Sensibility analysis of the object tracking algorithms in thermal image

Abstract

In military application target tracking has always been an interesting and challenging problem. Nowadays, it has also found its place in civil applications, especially concerning surveillance and monitoring. Until recently, thermal imagery (image is formed based on infrared spectrum radiation) was considered only in military applications because of the price and size of cameras. Also, thermal image quality was not as good as TV (image is formed based on visual spectrum radiation) camera image. The situation has changed, and thermal cameras are now widely used in many kinds of applications. Thermal image is different from TV camera image, as it measures temperature difference between objects and background. Therefore, it has an advantage over television cameras, since it can be used in low light conditions and in dark. This paper examines the options for a coarse and quick algorithm for rough target locating in thermal image, where the target is a small Unmanned Aerial Vehicle (UAV). Three different feature descriptor algorithms are tested in thermal imagery target tracking. Feature descriptor methods are widely used in visual imagery, but the goal of this paper is to examine their usage in thermal imagery. That is why three different feature descriptor algorithms from three different families are tested: FREAK (Fast Retina Keypoint), SURF (Speeded Up Robust Features) and MSER (Maximally Stable Extremal Regions). The algorithms are tested in case of translation, rotation, blur and size change of an object of interest, as well as in the case of noisy image. Since none of the tested methods works great in different situations, new, multi-stage algorithm is proposed. This algorithm is based on MSER and SURF algorithm combination, with a goal to use the advantages of each of them in different real situations. The obtained results show that the new, multi-stage algorithm has got the best performance among the group of the tested methods. All the algorithms are implemented in Matlab software.

Rolling 3D Laplacian Pyramid Video Fusion

“…Figure 3 shows a multi-sensor view, in this case IR and TV images, of the same scene. The IR image clearly shows a human figure but not the general structure of the scene [57,58], while it is not immediately detectable in the TV image. Figure 4 shows a fused image using the Laplacian pyramid fusion [27].…”

“…Finally, the third category is made up of so-called 3D algorithms [54][55][56][57][58][59]. These algorithms represent an extension of the conventional static image fusion algorithms into 3D space.…”

Robust tracking of moving objects using thermal camera and speeded up robust features descriptor

“…Using integral images, it is possible to calculate rectangular box filters in nearly constant time. 28 Scale spaces are usually implemented as pyramids of decreasing image resolutions. However, the use of box filters and integral images shortens the procedure and the images can be filtered in parallel by using box filters of different sizes (9 × 9, 15 × 15, 21 × 21 … ) and for different scaling factors .…”

“…Algorithms that use object descriptors, such as SIFT 11,23 or SURF 13,[24][25][26][27] are very popular in object tracking because they are robust to partial occlusions, scaling, and rotation. 28 However, not all descriptors can be employed with the same efficiency in both visual and thermal domains because the characteristics of the images differ considerably. Thermal images have no shadows, noise characteristics differ from those in the visual domain, 29,30 and since they have no color and different patterns and shapes based on variations in object material and temperature occur in images.…”

“…Thermal images have no shadows, noise characteristics differ from those in the visual domain, 29,30 and since they have no color and different patterns and shapes based on variations in object material and temperature occur in images. Speeded up robust features (SURF) descriptors yield good results in object tracking in the thermal domain 28,31 and are thus a good solution for that domain.…”