The multiple uncertainties in real radar detection scenarios require that radar automatic target recognition systems must have efficient dynamic learning capabilities. And current deep learning methods are inefficient and impractical for incremental update learning of data. To address the problem of data incremental learning in radar target recognition, a network ensemble-based target incremental fusion recognition method is proposed by combining lightweight incremental learning with neural network fusion. Multiple convolutional neural networks are constructed to be trained and tested in the split-angle domains, and then integrated and fused to obtain a robust recognition performance close to that of large data volumes with significantly reduced data requirements. The experimental results based on the measured radar data show that the proposed method can efficiently accomplish the target incremental recognition task, and has strong engineering practicality.
Accurate target detection under heavy background noise and clutter remains the key challenge for radar applications. Traditional target detection methods based on statistical models have limited performance in complex environment. Although advanced deep learning methods such as Convolutional Neural Networks (CNN) have been introduced to suppress clutter and improve the target detection performance, the limited interpretability and flexibility hinders their further implication and extension. To address this challenge, A novel multi-dimensional feature target detection method based on deep forest (DF) is proposed in this paper. Firstly, a low threshold Constant False Alarm Rate (CFAR) detector is employed to preprocess the received radar signals. Afterwards, the multi-dimensional features of filtered signals are classified using the designed DF model, which could deeply express the difference between radar targets and clutter. Finally, comparison has been conducted against CFAR and CNN by using experimental data and the results indicate that the proposed method significantly improves radar target detection capability under complex environment.
KEYWORDS: Image segmentation, Data modeling, Transformers, Target detection, Radar sensor technology, Network architectures, Deep learning, Systems modeling, Radar, Education and training
During the process of radar detection, various factors such as noise and clutter interfere with the received echo signals, leading to the detection of a large number of false targets. This poses significant challenges to the detection, tracking, and identification of real targets. This paper introduces a Transformer-based segmentation network for false target suppression. It innovatively transforms the problem of false target suppression in sequential signals into an image segmentation task. The dice loss is effectively employed to address the issue of class imbalance between targets and backgrounds. Furthermore, the introduction of the transformer module further enhances the segmentation performance of the model. The proposed method is validated on real radar measurement data, demonstrating both the effectiveness of the designed model and the improvements brought by each module.
This paper studies the collaborative unmanned aerial vehicle (UAV) sensing in integrated sensing and communication (ISAC) networks. By equipping sensing and communication units on UAVs, they can execute sensing tasks and transmit the sensing information to the base station (BS) for environment sensing. Due to the mobility and dense deployment of UAVs, they can sense the environment with much lower cost compared to the BS sensing. We aim to minimize the network sensing cost by optimizing the UAV deployment and task assignment collaboratively. For this joint optimization problem, we propose an iterative mechanism to optimize the UAV deployment and task assignment iteratively. UAV deployment problem is modeled as a cluster problem and we utilize a K-means cluster algorithm to solve it efficiently. For task assignment problem, we propose a greedy algorithm to solve it with low complexity. Simulation results validate the effectiveness of our proposed method in different scenarios.
With the advantage of fast imaging speed, video synthetic aperture radar (ViSAR) is able to monitor small targets in key areas continuously. W-band is relatively high band to realize video imaging, the Bragg scattering characteristics also create conditions for the imaging and detection of shadows for power lines. This paper reports the video imaging results of a small UAV-borne W-band SAR on power lines and analyzes the relationship to incident angles.
In this paper, a novel method of heterologous image registration method based on feature inertial following is proposed, which can perform high-precision and rapid registration of SAR image and optical image. The first image pair in the sequence is registered based on improved SURF feature to achieve high-precision registration. Based on this registration result, the other image pairs in the sequence are registered by the method of feature inertia following to achieve rapid registration. The proposed method makes full use of the correlation and gradient properties between image sequence frames. It maintains the registration accuracy of the preceding images, improves the registration speed greatly.
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.