Abstract
This paper presents a method for detecting high-speed incoming targets by the fusion of spatial and temporal detectors to achieve a high detection rate for an active protection system (APS). The incoming targets have different image velocities according to the target-camera geometry. Therefore, single-target detector-based approaches, such as a 1D temporal filter, 2D spatial filter and 3D matched filter, cannot provide a high detection rate with moderate false alarms. The target speed variation was analyzed according to the incoming angle and target velocity. The speed of the distant target at the firing time is almost stationary and increases slowly. The speed varying targets are detected stably by fusing the spatial and temporal filters. The stationary target detector is activated by an almost zero temporal contrast filter (TCF) and identifies targets using a spatial filter called the modified mean subtraction filter (M-MSF). A small motion (sub-pixel velocity) target detector is activated by a small TCF value and finds targets using the same spatial filter. A large motion (pixel-velocity) target detector works when the TCF value is high. The final target detection is terminated by fusing the three detectors based on the threat priority. The experimental results of the various target sequences show that the proposed fusion-based target detector produces the highest detection rate with an acceptable false alarm rate.
Highlights
An active protection system (APS) is designed to protect tanks from a guided missile or rocket attack via a physical counterattack
Radar and IR complement each other, this paper focuses on the IR
Target detection using non-linear filters, such as the median or morphology filter, shows a low rate of false alarms around the edge, but the process is computationally complex
Summary
An active protection system (APS) is designed to protect tanks from a guided missile or rocket attack via a physical counterattack. Target detection using non-linear filters, such as the median or morphology filter, shows a low rate of false alarms around the edge, but the process is computationally complex Combinational filters, such as max-mean or max-median, can preserve the edge information of background structures [11]. Wang et al proposed support vector machines in the wavelet domain and reported the feasibility of multiscale small target detection in low contrast backgrounds [18]. The temporal contrast filter (TCF)-based method was developed to detect supersonic small infrared targets [37]. An improved power law detector-based moving target detection method was presented; it was effective for image sequences that occur in heavy clutter [39].
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.
