Thermal Heap Monitoring with Dynamic ROI False Alarm Reduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Thermal cameras used for monitoring material heaps in recycling stations suffer from frequent false alarms due to the presence of machines with combustion engines, necessitating a method to reduce such false alarms.

Innovation Solution

A method and device that dynamically adjust the region of interest in thermal video streams by using spatial properties, such as spatial frequency, to ensure only the material heap remains within the monitored area, excluding non-heap regions, and set temperature thresholds for alarm generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a fixed region of interest is used to monitor the heap, then the monitoring setup is simple, but the system generates false alarms when the heap moves or changes size

Engineering Contradiction:

Improvealarm accuracyVSAvoidregion adjustment mechanism

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The region of interest is made dynamic by continuously adjusting its boundaries based on real-time spatial frequency analysis of the thermal video stream. The system automatically adapts the monitoring region to track the heap's movement and size changes, transforming a static fixed region into a dynamic adaptive region that maintains high alarm accuracy without requiring manual intervention.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the spatial frequency parameter threshold dynamically to distinguish between heap material and background elements. By adjusting the spatial frequency threshold based on the visual characteristics of the heap, the system can reliably identify heap boundaries and adjust the region of interest accordingly, improving alarm accuracy while maintaining automated operation.

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If the region of interest is expanded to cover potential heap positions, then movement is tracked, but false alarms increase due to inclusion of non-heap areas

Engineering Contradiction:

Improveheap tracking capabilityVSAvoidalarm false positive rate

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system applies different quality criteria to different regions within the video stream by using spatial frequency analysis. Instead of uniformly including or excluding areas, the system evaluates each region's spatial frequency characteristics and includes only those areas that match the heap's visual signature. This local quality assessment ensures the region of interest adapts to heap movement while maintaining high reliability by excluding non-heap areas.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system continuously monitors the spatial frequency distribution within the region of interest and uses this feedback to adjust the region boundaries. By analyzing the spatial frequency feedback from the thermal video stream, the system can distinguish between heap material and background elements, dynamically adjusting the region to track the heap while preventing false alarms from non-heap areas.

Inventive Principle:

Principle #23Feedback

3Reliability

If manual updating of region of interest is performed, then false alarms are reduced, but operational complexity and time consumption increase

Engineering Contradiction:

Improvemonitoring accuracyVSAvoidoperator intervention requirement

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system performs self-service by automatically adjusting its own region of interest based on real-time spatial frequency analysis of the thermal video stream. The automated region adjustment mechanism continuously monitors the heap's visual characteristics and adapts the monitoring region without requiring operator intervention, thereby maintaining high monitoring accuracy while eliminating manual updating requirements.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces the mechanical/manual process of region updating with an automated computational process based on spatial frequency analysis. Instead of requiring operator intervention to adjust region boundaries, the system uses image processing algorithms to automatically track the heap and adjust the region of interest, substituting manual operation with automated computational mechanics.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12578230B2Method and device for monitoring of a heap of material

Publication Date: 2026.03.17 AXIS

AI summary

A device for monitoring a heap of material, comprises circuitry for executing a plurality of functions. A region of interest function, in a thermal video stream captured by a thermal video camera, defines a region of interest covering the heap of material. A reference spatial property setting function, from pixels within a video frame of the thermal video stream, determines a spatial property of the heap of material; and sets the determined spatial property as a reference spatial property. A region of interest adjusting function determines a respective sample spatial property for regions in the thermal video stream; and adjusts the region of interest such that regions exhibiting a sample spatial property above a threshold are included by the region of interest. A temperature monitoring function over time and within the region of interest, monitors a temperature measure; and if it exceeds a predetermined threshold, generates an alarm event.