Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel

Tung-Han Hsieh,Chao-Lung Chou,Pin-Hsuan Ting,Chun-Ting Lin,Yu-Pin Lan

doi:10.1109/access.2021.3089376

Tung-Han Hsieh, Chao-Lung Chou + Show 3 more

Open Access

PDF Available

https://doi.org/10.1109/access.2021.3089376

Copy DOI

Export

Save

Cite

Abstract
Highlights/Summary
Full-Text PDF
Similar Papers

Abstract

Listen

Infrared (IR) small target detection is challenging because the IR imaging lacks detailed features, weak shape features, and a low signal-to-noise ratio (SNR). The existing small IR target detection methods usually focus on improving their high detective performance without considering the execution time. However, high-speed detection is vital for various applications, such as early warning systems, military surveillance, infrared search and track (IRST), etc. This paper proposes a fast and robust single-frame IR small target detection algorithm with a low computational cost while maintaining excellent detection performance. We propose a layered gradient kernel (LGK) based on the contrast properties of the human visual system (HVS) and model it through a three-layer patch image model. The layered gradient kernel is used to convolute with the input IR frame to obtain its gradient map. The target detection is further performed on the acquired gradient map with an adaptive threshold method. This method is compared with eight representative small target detection algorithms to evaluate the performance. Experimental results demonstrate that the algorithm is fast and suitable for real-time applications, and it is very effective even when the small target size is as small as 2×2.

Highlights

Target detection techniques in infrared (IR) images have been widely used in many applications, such as early warning systems, military surveillance, infrared search and track (IRST), medical images, and so on [1], [2]
This paper proposes a fast and robust single-frame infrared small target detection algorithm based on the human visual system and the convolution of the layered gradient kernel
Experimental results show the excellent detection performance in which detection rate is as high as 100% for Test Data 1‒4 and false alarm rate is as low as 0% for Test Data 2‒4 and 6.25% for Test Data 1

Summary

Introduction

Target detection techniques in infrared (IR) images have been widely used in many applications, such as early warning systems, military surveillance, infrared search and track (IRST), medical images, and so on [1], [2]. A lot of small IR target detection methods have been designed over the last two decades. These methods focus mostly on how to enhance the target and suppress background regions as much as possible. Single frames-based methods usually highlight the target through pre-processing and use a threshold to segment the target within the image. They are low computation cost, easy for hardware implementation, suitable for real-time applications, and are widely used in practice. Sequential framesbased methods deal with the spatial-temporal domain and separate the small target from a series of images through the prior information such as the small target’s shape, the grayscale change, and the motion path.

Methods

Results

Conclusion