Training an artificial neural network with backpropagation algorithms requires an extensive computational process. Our recent work proposes to implement the backpropagation algorithm optically for in-situ training of both the linear and nonlinear diffractive optical neural networks which enables the acceleration of training speed and improvement on the energy efficiency on core computing modules. We numerically validated that the proposed in-situ optical learning architecture achieves comparable accuracy to the in-silico training with an electronic computer on the task of object classification and matrix-vector multiplication, which further allows adaptation to the system imperfections. Besides, the self-adaptive property of our approach facilitates the novel application of the network for all-optical imaging through scattering media. The proposed approach paves the way for the robust implementation of large-scale diffractive neural networks to perform distinctive tasks all-optically.
Fusing multispectral images, Enhanced Vision (EV) has been proven helpful to improve pilot's Situation Awareness
(SA) under Degraded Vision Environment (DVE), such as low visibility or adverse observation conditions, which caused
by fog, dust, weak light, backlighting, etc. Numerous methods are applied to enhance and fuse optical and infrared (IR)
images for visual details to provide pilot with enough information as far as possible. However, most existing optical and
IR imaging devices, for their inherent defects, fail to acquire wide span of light and only generate Low Dynamic Range
images (LDR, Dynamic Range: range between the lightest and darkest areas), which causes the loss of useful details.
Normal display devices can't reveal HDR details as well.
The proposed paper introduces and expands High Dynamic Range (HDR) technologies to fuse optical and IR images,
which has rarely been involved in the study of HDR Imaging to our knowledge, for Enhanced Vision to better pilot's
Situation Awareness. Two major problems should be discussed. (1) The way to generate fused image with HDR
information under DVE. (2) The method to effectively display fused HDR image with normal LDR monitors. Aiming at
application environment, HDR fusion scheme is proposed and relevant methods are explored. The experimental results
prove that our scheme is effective and would be beneficial to enhancing pilot's Situation Awareness under DVE.
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.