which lead to downtime

Engineering Contradiction:

Improvesystem availabilityVSAvoiddowntime during updates

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

Multiple container instances can be prepared in advance and orchestrated to take over from each other. The system maintains a pool of ready-to-deploy containers that can immediately assume processing responsibilities when updates are needed, ensuring continuous operation without downtime.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

A container orchestration platform acts as an intermediary that manages the transition between container versions. The orchestrator coordinates the deployment of updated containers while maintaining service continuity, allowing updates to occur without interrupting the image analysis workflow.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If traditional image analysis systems are used, then the system architecture is simple, but the system has limited scalability for handling multiple concurrent image streams

Engineering Contradiction:

Improveprocessing capacity for multiple camera streamsVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

Containers are designed to be universal and stateless, allowing the same container image to handle different camera streams and image analysis tasks. The system can scale horizontally by deploying additional identical or customized container instances, each capable of processing concurrent image streams independently, thereby increasing productivity without proportionally increasing architectural complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Productivity

If traditional image analysis systems are used, then the software structure is simple, but the system has performance issues when handling multiple concurrent image streams

Engineering Contradiction:

Improveprocessing speed of multiple image streamsVSAvoidsystem performance stability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The image analysis workload is segmented across multiple independent container instances that process different camera streams in parallel. Each container handles a specific portion of the total processing load, preventing any single point of failure and maintaining performance stability even as the number of concurrent streams increases.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11734919B1Flexible computer architecture for performing digital image analysis

Publication Date: 2023.08.22 SAS INSTITUTE INC

AI summary

A flexible computer architecture for performing digital image analysis is described herein. In some examples, the computer architecture can include a distributed messaging platform (DMP) for receiving images from cameras and storing the images in a first queue. The computer architecture can also include a first container for receiving the images from the first queue, applying an image analysis model to the images, and transmitting the image analysis result to the DMP for storage in a second queue. Additionally, the computer architecture can include a second container for receiving the image analysis result from the second queue, performing a post-processing operation on the image analysis result, and transmitting the post-processing result to the DMP for storage in a third queue. The computer architecture can further include an output container for receiving the post-processing result from the third queue and generating an alert notification based on the post-processing result.