University of Pennsylvania

Samsung Electronics Co., Ltd.

Camillo Jose Taylor

Ibrahim Volkan Isler

Dae Won Lee

Konstantinos Daniilidis

Ziyun Wang

Anthony Robert Bisulco

Fernando Cladera Ojeda

Ani Hsieh

Provided is a method for predicting a location of a fast-moving object. The method includes receiving event information from an event camera, the event information corresponding to an event detected by the event camera, generating a Binary Event History Image (BEHI) based on the event information, providing the BEHI as an input to an event-based neural network, obtaining, as an output of the event-based neural network, a first predicted location of the fast-moving object, a normal distribution indicating prediction uncertainty of the predicted location, and a predicted time-to-collision (TTC). The method further includes estimating a second predicted location of the fast-moving object based on the first predicted location, the normal distribution, and the predicted TTC output by the event-based neural network, and actuating a mechanical catching device to be at the second predicted location.

Systems and methods for real-time state estimation of fast-moving objects

A plurality of camera devices are configured to localize one another based on visibility of each neighboring camera in an image plane. Each camera device captures images and identifies sightings of candidate targets. The camera device share information about sightings and triangulate positions of targets. Targets are matched to known tracks based on prior images, allowing targets to be tracked in a 3D environment.

Distributed target tracking using self localizing smart camera networks

Image and range data associated with an image can be processed to estimate planes within the 3D environment in the image. By utilizing image segmentation techniques, image data can identify regions of visible pixels having common features. These regions can be used to candidate regions for fitting planes to the range data based on a RANSAC technique.

Scene analysis using image and range data

A system and method for localizing imaging devices in a network using images taken by the imaging devices. The relative position and orientation of a network of camera-equipped communications devices are obtained by having each device examine images taken by its camera. The devices are also equipped with controllable light sources that vary their output in a predetermined manner. This variation is found in images and used to identify the devices in view and to define epipolar points related to the other imaging devices in view. Common reference points in the image are also identified. The imaging devices then exchange details of the epipolar and common reference points with each other, and use them to obtain their relative position and orientation.

Growing community of inventors

Philadelphia, PA, United States of America

Camillo Jose Taylor