Abstract
Small target detection in high strength clutter background is in great in remote imaging system, a new improved spatio-temporal filtering was proposed in this paper. Firstly, traditional anisotropy filtering has poor suppression effect in strength edge contour region, so a new diffusion filtering function proposed in paper. According to the analysis with difference of each component of the image, a new anisotropy diffusion function is constructed in this paper. When the difference of background and target is small, this algorithm will give in large diffusion coefficient to filter most background clutter and retain target signal well which achieves background prediction better. Secondly, because the traditional spatiotemporal filter algorithm cant follow the motion object in the fixed search pipe diameter what will make lose the target detection, a new weight constraint function of adaptive change of the search diameter in this paper is built which can change the search diameter with the moving of target, and improve the detection accuracy. Finally, experiments show that compared with traditional algorithms and detected in different scenes, this method can enhance small target detection effectively.
Highlights
T HE acquisition and detection of long-distance target is significant for the photoelectric system
In the process of system imaging, target is easy influenced by light intensity, atmospheric turbulence, moving clouds and so on[1], which make target detector receive target energy unevenness, and bring about numerous non-stationary edge contour areas in image, and target often overwhelmed by these strong noise clutter, which leads to the target information being excessively
Deep learning [25,26,27,28,29,30], which has been developed in recent years was utilized in small target detection it improved the accuracy of weak signal target detection and contributed to the small target detect in remote imaging
Summary
T HE acquisition and detection of long-distance target is significant for the photoelectric system. The traditional filtering method mainly uses difference in image to finish the background modeling[17], and gets the difference image by the subtracting between the original image and the background image, so as to achieve the purpose of segmentation and extraction of small and weak target. These algorithms are relatively simple, less time consuming and have outstanding performance in the process of sequence image of small target detection[18], that provide some better research ideas for the algorithm in this paper. The corresponding algorithm principles are described in detail in the related work
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
