Southwest Research Institute

Honda Motor Co., Ltd.

Douglas A Brooks

David R Chambers

Michael Odell Blanton, Jr

William C Flannigan

Akira Mizutani

Christopher L Lewis

Edmond M DuPont

Harold A Garza

In an approach to integrating real-world properties into machine learning training, a real-world image is received. The real-world image is compared to a simulated image, where the comparison is performed using a discriminator network of a generative adversarial network (GAN). A generator network of the GAN is trained with results of the comparison of the real-world image to the simulated image. Responsive to determining that the real-world image is not optimal, the real-world image is iteratively tuned, using the generator network of the GAN, until it is determined that the real-world image is optimal, where the real-world image is optimal if the real-world image meets a predetermined threshold for accuracy of one or more image parameters of the simulated image versus the real-world image. The discriminator network of the GAN is trained with the real-world image.

System and method for overcoming real-world losses in machine learning applications

A surrounding environment recognition device includes an image capturing unit that captures a peripheral image, and a traffic signal detecting unit, which sets a search region with respect to the peripheral image, and detects a traffic signal inside of the search region. The search region becomes smaller as the distance from the image capturing unit is farther away.

Surrounding environment recognition device

A system and method for estimating a location of an object or vehicle is provided. Images of a region encompassing the object are obtained, providing a three dimensional (3-D) view frame of the region. 3-D view frames are collected along a direction of travel of the object. A 3-D map is generated along the direction of travel of the object, the map based on the 3-D view frames and further based on an estimate of motion of the object at times associated with the 3-D view frames. A first set of features is extracted from the 3-D map. A geo-referenced feature database is searched for a second set of features that match the first set of features. A geo-location associated with the second set of features is retrieved from the feature database. The location of the object is estimated based on the retrieved geo-location.

3-D imaging sensor based location estimation

Growing community of inventors

San Antonio, TX, United States of America

Douglas A Brooks