Systems and methods are disclosed for tracking objects in a physical environment using visual sensors onboard an autonomous unmanned aerial vehicle (UAV). In certain embodiments, images of the physical environment captured by the onboard visual sensors are processed to extract semantic information about detected objects. Processing of the captured images may involve applying machine learning techniques such as a deep convolutional neural network to extract semantic cues regarding objects detected in the images. The object tracking can be utilized, for example, to facilitate autonomous navigation by the UAV or to generate and display augmentative information regarding tracked objects to users.
OBJECT TRACKING BY AN UNMANNED AERIAL VEHICLE USING VISUAL SENSORS
2018-06-07
Patent
Electronic Resource
English
Object tracking by an unmanned aerial vehicle using visual sensors
European Patent Office | 2024
|Object Tracking By An Unmanned Aerial Vehicle Using Visual Sensors
European Patent Office | 2022
|Object tracking by an unmanned aerial vehicle using visual sensors
European Patent Office | 2022
|Visual tracking and control of Unmanned Aerial Vehicle
IEEE | 2015
|Real-time visual object tracking for unmanned aerial vehicles (UAVs)
European Patent Office | 2023
|