A novel infrared small moving target detection method based on tracking interest points under complicated background
Section snippets
Introduce
Infrared (IR) technology has a wide application in the areas of pre-warning, precision-guide and so on, because it can be used in all kinds of weather. The ability to detect targets in infrared images or videos has a major impact on these applications. In these applications targets are always far away from imaging equipment, as a result, targets in the sensed IR images or videos are usually very dim, small and shapeless. Besides, IR images have a low Signal-to-Noise Ratio (SNR) and the
The proposed methods
In this section, a novel detection algorithm of infrared small moving targets is proposed. The process of this algorithm includes three steps. Fig. 1 gives the framework of this method. The following subsections give a detailed description of each part of the algorithm respectively.
Step 1: Extracting interest points with the means of DOG filters in the first frame. The moving targets should be included in these interest points.
Step 2: Tracking these interest points for several frames in order
Parameters analysis and experimental results
To evaluate the target detection performance, the proposed method is compared with other five sophisticated methods which are high-pass filter method, Max-median method [7], Max-mean method [7], Zhang’s method [9] and Bae’s method [11] by using a mass of image sequences. In this paper, we just present the results of six sequences (Seq1-Seq6). The backgrounds of Seq1–Seq4 are dynamic, and the other two are static. There are several parameters needed in the proposed method, so we analyze the
Conclusions
This paper introduces a novel infrared small moving target detection method based on tracking interest points under complicated background. Firstly, DOG filters are used to detect a group of interest points (including the moving targets). Secondly, a sort of small targets tracking method inspired by Human Visual System (HVS) is used to track these interest points for several frames, and then the relations between interest points in the first frame and the last frame are obtained. Last, a new
Conflict of interest
We declare that we have no conflict of interest.
References (14)
- et al.
Infrared dim small target enhancement using toggle contrast operator
Infrared Phys. Technol.
(2012) - et al.
Infrared point target detection with improved template matching
Infrared Phys. Technol.
(2012) - et al.
Moving dim point target detection with three-dimensional wide-to-exact search directional filtering
Pattern Recognit. Lett.
(2007) - et al.
Detecting and tracking dim moving point target in ir image sequence
Infrared Phys. Technol.
(2005) Small target detection using bilateral filter and temporal cross product in infrared images
Infrared Phys. Technol.
(2011)- et al.
Infrared dim and small target detecting and tracking method inspired by human visual system
Infrared Phys. Technol.
(2014) - X. Bai, Morphological operator for infrared dim small target enhancement using dilation and erosion through structuring...
Cited by (47)
IR saliency detection via a GCF-SB visual attention framework
2020, Journal of Visual Communication and Image RepresentationCitation Excerpt :IR saliency detection has been widely used in a lot of areas, such as remote sensing, target detection, and aerospace etc. [1,2]. Due to the low contrast, blurred edge and heavy background clutter of IR images, detecting saliency accurately has always been a challenging task [3,4]. The grayscale of a target is generally higher than that of the surrounding background region, but it is not necessarily higher than that of other regions of the image, and noise from sensors, environment and background may cause the grayscale of local regions higher than that of a target, resulting in low detection accuracy [2].
Vehicle Detection in High Density Traffic Surveillance Data using YOLO.v5
2024, Recent Advances in Electrical and Electronic Engineering