Multi-Sensor Surveillance System for Fire and Gas Leak Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional video surveillance systems rely solely on video cameras, which are inadequate for detecting events like fires or gas leaks, as they cannot provide complete environmental information in a timely manner, requiring extensive human resources for video retrieval and analysis.

Innovation Solution

A surveillance system utilizing a plurality of sensors, including cameras, microphones, taste sensors, smell sensors, and tactile sensors, that obtain multi-dimensional data, perform local-object processing to generate feature information, and global-object recognition to provide comprehensive scene monitoring.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If only video cameras are used for surveillance, then the system structure is simple, but the detection capability is insufficient for events like fires or gas leaks

Engineering Contradiction:
Improvedetection capabilityVSAvoidsystem structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple types of sensors (video cameras, audio sensors, smell sensors, taste sensors, tactile sensors) into a unified surveillance system. This merging of different sensing modalities enables comprehensive detection of various events including fires, gas leaks, and other environmental anomalies that single-sensor systems cannot detect reliably.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The surveillance system is designed to perform multiple detection functions simultaneously using different sensor types. Video cameras capture visual information, audio sensors detect sounds, smell sensors identify chemical compositions, taste sensors detect airborne particles, and tactile sensors sense physical conditions. This multi-functional approach allows a single system to handle diverse surveillance requirements.

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

2Reliability

If multiple sensors are integrated for comprehensive monitoring, then the detection capability improves, but the device complexity increases

Engineering Contradiction:
Improveenvironmental information completenessVSAvoidsensor integration
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the complex surveillance system into distinct functional modules, each responsible for processing data from specific sensor types. The computing device separately processes video data, audio data, smell data, taste data, and tactile data before integrating the results. This segmentation manages complexity by organizing multiple sensors into manageable, independent processing streams.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The computing device acts as an intermediary that receives data from multiple sensor types, processes each data stream independently, and integrates the results to generate comprehensive environmental information. This intermediary processing layer manages the complexity of multi-sensor integration by providing a centralized coordination point.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If video data is manually retrieved and inspected, then complete analysis is possible, but time consumption and human resources increase

Engineering Contradiction:
Improveevent detection speedVSAvoidvideo retrieval time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The surveillance system performs automatic event detection and analysis without requiring manual video retrieval and inspection. The computing device autonomously processes sensor data, identifies events of interest, and generates alerts. This self-service capability eliminates the need for human operators to manually review video footage, significantly reducing time consumption and human resource requirements.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual video retrieval and human inspection with automated computational processing. The computing device uses algorithms to analyze sensor data, detect patterns, and identify events automatically, substituting human cognitive work with machine-based processing that is faster and more efficient.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Adaptability or versatility

If single-type sensors are used, then the system is simple to operate, but the monitoring capability is limited

Engineering Contradiction:
Improvemonitoring capabilityVSAvoidsystem operation
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The surveillance system incorporates multiple sensor types that can detect various environmental conditions including visual changes, sounds, chemical compositions, airborne particles, and physical conditions. This multi-functional sensor array enables the system to adapt to diverse monitoring scenarios and detect a wide range of events using a unified operational interface.

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

Data Source

PatentEP3591633B1Surveillance system and surveillance method using multi-dimensional sensor data
Publication Date: 2020.12.16 WISTRON CORP
  • EP3591633B1 patent drawingFigure 1
  • EP3591633B1 patent drawingFigure 2
  • EP3591633B1 patent drawingFigure 3A

AI summary

A surveillance method using multi-dimensional sensor data for use in a surveillance system (100) is provided. The surveillance system (100) includes a plurality of sensors (110) installed within a scene, and the plurality of sensors (110) are classified into a plurality of types. The surveillance method includes the steps of: obtaining each type of sensor data from the scene using the sensors (110); performing a local-object process on each type of sensor data to generate local-object-feature information for each type; performing a global-object process according to the local-object-feature information of each type to generate global-object-feature information; and performing a global-object recognition process on the global-object-feature information to generate a global-recognition result.