Automated Smoke Detection Using Horizon-Based Image Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In the oil and gas industry, monitoring smoke on flaring equipment is costly due to the need for multiple thermal cameras and specialized equipment, making it impractical for widespread use, especially in environments where continuous on-site monitoring is not feasible.

Innovation Solution

A method and system that uses image processing techniques to detect objects of interest in images, such as smoke, by detecting the horizon in an image to define a candidate area and applying multiple image processing techniques to identify objects within that area, allowing for automated detection and alert generation using low-cost image capturing devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If thermal cameras and specialized equipment are used to detect smoke on flaring equipment, then detection reliability is improved, but device complexity and cost increase

Engineering Contradiction:
Improvesmoke detection reliabilityVSAvoidequipment complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces expensive thermal cameras with inexpensive standard digital cameras or smartphones that can detect smoke through image processing of visible light images. This substitution uses low-cost, widely available devices instead of specialized expensive equipment, directly resolving the contradiction between detection reliability and device complexity/cost.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The patent replaces thermal detection mechanisms with optical image capture and computational image processing. Instead of using thermal cameras that detect infrared radiation, the system uses standard cameras to capture visible light images and applies image processing techniques to detect smoke, thereby reducing device complexity while maintaining detection capability.

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

2Area of stationary object

If multiple thermal cameras are deployed to cover full scope of field operations, then detection coverage is improved, but device complexity and cost increase

Engineering Contradiction:
Improvedetection coverage areaVSAvoidnumber of cameras
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The patent makes a single standard camera perform multiple functions by equipping it with pan-tilt-zoom capabilities and image processing algorithms. The camera can scan different areas, adjust focus, and detect smoke through computational methods, allowing one device to replace multiple fixed thermal cameras and achieve comprehensive coverage without increasing device complexity.

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

Solution Approach 2:

The patent employs a dynamic pan-tilt-zoom camera system that can actively scan and adjust its field of view to cover the entire operational area. This dynamic positioning and zooming capability allows a single camera to achieve the coverage area of multiple fixed cameras, resolving the contradiction between detection coverage and number of devices.

Inventive Principle:
Principle #15Dynamics

3Device complexity

If visual monitoring by field personnel is used, then equipment complexity is reduced, but productivity and continuous monitoring capability deteriorate

Engineering Contradiction:
Improvemonitoring system complexityVSAvoidmonitoring efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The patent implements an automated smoke detection system that captures images, processes them through image processing algorithms, and generates alerts without human intervention. The system monitors itself continuously, eliminating the need for manual visual inspection by field personnel while significantly improving monitoring efficiency and productivity.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent establishes a closed-loop monitoring system where images are continuously captured, processed, and analyzed, with automated alerts generated when smoke is detected. This feedback mechanism enables continuous monitoring and rapid response without requiring constant human presence, resolving the contradiction between system simplicity and monitoring efficiency.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20230051823A1Systems, methods, and computer program products for image analysis
Publication Date: 2023.02.16 DEVON ENERGY CORP
  • US20230051823A1 patent drawing
  • US20230051823A1 patent drawing
  • US20230051823A1 patent drawing

AI summary

Image analytics systems, methods, and computer program products to autonomously analyze an image to identify and detect features in the image, such as the horizon, and/or identify and detect objects of interest therein, such as, smoke or possible smoke. The image is captured, for example, by RGB cameras, and depicts a scene to be analyzed. The intelligent image analytic system is configured to provide alerts and/or other information to one or more concerned parties and/or computing systems to take an appropriate response.