The present invention relates to methods, computer program products and computing devices for calibrating a Digital Twin for an autonomous vehicle using machine learning and to the use of the calibrated Digital Twin to both tune at least one controller, navigation algorithms and/or guidance algorithms for an autonomous vehicle using machine learning and to optimising a vehicle shape of an autonomous vehicle using machine learning.

A method is provided that includes receiving points of an image in which objects are depicted. The method includes performing a greedy nearest-neighbor (GNN) cluster analysis of the image to group the points of the image. The GNN cluster analysis includes grouping the points into a plurality of local GNN clusters, from a greedy analysis using a k-d tree in which the points are organized. The plurality of local GNN clusters are then extended into a plurality of global GNN clusters. This evaluating similarity of the local GNN clusters, merging the local GNN clusters into a global GNN cluster when each of the defined similarity criteria is evaluated to true, and passing the local GNN clusters as global GNN clusters when any of the defined similarity criteria is evaluated to false. The method then includes detecting the objects depicted in the image based on the global GNN clusters.

A method is provided that includes receiving points of an image in which objects are depicted. The method includes performing a greedy nearest-neighbor (GNN) cluster analysis of the image to group the points of the image. The GNN cluster analysis includes grouping the points into a plurality of local GNN clusters, from a greedy analysis using a k-d tree in which the points are organized. The plurality of local GNN clusters are then extended into a plurality of global GNN clusters. This evaluating similarity of the local GNN clusters, merging the local GNN clusters into a global GNN cluster when each of the defined similarity criteria is evaluated to true, and passing the local GNN clusters as global GNN clusters when any of the defined similarity criteria is evaluated to false. The method then includes detecting the objects depicted in the image based on the global GNN clusters.

Embodiments of the present invention are a trajectory tracking method and an unmanned aerial vehicle. The method is including an unmanned aerial vehicle body and a gimbal, and the unmanned aerial vehicle body being equipped with at least one visual sensor, and the method includes: obtaining a flight image acquired by the at least one visual sensor, the flight image including a to-be-tracked target; performing visual image processing on the flight image, to generate a gimbal rotation instruction and a path instruction; adjusting an angle of the gimbal according to the gimbal rotation instruction and a gimbal state parameter of the gimbal, to lock the to-be-tracked target; and controlling a motor speed of a flight motor of the unmanned aerial vehicle according to the path instruction and a flight state parameter of the unmanned aerial vehicle, to cause the unmanned aerial vehicle to track the to-be-tracked target according to the path instruction.

Embodiments of the present invention are a trajectory tracking method and an unmanned aerial vehicle. The method is including an unmanned aerial vehicle body and a gimbal, and the unmanned aerial vehicle body being equipped with at least one visual sensor, and the method includes: obtaining a flight image acquired by the at least one visual sensor, the flight image including a to-be-tracked target; performing visual image processing on the flight image, to generate a gimbal rotation instruction and a path instruction; adjusting an angle of the gimbal according to the gimbal rotation instruction and a gimbal state parameter of the gimbal, to lock the to-be-tracked target; and controlling a motor speed of a flight motor of the unmanned aerial vehicle according to the path instruction and a flight state parameter of the unmanned aerial vehicle, to cause the unmanned aerial vehicle to track the to-be-tracked target according to the path instruction.

An aerial craft and sealed force vectoring flight system is disclosed. The aerial craft includes a main body hull, lift jets, a generator, an electrical re-introduction circuit, a hydraulic pump, air flow compressors, an RPM sensor, a max speed limiter hydraulic draft by-pass valve, and a battery. The electrical re-introduction circuit throttles the generator into high-velocity rotation and yields excess electrical current to then be applied to the lift jets. The hydraulic pump pulls pressurized hydraulic fluid across a preceding hydraulic drive impellor such that the pressurized hydraulic fluid returns to confinement under pneumatic pressure faster than a discharge of hydraulic fluid. The air flow compressors generate electricity that is re-introduced into the lift electric motors. The RPM sensor and max speed limiter hydraulic draft by-pass valve speed regulate the generator. The battery initially powers the generator.

An aerial craft and sealed force vectoring flight system is disclosed. The aerial craft includes a main body hull, lift jets, a generator, an electrical re-introduction circuit, a hydraulic pump, air flow compressors, an RPM sensor, a max speed limiter hydraulic draft by-pass valve, and a battery. The electrical re-introduction circuit throttles the generator into high-velocity rotation and yields excess electrical current to then be applied to the lift jets. The hydraulic pump pulls pressurized hydraulic fluid across a preceding hydraulic drive impellor such that the pressurized hydraulic fluid returns to confinement under pneumatic pressure faster than a discharge of hydraulic fluid. The air flow compressors generate electricity that is re-introduced into the lift electric motors. The RPM sensor and max speed limiter hydraulic draft by-pass valve speed regulate the generator. The battery initially powers the generator.

Embodiments of the present invention are an image processing method, a photographing device, and a storage medium. The method includes: acquiring an image according to a first resolution and processing the image in a first processing method in a real-time preview state, switching to a photographing state, acquiring an image according to a second resolution and processing the image in a second processing method in the photographing state, and then switching from the photographing state to the real-time preview state. In this way, in a process of switching between the two working states, the image can be processed in a corresponding state without restarting an ISP or re-importing a parameter. Compared with a method of switching different working states by powering on and off the ISP in the prior art, the method provided in the present application can achieve faster dynamic switching between different working states.

Embodiments of the present invention are an image processing method, a photographing device, and a storage medium. The method includes: acquiring an image according to a first resolution and processing the image in a first processing method in a real-time preview state, switching to a photographing state, acquiring an image according to a second resolution and processing the image in a second processing method in the photographing state, and then switching from the photographing state to the real-time preview state. In this way, in a process of switching between the two working states, the image can be processed in a corresponding state without restarting an ISP or re-importing a parameter. Compared with a method of switching different working states by powering on and off the ISP in the prior art, the method provided in the present application can achieve faster dynamic switching between different working states.

An unmanned aircraft (100) according to the present disclosure is equipped with a flight propeller (2) and includes a main body (1), a locomotion unit having an aquatic locomotion mechanism and a terrestrial locomotion mechanism independent of the flight propeller, and a connector that connects the main body and the locomotion mechanisms.