KEYWORDS: Machine learning, Modulation, Frequency modulation, Antennas, Signal to noise ratio, Receivers, Frequency shift keying, Data modeling, Classification systems, Digital modulation, Demodulation, Angle measurement
Deep learning can identify different signals and extract a range of useful features or track a signal source. Semi and selfsupervised learning techniques can be used to teach networks the underlying dynamics of a problem and broaden generalizability. We demonstrate preliminary results on machine learning software capable of identifying the source of a target and extracting key pieces of information to help resolve or identify the source including angle of arrival. A Ushaped convolutional network may be trained to classify signals based on IQ samples according to modulations or other select features while reconstructing the clean signal. Use of semi-supervised learning training schedule including Barlow Twins on the generated latent space was demonstrated on combinations of real and synthetic radiofrequency (RF) signals. These signals were augmented under various common signal obfuscations such as Raleigh fading, reflections, varying noise and background signals. Group structure of the signals may be displayed through latent space visualizations. Classification accuracy on unseen test sets was used as the primary measurement of performance under varying levels of obfuscation. From this base, we attempted to combine this network with directional sensitivity in order to enable beam steering or identifying the source. A similar augmentation route enhanced by similar semi and selfsupervised techniques was deployed to improve tracking accuracy under realistic conditions. Statistical techniques may be used to identify frequency regions of interest during the prototyping of this signal identification network. This Deep network framework may be applied across a variety of domains and regimes for sensing and tracking.
Advanced fire control technologies that utilize computer vision-guided target recognition will enable dismounted soldiers with augmented reality displays, such as the integrated visual augmentation system, enhanced situational awareness. Here we describe a virtual reality framework and environment for the design and evaluation of computer vision algorithms and augmented reality interfaces intended to enhance dismounted soldier situational awareness. For training models, synthetic image datasets of targets in virtual environments can be generated in tandem with neural network learning. To evaluate models under simulated operational environments, a dismounted soldier combat scenario was developed. Trained models are used to process input from a “virtual camera” in-line with a rifle-mounted telescopic sight. Augmented reality overlays are projected over the sight’s optics, modeling the function of current state-of-the-art holographic displays. To assess the impact of these capabilities on situational awareness, performance metrics and physiological monitoring were integrated into the system. To investigate how sensors beyond visible wavelength optical imaging may be leveraged to enhance this capability, particularly in degraded visual environments, the virtual camera framework was extended to introduce methods for simulating multispectral infrared imaging. Thus, this virtual reality framework provides a platform for evaluating multispectral computer vision algorithms under simulated operational conditions, as well as iteratively refining the design of augmented reality displays. Improving the design of these components in virtual reality provides a rapid and cost-effective method for refining specifications and capabilities toward a field-deployable system.
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.