Abstract
Abstract. 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.
Highlights
Detection is the identification of unusual elements, occurrences or observations, which raise suspicions because of a significant deviation from the majority of data or expected behaviour
It is important to understand the effect of the saliency model parameters and their relationship to the Thermal InfraRed (TIR) and the optical images, the influence of the different training methods for the supervised learning of the second phase, and the influence of the temperature of the thermal anomaly candidates on the results of the classification
This paper suggests a two-phase classification approach for thermal anomaly detection from a combination of thermal, optical and height data
Summary
Detection is the identification of unusual elements, occurrences or observations, which raise suspicions because of a significant deviation from the majority of data or expected behaviour. The background of this study is the detection of leakages of underground district heating systems (DHS) Such leakages produce hot areas underneath the surface and possibly thermal anomalies on the surface, which typically cannot be detected in the visible spectrum from above. In passing, that a poorly insulated roof of a building is being detected using our approach It is, easy to separate the two cases, as we assume to have access to height data . In DS theory, a probability mass m A is assigned to every element A ∈ 2 by an information source such that 0 m A 1, m ∅ 0 and ∑ ∈ m A 1. Imprecise information can be handled by assigning a non-zero probability mass to the union of two or more classes. The DST allows the fusion of these probability masses from a variety of data sources to compute a combined probability mass for each
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have