Object Identification System Reducing Remote Service Calls

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object identification systems face challenges in managing real-time or near real-time object identification for video content, as they require frequent service calls that consume significant bandwidth and processing power, making it difficult for third-party video systems to implement efficiently, especially in scenarios like security services where fast and accurate identification is crucial.

Innovation Solution

Implementing an object identification system that uses a processor to execute object detection and tracking algorithms on video frames, reducing the need for remote service calls by tracking identified objects within frames and only requesting identification from remote interfaces when objects are new or confidence thresholds are met, thereby minimizing service calls and resource usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If object identification is performed on each frame of video content using remote service calls, then identification accuracy is maintained, but bandwidth consumption and processing power requirements increase significantly

Engineering Contradiction:

Improveidentification accuracyVSAvoidbandwidth consumption

Core Design Contradiction:

Measurement precisionVSLoss of energy

Solution Approach 1:

The video processing system is divided into local and remote components. The local system performs object detection and tracking on each frame, while the remote service is only invoked when necessary (when objects are newly detected or leave the frame). This segmentation reduces bandwidth consumption by avoiding redundant remote calls while maintaining identification accuracy through selective remote verification.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary object detection and tracking locally before making remote service calls. By pre-processing frames locally to identify objects of interest and track their movement, the system reduces the number of remote calls needed, thereby reducing bandwidth consumption while maintaining accurate identification through the preliminary local analysis.

Inventive Principle:

Principle #10Preliminary action

2Speed

If object identification service calls are made for every frame, then real-time identification is achieved, but processing power consumption increases

Engineering Contradiction:

Improvereal-time identification speedVSAvoidprocessing power consumption

Core Design Contradiction:

SpeedVSUse of energy by stationary object

Solution Approach 1:

Processing tasks are segmented between local and remote systems. The local system handles frame-by-frame object detection and tracking at high speed, while the remote system only processes identification requests when necessary. This segmentation enables real-time identification speed through efficient local processing while reducing overall processing power consumption by minimizing remote service calls.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of performing full object identification processing on every frame, the system performs partial processing locally (detection and tracking) and only invokes remote identification services when necessary (when objects are newly detected or leave the frame). This partial action approach maintains real-time identification capability while significantly reducing processing power consumption compared to full remote processing of every frame.

Inventive Principle:

Principle #16Partial or excessive action

3Reliability

If remote object identification services are called frequently, then accurate object tracking is maintained, but service costs and bandwidth usage increase

Engineering Contradiction:

Improveobject tracking accuracyVSAvoidservice calls volume

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The identification system is segmented into local detection/tracking functions and remote identification functions. The local system maintains continuous object tracking across frames using detection results, while remote services are only called when objects are newly detected or leave the frame. This segmentation reduces service calls volume while maintaining tracking accuracy through the local tracking system that bridges gaps between remote calls.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The local object tracking system maintains continuous tracking of detected objects across video frames, providing uninterrupted identification information. This continuous local tracking action reduces the need for frequent remote service calls, thereby reducing service calls volume and bandwidth usage while maintaining reliable object tracking accuracy through the continuous local tracking process.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS11798251B2Object identification system with reduced service calls

Publication Date: 2023.10.24 COHEN TRACEY

AI summary

Methods and systems for implementing an object identification system equipped to reduce the number of service calls for remote object identification lookups are disclosed. The object identification management server works to reduce the number of object identification requests, which overall improves the process of quickly and accurately providing object identifications when needed and without unnecessarily wasting computing resources. The object identification server can subsequently manage the number of identification requests by setting a tunable threshold, which allows a system to operate more efficiently and allocate computing resources accordingly.