Abstract: A goal of the disclosure is to provide real-time adjustment of a deep learning-based tracking system to track a moving individual without using a labeled set of training data. Disclosed are systems and methods for tracking a moving individual with an autonomous drone. Initialization video data of the specific individual is obtained. Based on the initialization video data, real-time training of an input neural network is performed to generate a detection neural network that uniquely corresponds to the specific individual. Real-time video monitoring data of the specific individual and the surrounding environment is captured. Using the detection neural network, target detection is performed on the real-time video monitoring data and a detection output corresponding to a location of the specific individual within a given frame of the real-time video monitoring data is generated.

Abstract: Disclosed are technologies for autonomous tracking. An initial coordinate of a beacon device carried by a user is registered as a dead reckoning waypoint with a drone configured to track the user. The drone receives IMU measurements from the beacon as the user moves. For each IMU measurement, a displacement vector characterizing user movement is calculated. Estimated beacon locations are calculated by dead reckoning, based on the displacement vectors and the dead reckoning waypoint. Later, an updated dead reckoning waypoint is calculated by obtaining the current location coordinate of the drone and performing optical triangulation to determine a relative position of the user with respect to the drone. The updated dead reckoning waypoint does not depend on previously estimated beacon locations, and accumulated IMU/estimation error is eliminated. Tracking continues, where subsequent estimated locations of the beacon are calculated by dead reckoning based on the updated dead reckoning waypoint.

Abstract: Disclosed are technologies for autonomous tracking. An initial coordinate of a beacon device carried by a user is registered as a dead reckoning waypoint with a drone configured to track the user. The drone receives IMU measurements from the beacon as the user moves. For each IMU measurement, a displacement vector characterizing user movement is calculated. Estimated beacon locations are calculated by dead reckoning, based on the displacement vectors and the dead reckoning waypoint. Later, an updated dead reckoning waypoint is calculated by obtaining the current location coordinate of the drone and performing optical triangulation to determine a relative position of the user with respect to the drone. The updated dead reckoning waypoint does not depend on previously estimated beacon locations, and accumulated IMU/estimation error is eliminated. Tracking continues, where subsequent estimated locations of the beacon are calculated by dead reckoning based on the updated dead reckoning waypoint.

Abstract: A goal of the disclosure is to provide real-time adjustment of a deep learning-based tracking system to track a moving individual without using a labeled set of training data. Disclosed are systems and methods for tracking a moving individual with an autonomous drone. Initialization video data of the specific individual is obtained. Based on the initialization video data, real-time training of an input neural network is performed to generate a detection neural network that uniquely corresponds to the specific individual. Real-time video monitoring data of the specific individual and the surrounding environment is captured. Using the detection neural network, target detection is performed on the real-time video monitoring data and a detection output corresponding to a location of the specific individual within a given frame of the real-time video monitoring data is generated.