Abstract: Progressive precision image classifier and method of training include storing a dataset of labeled images, training a neural network to generate a classification vector comprising a plurality of confidence values, each confidence value corresponding to a classification, validating the trained neural network, calculating fine-grained confidence thresholds for each classification, wherein each classification represents a leaf-level classification in a hierarchical classification structure, and calculating coarse-level confidence thresholds for at least one parent class in the hierarchical classification structure, wherein each parent class defines a group of at least one leaf-level classification. Each label in the training data identifies a leaf-level classification in the hierarchical classification structure, and the classification vector includes a 1xN vector of confidence values, where N represents a number of leaf-level classifications output by the trained neural network.

Abstract: Radar installation and calibration systems and methods are provided. In one example, a controller of a radar system receives installation parameters associated with an installation of a radar system. A present orientation of a radar device of the radar system is determined and compared to the installation parameters to determine a deviation of the present orientation from the installation parameters. The deviation is sent to a coordinating device associated with the radar device to cause the deviation to be outputted as installation feedback through the coordinating device. Related systems and methods are also provided.

Abstract: Systems and methods include an image capture component configured to capture infrared images of a scene, and a logic device configured to identify a target in the images, acquire temperature data associated with the target based on the images, evaluate the temperature data and determine a corresponding temperature classification, and process the identified target in accordance with the temperature classification. The logic device identifies a person and tracks the person across a subset of the images, identify a measurement location for the target in a subset of the images based on target feature points identified by a neural network, and measure a temperature of the location using corresponding values from one or more captured thermal images. The logic device is further configured calculate a core body temperature of the target using the temperature data to determine whether the target has a fever and calibrate using one or more black bodies.

Abstract: High resolution image target classification systems and methods include a proposal component configured to receive a first set data associated with a scene, the first set of data including at least one image of the scene, a multistage neural network comprising a plurality of neural networks, each neural network trained to receive a region of interest and output an object classification in accordance with an associated resource allocation, and an attention coordinator configured to determine regions of interest in the image and allocate each determined region to one of the plurality of neural networks from the multi-scale neural network, in accordance with available system resources. The system may be configured to optimize a probability of detecting objects in the image, while minimizing a number of pixels processed through the multi-scale neural network.

Abstract: Various techniques are disclosed to provide for improved human body temperature detection using thermal images of an inner canthus. In one example, a method includes capturing a thermal image of a human being using a thermal imager. The method also includes detecting a face and an inner canthus of the human being in the thermal image using an artificial neural network. The method also includes determining a temperature measurement of the inner canthus using corresponding pixels of the thermal image. The method also includes determining a body temperature of the human being using the temperature measurement. Additional methods and systems are also provided.

Abstract: A method and system are disclosed for managing power demand of a plurality of charging stations sharing the same portion of an electrical network, the method comprising obtaining an indication of a maximum value of power allowed at the portion of the electrical network; obtaining an indication of a current power consumed at the portion of the electrical network; managing a charging configuration of the plurality of charging stations to ensure that the current power consumed at the portion of the electrical network stays lower than the maximum value of power demand allowed.

Abstract: A method and system are disclosed for managing power sharing of a plurality of charging stations sharing the same portion of an electrical network, the method comprising detecting an event at a charging station of the plurality of charging stations; determining if a charging configuration is acceptable with the event and if the charging configuration is not acceptable, modifying the charging configuration accordingly.

Abstract: There is described an electric vehicle charging station for charging an electric vehicle, comprising: an electrical connector electrically connectable to a source of electrical energy, the electrical connector adapted for connecting to a battery of the electric vehicle; a frame having a connector receiving portion for receiving the electrical connector; a locking unit mounted to the frame for preventing a user access to the electrical connector; and a control unit operatively connected to the locking unit, the control unit for verifying rights of a user to access the electrical connector and unlocking the locking unit upon successful verification of the user rights to provide the user access to the electrical connector.

