The GrabCut image segmentation algorithm based on the principle of graph theory has been extensively used in the field of computer vision. However, the shortcoming is that it requires human-computer interaction to complete the ROI region selection to solve the segmentation task of the foreground image. Therefore, it cannot meet the requirements of fully intelligent image processing. In order to eliminate human-computer interaction and realize smart region selection, this paper proposes a ROI smart region generating and fine-tuning method to improve the GrabCut method, so as to realize intelligent image segmentation. The experimental results show that our method is compatible with both single-target and multi-target foreground image segmentation solutions.
Bistatic inverse synthetic aperture radar (ISAR) can help image the high-speed target for its advantage in tracking and more observation angle to provide more information than monostatic ISAR. However, the complex image geometry makes it difficult to achieve a clear image of the target with geometry distortion correction and calibration. Furthermore, high-speed motion will make the image blurred or defocussed. To address these problems, a bistatic ISAR (B-ISAR) imaging method for high-speed motion target with geometric distortion correction and calibration is proposed. According to the motion decomposition idea, we established the B-ISAR echo model of the high-speed motion target. Then, based on the range Doppler algorithm, we deduce the analytic formula of the geometric distortion factor and calibration factor, and transform the imaging problem into a parameter estimation problem. With the sparsity of the scattering points, the required parameters are solved using the expectation maximization algorithm based on the maximum a posteriori probability criterion. With the estimated parameters, a clear B-ISAR image of a high-speed motion target with geometric correction and calibration is obtained. The simulations show that the proposed method has better resolution and simultaneously attains geometric distortion correction and calibration of the image.
A bistatic inverse synthetic aperture radar (B-ISAR) imaging method is proposed for the rectilinear maneuvering target. According to the idea of the motion decomposition, a B-ISAR echo model is established. By introducing the concept of the equivalent average rotation velocity (EARV), the original sparse imaging algorithm with geometric distortion correction and calibration is extended to the rectilinear maneuvering target. Firstly, both the relationship between the calibration factors and the parameters of B-ISAR system, and the relationship between the geometric distortion and the B-ISAR system and the target motion parameters are deduced. Based on the relationships, the problems of the distortion correction and calibration are transformed into the parameters estimation problem. Then, using the sparsity of scattering points and the maximum a posteriori (MAP) criterion, the parameters are estimated by iterative optimization. After that, the clear ISAR images of the target with geometric distortion correction and calibration is derived. The simulation results show that compared with Range-Doppler (RD) imaging method, the proposed method has better resolution and is more clear with distortion correction and calibration.
High Speed Motion of target will lead to the peak splitting and spectrum spreading of the range profile, which does harm to the traditional R-D imaging algorithm. Due to the low processing bandwidth, the previous high speed compensation methods are mostly based on the Stretch system, where the echo signals are modeled as multi-component LFM signals, and motion compensation is achieved by estimating the chirp rate. However, these methods cannot be directly applied to the matched filtering system, so the coherence of the echoes cannot be utilized. For this, a range profile compensation algorithm of high speed target for ISAR based on wideband Radon-Fourier transform (WRFT) is proposed. The response function of the wideband matched filter is firstly given, and at second the motion of the target is projected to the rangevelocity plane by WRFT, so as to realize the coherent accumulation of signal energy. At last, with the accurate estimated velocity of the target, a compensation function is constructed to eliminate the range walk. Furthermore, a compensation method based on wideband generalized Radon-Fourier transform (WGRFT) for high speed high maneuvering is deduced. Simulation results show the effectiveness of the range profile compensation algorithms.
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.