Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel
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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9454439/ |
| _version_ | 1818652148967145472 |
|---|---|
| author | Tung-Han Hsieh Chao-Lung Chou Yu-Pin Lan Pin-Hsuan Ting Chun-Ting Lin |
| author_facet | Tung-Han Hsieh Chao-Lung Chou Yu-Pin Lan Pin-Hsuan Ting Chun-Ting Lin |
| author_sort | Tung-Han Hsieh |
| collection | DOAJ |
| description | 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 <inline-formula> <tex-math notation="LaTeX">$2\times 2$ </tex-math></inline-formula>. |
| first_indexed | 2024-12-17T02:17:24Z |
| format | Article |
| id | doaj.art-7e99d674a05e449b9a6507c6b41d403e |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T02:17:24Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7e99d674a05e449b9a6507c6b41d403e2022-12-21T22:07:21ZengIEEEIEEE Access2169-35362021-01-019948899490010.1109/ACCESS.2021.30893769454439Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient KernelTung-Han Hsieh0https://orcid.org/0000-0002-1574-0808Chao-Lung Chou1https://orcid.org/0000-0001-7811-9501Yu-Pin Lan2Pin-Hsuan Ting3https://orcid.org/0000-0002-1395-698XChun-Ting Lin4https://orcid.org/0000-0001-5243-6242Institute of Photonic System, National Yang Ming Chiao Tung University, Guiren District, Tainan, TaiwanDepartment of Computer Science and Information Engineering, Chung Cheng Institute of Technology, National Defense University, Taoyuan, TaiwanInstitute of Lighting and Energy Photonics, National Yang Ming Chiao Tung University, Guiren District, Tainan, TaiwanInstitute of Imaging and Biomedical Photonics, National Yang Ming Chiao Tung University, Tainan, TaiwanInstitute of Photonic System, National Yang Ming Chiao Tung University, Guiren District, Tainan, TaiwanInfrared (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 <inline-formula> <tex-math notation="LaTeX">$2\times 2$ </tex-math></inline-formula>.https://ieeexplore.ieee.org/document/9454439/Infrared (IR) small target detectionsignal-to-noise ratio (SNR)infrared search and track (IRST)human visual system (HVS)layered gradient kernel (LGK)real-time |
| spellingShingle | Tung-Han Hsieh Chao-Lung Chou Yu-Pin Lan Pin-Hsuan Ting Chun-Ting Lin Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel IEEE Access Infrared (IR) small target detection signal-to-noise ratio (SNR) infrared search and track (IRST) human visual system (HVS) layered gradient kernel (LGK) real-time |
| title | Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel |
| title_full | Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel |
| title_fullStr | Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel |
| title_full_unstemmed | Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel |
| title_short | Fast and Robust Infrared Image Small Target Detection Based on the Convolution of Layered Gradient Kernel |
| title_sort | fast and robust infrared image small target detection based on the convolution of layered gradient kernel |
| topic | Infrared (IR) small target detection signal-to-noise ratio (SNR) infrared search and track (IRST) human visual system (HVS) layered gradient kernel (LGK) real-time |
| url | https://ieeexplore.ieee.org/document/9454439/ |
| work_keys_str_mv | AT tunghanhsieh fastandrobustinfraredimagesmalltargetdetectionbasedontheconvolutionoflayeredgradientkernel AT chaolungchou fastandrobustinfraredimagesmalltargetdetectionbasedontheconvolutionoflayeredgradientkernel AT yupinlan fastandrobustinfraredimagesmalltargetdetectionbasedontheconvolutionoflayeredgradientkernel AT pinhsuanting fastandrobustinfraredimagesmalltargetdetectionbasedontheconvolutionoflayeredgradientkernel AT chuntinglin fastandrobustinfraredimagesmalltargetdetectionbasedontheconvolutionoflayeredgradientkernel |