Abstract:
Die Erfindung betrifft ein künstliches neuronales Netz (3), das über eine Datenbank (9) eingelernt ist, welche zumindest Verkehrsunfalldaten enthält, und mit zumindest einem unbemannten Luftfahrzeug (1) in Verbindung steht, welches Umgebungsdaten an das neuronale Netz (3) sendet, wobei das neuronale Netz (3) mittels zumindest den Verkehrsunfalldaten der Datenbank (9) und den Umgebungsdaten des unbemannten Luftfahrzeugs (1) einen Verkehrsunfall (6, 7) erkennen und klassifizieren kann.
Abstract:
A method for operating a system including a plurality of cameras, the method including: selecting a subset of the cameras, determining a subset of pixels captured by the camera subset, determining a pixel depth associated with each pixel of the pixel subset, and controlling system operation based on the pixel depth.
Abstract:
System and method can support moment capturing in an imagery environment. The system can obtain a plurality of images of an object, wherein the plurality of images are captured using one or more imaging devices within a period of time while the object is being tracked. Furthermore, the system can perform motion and/or state estimation of the object for the period of time. Then, the system can select one or more images related to a moment from the plurality of images based on the motion and/or state estimation of the object.
Abstract:
The disclosed embodiments include methods, apparatuses, systems, and UAVs configured to an interactive and automatic initialization of the tracking systems. The disclosed embodiments observe an object of interest in a surrounding of the movable object and detect a feature of the object of interest, which acts as a trigger for automatically initializing the tracking system. As a result, the disclosed embodiments may provide efficiency and reliability to initializing a robotic system.
Abstract:
Le véhicule aérien (1) sans pilote comprend un premier moyen de commande du vol dudit véhicule (1), un moyen d'emport de charge (6), mobile selon au moins deux axes (F, F1), au moins un moyen (7) d'identification et de suivi d'un animal et au moins un 10 dispositif d'intervention (10) sur un animal associé à un second moyen de commande, ledit dispositif d'intervention étant adapté pour envoyer (P) un moyen d'intervention par contact sur l'animal. Ledit moyen (7) d'identification et de suivi et ledit dispositif d'intervention (10) sont solidaires, en déplacement, avec le moyen d'emport de charge (6). Les premier et second moyens de commande, respectivement de vol du véhicule (1) et du dispositif d'intervention (10), sont indépendants. L'invention concerne aussi un procédé d'utilisation d'un tel véhicule (1).
Abstract:
An unmanned aerial vehicle (20) includes a support (21) having a plurality of receiving slots (27); a plurality of arms (22) attached to the support (21); and a plurality of propellers (23) respectively attached to the plurality of arms (22). Each of the plurality of receiving slots (27) is configured to receive one of the plurality of arms (22) and one of the plurality of propellers (23) attached to the one of the plurality of arms (22).
Abstract:
An apparatus for zooming relative to an object and methods for making and using same. A condition of the object and/or an imaging device can be determined. A zooming mode can be selected based on the determined condition. Additionally, the condition can include a condition of an aerial vehicle associated with the imaging device.
Abstract:
An imaging system and methods for balancing an imaging device and making and using same. The imaging system can determine a center of gravity of the imaging device. A supporting position of the imaging device can be moved for compensating a change in the center of gravity based upon the determined the center of gravity.