TY - JOUR

T1 - THERMAL ANOMALY DETECTION BASED on SALIENCY ANALYSIS from MULTIMODAL IMAGING SOURCES

AU - Sledz, A.

AU - Heipke, C.

N1 - Funding Information: The work is supported by the Arbeitsgemeinschaft industrieller Forschungsvereinigungen (AiF) under IGF-grant no. 19768 N. This support is gratefully acknowledged. The authors would like to thank our partners Fernwärme-Forschungsinstitut (FFI) GmbH, Hemmingen (Germany) and Enercity AG, Hannover (Germany), and in particular Volker Herbst (FFI) and Werner Manthey (Enercity) for their strong support.

PY - 2021/6/17

Y1 - 2021/6/17

N2 - Thermal anomaly detection has an important role in remote sensing. One of the most widely used instruments for this task is a Thermal InfraRed (TIR) camera. In this work, thermal anomaly detection is formulated as a salient region detection, which is motivated by the assumption that a hot region often attracts attention of the human eye in thermal infrared images. Using TIR and optical images together, our working hypothesis is defined in the following manner: a hot region that appears as a salient region only in the TIR image and not in the optical image is a thermal anomaly. This work presents a two-step classification method for thermal anomaly detection based on an information fusion of saliency maps derived from both, TIR and optical images. Information fusion, based on the Dempster-Shafer evidence theory, is used in the first phase to find the location of regions suspected to be thermal anomalies. This classification problem is formulated as a multi-class problem and is carried out in an unsupervised manner on a pixel level. In the following phase, classification is formulated as a binary region-based problem in order to differentiate between normal temperature variations and thermal anomalies, while Random Forest (RF) is chosen as the classifier. In the seconds phase, the classification results from the previous phase are used as features along with temperature information and height details, which are obtained from a Digital Surface Model (DSM). We tested the approach using a dataset, which was collected from a UAV with TIR and optical cameras for monitoring District Heating Systems (DHS). Despite some limitations outlined in the paper, the presented innovative method to identify thermal anomalies has achieved up to 98.7 percent overall accuracy.

AB - Thermal anomaly detection has an important role in remote sensing. One of the most widely used instruments for this task is a Thermal InfraRed (TIR) camera. In this work, thermal anomaly detection is formulated as a salient region detection, which is motivated by the assumption that a hot region often attracts attention of the human eye in thermal infrared images. Using TIR and optical images together, our working hypothesis is defined in the following manner: a hot region that appears as a salient region only in the TIR image and not in the optical image is a thermal anomaly. This work presents a two-step classification method for thermal anomaly detection based on an information fusion of saliency maps derived from both, TIR and optical images. Information fusion, based on the Dempster-Shafer evidence theory, is used in the first phase to find the location of regions suspected to be thermal anomalies. This classification problem is formulated as a multi-class problem and is carried out in an unsupervised manner on a pixel level. In the following phase, classification is formulated as a binary region-based problem in order to differentiate between normal temperature variations and thermal anomalies, while Random Forest (RF) is chosen as the classifier. In the seconds phase, the classification results from the previous phase are used as features along with temperature information and height details, which are obtained from a Digital Surface Model (DSM). We tested the approach using a dataset, which was collected from a UAV with TIR and optical cameras for monitoring District Heating Systems (DHS). Despite some limitations outlined in the paper, the presented innovative method to identify thermal anomalies has achieved up to 98.7 percent overall accuracy.

KW - Dempster-Shafer theory

KW - Distributed heating systems

KW - Random Forest

KW - Saliency map

KW - Thermal anomaly

KW - Thermal infrared imaging

UR - http://www.scopus.com/inward/record.url?scp=85119684255&partnerID=8YFLogxK

U2 - 10.5194/isprs-annals-V-1-2021-55-2021

DO - 10.5194/isprs-annals-V-1-2021-55-2021

M3 - Conference article

AN - SCOPUS:85119684255

VL - 5

SP - 55

EP - 64

JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SN - 2194-9042

IS - 1

T2 - 2021 24th ISPRS Congress "Imaging Today, Foreseeing Tomorrow", Commission I

Y2 - 5 July 2021 through 9 July 2021

ER -