Multi-Camera Query Update for Object Tracing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current multi-camera image analysis systems are inefficient in tracing a specific target object across multiple cameras due to fixed query information, leading to prolonged search times, especially during emergencies.

Innovation Solution

A method for updating query information by searching for and incorporating features from images matching the query image, using a multi-camera system with an image analysis server that extracts and updates query features based on found images, improving matching performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If fixed query information is used for object search in multi-camera system, then system complexity is reduced, but search time increases significantly

Engineering Contradiction:
Improvesearch timeVSAvoidsystem complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by pre-processing images from multiple cameras and pre-extracting features before a search query is submitted. Query images are pre-processed and their features are extracted in advance, so when a search is needed, the system can quickly compare pre-computed features rather than processing everything from scratch, significantly reducing search time without adding operational complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adapts query information by iteratively updating query features based on matching results from multiple cameras. Instead of using fixed query information, the system refines query features through multiple rounds of comparison and updating, allowing the search to adapt to the actual distribution of target objects across different camera views, thereby improving search efficiency.

Inventive Principle:
Principle #15Dynamics

2Productivity

If fixed query information is used for tracing target object, then ease of operation is improved, but productivity decreases

Engineering Contradiction:
Improveobject tracing efficiencyVSAvoidoperation simplicity
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system performs self-service by automatically updating query information using matching results from multi-camera comparisons. After initial query processing, the system uses found matches to refine and update query features, which are then used to improve subsequent searches. This self-updating mechanism continuously improves tracing efficiency without requiring manual intervention or complex user operations.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system implements feedback by using the results of each search round to update and refine query information for the next round. Matching results from multiple cameras provide feedback that is used to adjust query features, creating a closed-loop system that continuously improves its performance. This feedback mechanism enables the system to learn from each search iteration and improve overall tracing productivity.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If query information is updated using found images, then matching precision is improved, but device complexity increases

Engineering Contradiction:
Improveobject matching precisionVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies segmentation by dividing the image processing into distinct modules: image acquisition from multiple cameras, feature extraction, query-image comparison, and query information updating. Each module handles a specific task independently, making the complex processing pipeline manageable and maintainable. The feature extraction module specifically segments relevant object features from background elements, improving matching precision while keeping processing organized.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system achieves universality by designing a multi-functional image processing framework that handles multiple camera inputs, performs feature extraction, conducts similarity comparison, and updates query information within a unified system. This multi-functional approach allows the same processing pipeline to handle various search scenarios across different cameras and conditions, improving matching precision without requiring separate specialized systems for each function.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS11853350B2Method for updating query information for tracing target object from multi-camera and multi-camera system performing the same
Publication Date: 2023.12.26 KOREA INST OF SCI & TECH
  • US11853350B2 patent drawing
  • US11853350B2 patent drawing
  • US11853350B2 patent drawing

AI summary

Embodiments relate to a method for updating query information for tracing a target object from multi-camera including receiving a query information update command including query information for tracing a target object from multi-camera, searching for at least one image displaying the target object among a plurality of images captured by the multiple cameras, and updating the query information of a query image based on the at least one found image, and a multi-camera system performing the same.