Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.

Methods, systems, apparatus, and computer-readable media for data band selection using machine learning. In some implementations, image data comprising information for each of multiple wavelength bands is obtained. A multi-layer neural network is trained using the image data to perform one or more classification or regression tasks. A proper subset of the wavelength bands is selected based on parameters of a layer of the trained multi-layer neural network, where the parameters were determined through training of the multi-layer neural network using the image data. Output is provided indicating that the selected wavelength bands are selected for the one or more classification or regression tasks.

According to various embodiments of the present invention, an electronic device comprises: a memory including instructions and a training database, which includes data, on at least one object, acquired on the basis of an artificial intelligence algorithm; at least one sensor; and a processor connected to the at least one sensor and the memory, wherein the processor can be configured to execute the instructions in order to acquire data on a designated area including the at least one object by using the at least one sensor, identify location information and positioning information on the at least one object on the basis of the training database, and transmit a control signal for picking the at least one object to a picking tool related to the electronic device on the basis of the identified location information and positioning information.

According to various embodiments of the present invention, an electronic device comprises: a memory including instructions and a training database, which includes data, on at least one object, acquired on the basis of an artificial intelligence algorithm; at least one sensor; and a processor connected to the at least one sensor and the memory, wherein the processor can be configured to execute the instructions in order to acquire data on a designated area including the at least one object by using the at least one sensor, identify location information and positioning information on the at least one object on the basis of the training database, and transmit a control signal for picking the at least one object to a picking tool related to the electronic device on the basis of the identified location information and positioning information.

A motion sensor for detection motion of humans is provided. The motion sensor contains a near infrared (NIR) low resolution image sensor that captures image frames in the near infrared spectrum and a sensor that detects the amount of visible light. In addition, a processor is connected to the visible light sensor and the NIR motion sensor. The processor is configured to receive the amount of visible light from the visible light sensor and the images from the NIR low resolution image sensor. The processor is further configured to compare the image frames to detect motion; the sensitivity of the detection of motion is determined by the amount of visible light detected by the visible light sensor. The output has two or modes based on the detection of motion by the processor.

A system and method for automatically screening anyone arriving to a facility outside of predetermined entry and exit times is provided. The automated screening system denies entry and detains anyone determined to be a threat. An operator may then take the person denied entry into custody or manually override the system to allow the person access to the facility.

Provided are a display panel and a display device. An array layer is located on a substrate. A display layer is located on a side of the array layer facing away from the substrate and includes light-emitting elements. A color filter layer is located on a side of the display layer facing away from the array layer. The color filter layer includes a light-blocking layer and color filters. The light-blocking layer includes first light-blocking portions. Each first light-blocking portion forms an imaging aperture. A protective layer is located on the color filter layer. Each first metal part overlaps the first light-blocking portion. The optical sensor layer is located on a side of the color filter layer facing away from the protective layer and configured to detect an image formed by the imaging aperture. Further provided is a display device including the preceding display panel.

To provide an imaging device capable of reducing discomfort caused by visible light. A light source can emit the visible light and invisible light as irradiation light. An imaging unit captures an image of an irradiation region irradiated with the irradiation light to acquire an image. A processor causes the imaging unit to acquire a detection image in a first irradiation mode in which the invisible light is emitted from the light source, and determines whether a biometric object is presented in the irradiation region based on the detection image. When the biometric object is presented, the processor causes the imaging unit to acquire the biometric image obtained by copying the biometric object as the image in a second irradiation mode in which the visible light and the invisible light are emitted from the light source.

Embodiments of the disclosure provided herein generally relate to methods and video system components that have integrated background differentiation capabilities that allow for background replacement and/or background modification. In some embodiments, undesired portions of video data generated in a video environment are separated from desired portions of the video data by taking advantage of the illumination and decay of the intensity of electromagnetic radiation, provided from an illuminator, over a distance. Due to the decay of intensity with distance, the electromagnetic radiation reflected from the undesired background has a lower intensity when received by the sensor than the electromagnetic radiation reflected from the desired foreground. The difference in the detected intensity at the one or more wavelengths can then be used to separate and/or modify the undesired background from the desired foreground for use in a video feed.

An image processing method and apparatus for a smart pen, and an electronic device are provided in embodiments of the present disclosure, and belong to the technical field of data processing. The method comprises: monitoring a working state of a second pressure switch provided at a pen tip of the smart pen when the smart pen is in a working state; controlling an infrared transceiver circuit on the smart pen to send an infrared signal to an area where the smart pen writes; performing feature calculation on an original image by using a first part of a preset lightweight network model; performing feature retrieval on a first feature image to obtain a trajectory identification result corresponding to the original image; and sending, by means of a Bluetooth module on the smart pen, a trajectory vector to a target object with which the smart pen establishes a communication connection.