Synthetic aperture radar (SAR) is an active microwave imaging sensor, which can provide images in all-weather and all-day conditions. The various scales and irregular distribution of different ships in SAR images, is a heated and challenging problem. As a basic component in the object detection frameworks, Feature Pyramid Networks (FPNs) improve feature representations for detecting objects at different scales. However, FPN adopts the same convolution operation at different layers, which does not consider the differences between different levels. In this paper, we present Dense Feature Pyramid Network (DenseFPN). Based on the hierarchy of backbone network, the cross-scale connections and lateral connections, the shallow features and deep features are processed differently in DenseFPN. Compared with conventional FPN, we integrate DenseFPN into Faster R-CNN framework and thus form a novel detector. Experiments on high-resolution SAR images dataset (HRSID) have verified the effectiveness of the enhanced hierarchical feature in the proposed method compared with other typical CNN based methods.
A model-based joint tracking and classification (JTC) method is proposed for narrowband radar with kinematic and radar cross section (RCS) measurements. The method is derived from the 3D scattering center model (3DSCM), which can construct an explicit relation between the aspect angle and the predicted RCS. To deal with the numerical problem in observation model, a modified likelihood function for RCS measurement is adopted under the assumption of additive Gaussian observation noise. The JTC processing is realized by sequential Monte Carlo (SMC) technique. Specifically, a bank of particle filters are used to obtain type-dependent target state and type estimates. Compared with the traditional JTC methods using low resolution sensor, the proposed method is free from the constraint that target classification has to rely on different maneuvering modes. Simulation results validate the effectiveness of the proposed method with maritime application scenario.
An effective target classification algorithm based on feature aided tracking (FAT) is proposed, using the length of target (target extent) as the classification information. To implement the algorithm, the Rao-Blackwellised unscented Kalman filter (RBUKF) is used to jointly estimate the kinematic state and target extent; meanwhile the joint probability data association (JPDA) algorithm is exploited to implement multi-target data association aided by target down-range extent. Simulation results under different condition show the presented algorithm is both accurate and robust, and it is suitable for the application of near spaced targets tracking and classification under the environment of dense clutters.
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.