Ford Global Technolgoies, LLC

Ford Motor Company Limited

Pol Llado

John William Schmotzer

Ali Hassani

Alexander Groh

Arun Dutta

Vidya Nariyambut Murali

Gintaras Vincent Puskorius

Guy Hotson

Jakob Nikolaus Hoellerbauer

Gaurav Kumar Singh

Yao Ge

Taylor Hawley

Dylan Verster

The present disclosure is directed toward a method and system for deconstructing and searching binary based vehicular data. The method includes extracting a vehicle filename metadata for one or more vehicular files; parsing data of the vehicular files to generate categorized objects based on a vehicular data dictionary for the vehicular files; associating each of the categorized objects with a respective vehicle filename metadata; storing vehicular documents indicative of the categorized objects with associated vehicle filename metadata in a database system; building a query based on a search input acquired by way of a search interface being displayed; and transmitting search results in response to the search input. The vehicular data dictionary defines multiple terms indicative of decoding logic provided in the vehicular files.

Method and system for deconstructing and searching binary based vehicular data

A vehicle is described that includes a video camera configured to record video, a processor configured to process the recorded video from the video camera into hyperlapse video, and an input/output device to link the hyperlapse video with a social network associated with at least one of a driver of the vehicle and the vehicle. The processor may be configured to receive video data from the video camera and to create the hyperlapse video by reconstructing a video stream from the video data, planning a smooth path through the video stream, and rendering the video data along the smooth path into the hyperlapse video that has a faster speed and less jitter than the video stream. The hyperlapse video may be a non-native, sped-up video of the recorded video from the video camera.

Vehicle with hyperlapse video and social networking

Techniques and examples pertaining to objection detection and trajectory prediction for autonomous vehicles are described. A processor receives an input stream of image frames and fuses a spatiotemporal input stream of the image frames and an appearance-based stream of the image frames using a deep neural network (DNN) to generate an augmented stream of the image frames. The processor performs object detection and trajectory prediction of one or more objects in the image frames based on the augmented stream.

Fusion of motion and appearance features for object detection and trajectory prediction

A vehicle includes a steering wheel and a controller. The controller is configured to, in response to receiving location and speed data from other vehicles indicating an expected collision absent a trajectory change, automatically control the steering wheel to direct the vehicle along a collision avoidance path. The collision avoidance path is based on map data identifying a marking type for a traveling lane such that the path crosses the lane when the marking type is broken and does not cross the lane when the marking type is solid.

Dynamic lane positioning for improved biker safety

Growing community of inventors

Royal Oak, MI, United States of America

Pol Llado