To solve the problem that infrared dim small targets are difficult to be detected and tracked under complex background,this paper proposes a method based on the fusion of Pipeline Filter and Kernelized Correlation Filter.First, preprocess the obtained image sequence to reduce the influence of complex background on target detection; then, detect dim small infrared moving targets based on Background Prediction and Pipeline Filter;Finally,track the targets by Kernelized Correlation Filter which is initialized by the obtained detection information.To deal with the interference caused by the lens moving, the target position is predicted in the process of targets tracking.The algorithm is verified by the constructed infrared dim target data set. The results show that the proposed algorithm has better robustness and realtime performance, and the tracking effect is obvious.
Aiming at the problem of the low contrast between target and background in the detected UAV target intensity images, a low-speed and small UAV targets detection and tracking method based on polarization imaging detection is proposed. Based on the analysis of the polarization imaging characteristics of low-speed and small UAV targets, through polarization image analysis, single-frame detection based on spatial filtering and adaptive threshold segmentation, continuous frame target trajectory association based on spatiotemporal information, and improved KCF algorithm Target tracking and other processing processes have realized the effective detection and tracking of low-speed and small UAV targets.
Image information for single polarization parameters is weak, low contrast and the common visible light intensity image detail fuzzy problems, in order to further improve the target detection of polarization imaging detection system identification capability, put forward a kind of based on the sampling of shear wave transformation under visible light image fusion algorithms, intensity and polarization parameters can effectively improve the identification of targets in complex background. Polarization degree of the image and visible light intensity image using the sampling shear wave transformation under the decomposed high frequency subband and low-frequency subband, then low frequency subband image fusion rules design based on region distance energy weighted algorithm, and the high frequency subband image fusion rule is designed to combine guide take large filtering area of energy, will eventually high low frequency subband image by the NSST finally fused image is obtained by inverse transformation refactoring. By comparing the fusion results of this algorithm with those of other methods that adopt the same decomposition transformation method but choose different fusion rules, the experiment proves that this algorithm not only has the best visual effect, but also has the advantage in the objective evaluation index value.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.