A novel infrared small moving target detection method based on tracking interest points under complicated background

doi:10.1016/j.infrared.2014.03.007

Infrared Physics & Technology

Volume 65, July 2014, Pages 36-42

https://doi.org/10.1016/j.infrared.2014.03.007 Get rights and content

Highlights

•
A moving target detection method based on tracking interest points is proposed.
•
A novel clustering method named as R-means is proposed.
•
These interest points are divided into target points and background points.

Abstract

Infrared moving target detection is an important part of infrared technology. We introduce a novel infrared small moving target detection method based on tracking interest points under complicated background. Firstly, Difference of Gaussians (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 correlations between interest points in the first frame and the last frame are obtained. Last, a new clustering method named as R-means is proposed to divide these interest points into two groups according to the correlations, one is target points and another is background points. In experimental results, the target-to-clutter ratio (TCR) and the receiver operating characteristics (ROC) curves are computed experimentally to compare the performances of the proposed method and other five sophisticated methods. From the results, the proposed method shows a better discrimination of targets and clutters and has a lower false alarm rate than the existing moving target detection methods.

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)

X. Bai et al.
Infrared dim small target enhancement using toggle contrast operator
Infrared Phys. Technol.
(2012)
R. Liu et al.
Infrared point target detection with improved template matching
Infrared Phys. Technol.
(2012)
T. Zhang et al.
Moving dim point target detection with three-dimensional wide-to-exact search directional filtering
Pattern Recognit. Lett.
(2007)
F. Zhang et al.
Detecting and tracking dim moving point target in ir image sequence
Infrared Phys. Technol.
(2005)
T. Bae
Small target detection using bilateral filter and temporal cross product in infrared images
Infrared Phys. Technol.
(2011)
X. Dong 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...

There are more references available in the full text version of this article.

Cited by (47)

IR saliency detection via a GCF-SB visual attention framework
2020, Journal of Visual Communication and Image Representation
Citation 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].
Infrared (IR) saliency detection with high detection accuracy is a challenging task due to the complex background and low contrast of IR images. In this paper, an IR saliency detection method via a new visual attention framework is proposed, which comprises two phases. In the first phase, a Gray & Contrast Features (GCF) model is established, in which the IR image is processed in two feature channels, a gray feature channel and a contrast feature channel. And then a primary feature map can be obtained by fusing the gray and contrast features from these two channels, which is the basis of the second phase. In the second phase, a Similarity-based Bayes (SB) model is established, in which two prior probabilities and two likelihood functions are calculated according to the previously obtained primary feature map. Finally, the saliency map is calculated with the obtained prior probabilities and likelihood functions by Bayes formula. Experimental results indicate that the proposed method can effectively reduce noise and enhance contrast of IR images with complex background and low contrast, and obtain a higher detection accuracy and robustness than seven state-of-the-art methods.
Vehicle Detection in High Density Traffic Surveillance Data using YOLO.v5
2024, Recent Advances in Electrical and Electronic Engineering
Infrared Small Dim Target Detection Using Group Regularized Principle Component Pursuit
2024, Remote Sensing
Infrared Dim and Small Target Detection Based on Superpixel Segmentation and Spatiotemporal Cluster 4D Fully-Connected Tensor Network Decomposition
2024, Remote Sensing
Small Object Detection and Tracking: A Comprehensive Review
2023, Sensors
Pearson's correlation and background subtraction (BGS) based approach for object's motion detection in infrared video frame sequences
2023, Statistical Papers

View all citing articles on Scopus

View full text

A novel infrared small moving target detection method based on tracking interest points under complicated background

Highlights

Abstract

Section snippets

Introduce

The proposed methods

Parameters analysis and experimental results

Conclusions

Conflict of interest

Infrared Phys. Technol.

Infrared Phys. Technol.

Pattern Recognit. Lett.

Infrared Phys. Technol.

Infrared Phys. Technol.

Infrared Phys. Technol.