Abstract: A method and system are disclosed for managing power sharing of a plurality of charging stations sharing the same portion of an electrical network, the method comprising detecting an event at a charging station of the plurality of charging stations; determining if a charging configuration is acceptable with the event and if the charging configuration is not acceptable, modifying the charging configuration accordingly.

Abstract: A method and system are disclosed for managing power demand of a plurality of charging stations sharing the same portion of an electrical network, the method comprising obtaining an indication of a maximum value of power allowed at the portion of the electrical network; obtaining an indication of a current power consumed at the portion of the electrical network; managing a charging configuration of the plurality of charging stations to ensure that the current power consumed at the portion of the electrical network stays lower than the maximum value of power demand allowed.

Abstract: There is described an electric vehicle charging station for charging an electric vehicle, comprising: an electrical connector electrically connectable to a source of electrical energy, the electrical connector adapted for connecting to a battery of the electric vehicle; a frame having a connector receiving portion for receiving the electrical connector; a locking unit mounted to the frame for preventing a user access to the electrical connector; and a control unit operatively connected to the locking unit, the control unit for verifying rights of a user to access the electrical connector and unlocking the locking unit upon successful verification of the user rights to provide the user access to the electrical connector.

Abstract: A modular charging station for charging an electric vehicle, the modular charging station comprising: a frame having a receiving portion; a control unit removably secured to the receiving portion of the frame and electrically connectable to a source of electrical energy, the control unit for selectively controlling access to the electrical energy; and a distributing unit removably secured to the frame, electrically connected to the control unit for receiving the electrical energy therefrom, and electrically connectable to the electric vehicle for providing the electrical energy to the electric vehicle, a powering of the distributing unit being controlled by the control unit.

Abstract: A high energy density flywheel has a central rotating axle for storing kinetic energy. The flywheel comprises a first member to be operatively mounted around the axle. The first member comprises a first material having a given high mass density enabling a given high kinetic energy storage capacity. The flywheel comprises a second member operatively attached to the first member. The second member surrounds an outside portion of the first member subject to radial forces generated by a rotation of the flywheel. The second member comprises a second material having a given high yield strength enabling a given high maximum rotational speed. The second member enables an operation of the flywheel at a given high flywheel rotational speed greater than the rotational speed that would be allowed by the maximal yield strength of the first material, to thereby provide the flywheel with a given high kinetic energy storage capacity.

Abstract: A dual switching frequency hybrid power converter comprising two different types of power switching element switching at two different frequencies is presented for DC-to-AC and AC-to-DC voltage conversion and for monophase or multi-phase devices with the aim of reducing considerably the conduction and switching losses of those power switching elements. The dual switching frequency hybrid power converter also enables a DC to DC voltage conversion as well as an AC to AC voltage conversion.

Abstract: An system for storing electrical energy over at least a medium term duration. The energy storage system comprises a motor assembly operatively connectable to at least one of an electrical energy source and an electrical distribution network for providing kinetic energy, a flywheel device operatively connectable to the motor assembly for storing at least one part of the kinetic energy, a generator assembly operatively connectable to the flywheel device for receiving at least one portion of the part of the kinetic energy and generating regenerated electrical energy in response thereto, and a control unit for controlling operation of the energy storage system, which enables an energy storage operating mode for storing the part of the kinetic energy into the flywheel device, and an energy supply operating mode for providing at least one portion of the regenerated energy to at least one of the electrical distribution network and an electrical appliance.

Abstract: A system for decoupling a rotor from a stator of a permanent magnet motor and a flywheel storage system using the same are provided. The flywheel storage system uses the permanent magnet motor as a magnetic active coupler to minimize magnetic losses in flywheel energy storage system during the motor-generator electric power transfer for enabling a magnetic field weakening method and a way of cancelling the losses during a conservative mode where the stator is totally decoupled from the rotor. Also, the present invention enables the optimal sizing of a permanent motor-generator to be able to supply a constant power over a large range of rotating speeds.