Recently, thermal cameras have been used in various surveillance and monitoring systems. In particular, in camera-based surveillance systems, algorithms are being developed for detecting and recognizing objects from images acquired in dark environments. However, it is difficult to detect and recognize an object due to the thermal reflections generated in the image obtained from a thermal camera. For example, thermal reflection often occurs on a structure or the floor near an object, similar to shadows or mirror reflections. In this case, the object and the areas of thermal reflection overlap or are connected to each other and are difficult to separate. Thermal reflection also occurs on nearby walls, which can be detected as artifacts when an object is not associated with this phenomenon. In addition, the size and pixel value of the thermal reflection area vary greatly depending on the material of the area and the environmental temperature. In this case, the patterns and pixel values of the thermal reflection and the object are similar to each other and difficult to differentiate. These problems reduce the accuracy of object detection and recognition methods. In addition, no studies have been conducted on the elimination of thermal reflection of objects under different environmental conditions. Therefore, to address these challenges, we propose a method of detecting reflections in thermal images based on deep learning and their elimination via post-processing. Experiments using a self-collected database (Dongguk thermal image database (DTh-DB), Dongguk items and vehicles database (DI&V-DB)) and an open database showed that the performance of the proposed method is superior compared to that of other state-of-the-art approaches.

Introduction

Recently, in various fields, data analysis, object detection, pattern recognition, etc. have been performed using a longwavelength infrared (LWIR) camera. LWIR cameras can measure electromagnetic radiation (EMR) in the range of 8–۱۲ µm [1]. Most of the thermal radiation emitted from living bodies and objects is infrared, and in many cases, LWIR cameras are used to measure heat information. Therefore, the LWIR camera is also called a thermal camera. Figure 1 shows the example of visible light and thermal images with thermal camera. Thermal cameras can enhance the visibility of near and far objects in dark environments without additional illuminators. However, it is difficult to detect and recognize an object due to the thermal reflections generated in the image obtained using a thermal camera. The EMR emitted by object reflects off the floor or walls nearby, creating shadow-like areas around the object. This is called the thermal reflection of the object. The pattern, size, and pixel value of thermal reflections vary greatly depending on the material, the generated heat in the range of reflection, the temperature of the object and the surrounding environment. For example, in an 8-bit thermal image, the pixels in the area of thermal reflection can have any value between 0–۲۵۵٫