KEYWORDS: Convolution, Signal to noise ratio, Covariance matrices, Deep convolutional neural networks, Deep learning, Monte Carlo methods, Computer simulations
Aiming at the problem of Direction of Arrival (DOA) estimation of coherent mixed targets in the far field of uniform linear array, the deep convolutional neural network and deep convolutional self-encoder are designed by combining deep learning with DOA estimation of coherent sources. The deep convolutional encoder is trained by comparing the difference between the received covariance matrix of the independent source array and the received covariance matrix of the coherent source array under the same condition, so as to realize the process of decorrelation, and then DOA estimation is carried out. The simulation results show that both methods can extract spatial features sufficiently, improve the accuracy of DOA estimation and reduce the complexity of the algorithm, and the method based on deep convolutional self-encoder has better performance.
Due to the high efficiency of discriminative correlation filter (DCF), it has attracted widespread attention in the field of UAV object tracking. To handle the problem of filter degradation, many trackers usually introduce temporal regularization to enhance the discriminative power of the filter. However, these temporal regularization methods only utilize the limited information between two consecutive frames, which are susceptible interference by previous corrupted information. Besides, regularization terms with predefined hyperparameters can not well adapt to the variations of the target across sequent frames, which may cause the model degradation or drift. We propose a tracker based on DCF framework to fully exploit the information hidden in the historical response map, namely adaptive weighted response consistency-based DCF tracking. Specifically, carefully selected historical response maps with fixed weight distribution are introduced in training phase to increase the robustness of the filter. Further, we present a unified loss for jointly learning the filter and the weight distribution, which can be solved by the alternate convex search method. The joint loss guarantees that reliable response maps contribute more to filter learning, leading to a more discriminative and adaptive filter for tracking the target. Extensive experiments show that the proposed method achieves state-of-the-art results on two datasets.
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.