The goal of our work is to use visual attention to enhance autonomous driving performance. We present two methods of predicting visual attention maps. The first method is a supervised learning approach in which we collect eye-gaze data for the task of driving and use this to train a model for predicting the attention map. The second method is a novel unsupervised approach where we train a model to learn to predict attention as it learns to drive a car. Finally, we present a comparative study of our results and show that the supervised approach for predicting attention when incorporated performs better than other approaches.
This paper reports our investigations on the design of globally or quasi-globally optimal structures for three-component and four-component mechanically compensated zoom lenses. This is accomplished by implementation of a global optimization technique based on evolutionary programming. The technique searches optimal structures in the configuration space formed by the specific design variables: powers of individual components and the intercomponent separations. Any requirements for system length and Petzval curvature of the zoom lens can be incorporated in the search for optimal solutions. Illustrative numerical results of our investigations on four regular types of zoom systems, as classified by Tanaka, are presented.
A new approach for 'ab initio' synthesis of thin lens structure of zoom lenses is reported. This is accomplished by an
implementation of evolutionary programming, based on Genetic Algorithm, which explores the available configuration
space formed by powers of individual components and inter-component separations. Normalization of the variables is
carried out to get an insight on the optimum structures. The method has been successfully used to get thin lens structures
of mechanically compensated, optically compensated, and linearly compensated zoom lens systems by suitable
formulation of merit function of optimization. Investigations have been carried out on three component and four
component zoom lens structures. Illustrative numerical results are presented.
A new approach for structural synthesis of optically compensated zoom lenses is reported. An implementation of
evolutionary programming facilitates the procedure by carrying out a global search over the available degrees of
freedom, namely, powers of the components and the inter-component separations. Practical success of the method
depends on suitable formulation of the fitness function. Normalization of the variables is carried out to get an insight on
the optimum structures. Illustrative numerical results are presented.
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.