Abstract: Techniques are disclosed for generating tutorial recommendations to users of image editing applications, based on image content. A methodology implementing the techniques according to an embodiment includes using neural networks configured to determine subject matter of a user provided image and to identify objects in the image. The method also includes selecting one or more proposed tutorials from a database of tutorials. The database is indexed by tutorial subject matter and tutorial object content, and the selection is based on a matching of the determined subject matter to the tutorial subject matter and a matching of the identified objects to the tutorial object content. The method further includes calculating an effectiveness score associated with each of the proposed tutorials, the effectiveness score based on application of the proposed tutorial to the image. The method further includes sorting the proposed tutorials for recommendation to the user based on the effectiveness scores.
Abstract: The embodiments of the present disclosure provide a processing method and apparatus for vehicle scene sequence tracking, and a vehicle. The method includes: obtaining a current vehicle speed of a vehicle driving in a first area and at least one frame of a current image taken; determining a vehicle speed ratio interval and a length of a sequence to be tracked according to the current vehicle speed; and performing the scene sequence tracking according to the vehicle speed ratio interval, the length of the sequence to be tracked, the at least one frame of the current image, and pre-stored multiple frames of historical reference images of the vehicle, to obtain position information of the vehicle. The method ensures that an accurate speed scanning range can still be quickly found when the vehicle speed changes greatly, and the speed scanning efficiency is greatly improved when the vehicle speed is relatively stable.
Abstract: The system is for confirming that a user of a portable terminal device has viewed posted material in a plurality of places by visiting one of the posted places, the system including the portable terminal device and a server, the device including a portable-terminal control unit, a portable-terminal communication unit, an image capturing unit, a portable-terminal storage unit, and a position-information obtaining unit, the server including a server control unit, a server communication unit, and a server storage unit that stores authenticated images about the posted material in the individual posted places in association with position information of the posted places, wherein the portable-terminal control unit sends a viewing confirmation request including a viewed image, the normalization information, and the portable-terminal position information to the server by using the portable-terminal communication unit, and the server control unit determines whether the viewed image is valid on the basis of the request
Abstract: Mechanisms and processes for enhancing limited datasets for use in training or deep learning models are discussed. Such creation generates synthetic overhead imagery based on cluster sampling and spatial aggregator factors (SAFs). The implementation accomplishes this by generating Synthetic images created by cropping objects from original images and inserting them into uniform, natural or synthetic backgrounds. The objects are selected from clusters based on pixel distribution similarity, and through SAFs mining then used for the synthetic data generation.
Type:
Grant
Filed:
July 31, 2019
Date of Patent:
June 1, 2021
Inventors:
Brian A. Landron-Rivera, Leslie De Jesus-Lebron, Christian G Gonzalez, Carlos M Melendez, Vincent Tompkins