Abstract: Image processing techniques are described to select and crop a region of interest from an image obtained from a camera located on or in a vehicle, such as an autonomous semi-trailer truck. The region of interest can be identified by selecting one or more reference points and determining one or more positions of the one or more reference points on the image obtained from the camera. As an example, a location of two reference points may be 500 meters and 1000 meters in front of a location of autonomous vehicle, where the front of the autonomous vehicle is an area towards which the autonomous vehicle is being driven.

Abstract: The present application provides an under-display camera assembly, including: an organic light-emitting diode display screen, wherein a display region of said display screen includes an under-display camera region and a non-under-display camera region, and a pixel density of the under-display camera region is configured to be less than that of the non-under-display camera region; and a camera module located at a rear end of the under-display camera region, and including an iris diaphragm, a lens group, and a photosensitive component, wherein the iris diaphragm is provided between a bottom surface of a pixel light-emission layer and a top surface of the foremost lens of the lens group, and has a closed state and a transmission state. The iris diaphragm, in the closed state, reflects light from the display screen or emits light by itself from the front of the display screen, and the transmission state refers to a state in which a light path of the camera module is opened.

Abstract: The present application relates to a terminal device and a display screen thereof, and a preparation method for the display screen, wherein the display screen includes a cover plate layer, a touch layer, a polarizing layer, an encapsulation layer, a pixel layer and a circuit driving layer from top to bottom. In particular, the display screen further includes a microlens layer formed above the pixel layer, wherein the microlens layer corresponds to each gap between pixels in the pixel layer, and is used to converge light to each of the gaps before the light passes through the pixel layer via the gaps so as to increase the light transmittance of the display screen.

Abstract: The present application provides an under-screen camera assembly, including: an organic light-emitting diode display screen, a display area of which includes an under-screen camera area and a non-under-screen camera area; and a camera module, which is arranged locate at a rear end of the under-screen camera area, the camera module includes a lens barrel, a lens group and a photosensitive assembly, wherein the lens barrel includes: a lens group installation section, the lens group being installed on an inner side face of the lens group installation section; and an extension section, which is formed to extend upwards from the top of the lens group installation section, and a top surface of the extension section bearing against a bottom surface of the organic light-emitting diode display screen. The present application further provides a corresponding terminal device.

Abstract: A method for performing retrospective magnetic resonance imaging (MRI) artifact correction includes receiving, as input, an MRI image having at least one artifact; using a trained adversarial network for performing retrospective artifact correction on the MRI image, wherein the trained adversarial network is trained using unpaired artifact-free MRI images and artifact-containing MRI images; and outputting, by the trained adversarial network, a derivative MRI image related to the input, wherein the at least one artifact is corrected in the derivative MRI image.

Abstract: Provided is an under-display camera assembly, including: an organic light-emitting diode display screen, a display region of which includes an under-display camera region and a non-under-display camera region, wherein a pixel density of the under-display camera region is set to be less than a pixel density of the non-under-display camera region; and a camera module, wherein the optical axis thereof is perpendicular to the surface of the organic light-emitting diode display screen, and the camera module is located at a rear end of the under-display camera region. Further provided is a corresponding terminal device.

Abstract: A computer-implemented method for generating a computer-readable model for a technical system on the basis of text-based specification data for the technical system, the text-based specification data specifying at least one system condition is provided. A plurality of model components for the computer-aided modelling of the technical system are provided, each model component being assigned a model component identifier. By means of generative adversarial networks, model components are selected, using their model component identifiers, from the plurality of model components on the basis of the text-based specification data, and a computer-readable model for the technical system is generated from the selected model components in such a way that model data of the computer-readable model satisfy at least one system condition specified in the text-based specification data.

Abstract: This application discloses a flexible sensing system and an associated proximity sensing method. The flexible sensing system includes: a first thin film encapsulation layer and a first electrode layer attached to the first thin film encapsulation layer; the first electrode layer includes a bipolar electrode configured for forming an arc-shaped electric field for determining whether a distance between a target object and the sensing system is within the first distance range; the first electrode layer further includes a unipolar electrode configured for forming a vertical electric field for determining whether a distance between the target object and the sensing system is within the second distance range; and the first distance range is less than the second distance range. By using different sensing solutions for the object at different distance positions, the sensing system avoids the issue that a single sensing solution has a relatively low sensing accuracy.

Abstract: Image processing techniques are described to obtain an image from a camera located on a vehicle while the vehicle is being driven, cropping a portion of the obtained image corresponding to a region of interest, detecting an object in the cropped portion, adding a bounding box around the detected object, determining position(s) of reference point(s) on the bounding box, and determining a location of the detected object in a spatial region where the vehicle is being driven based on the determined one or more positions of the second set of one or more reference points on the bounding box.

Abstract: Image processing techniques are described to receive bounding box information that describes a bounding box located around a detected obj ect in an image, determine one or more positions of one or more reference points on the bounding box, determine, for each reference point, 3D world coordinates of a point of intersection of the reference point and the road surface, and assign the 3D world coordinates of the one or more reference points to a location of the detected object.

Abstract: Image processing techniques are described to select and crop a region of interest from an image obtained from a camera located on or in a vehicle, such as an autonomous semi-trailer truck. The region of interest can be identified by selecting one or more reference points and determining one or more positions of the one or more reference points on the image obtained from the camera. As an example, a location of two reference points may be 500 meters and 1000 meters in front of a location of autonomous vehicle, where the front of the autonomous vehicle is an area towards which the autonomous vehicle is being driven.

Abstract: Provided are a control method of a heat pump system and a heat pump system. The heat pump system includes a throttling element and a four-way valve. The four-way valve has a first state in a case that the heat pump system operates for refrigerating and a second state in a case that the heat pump system operates for heating. The control method includes that: before the four-way valve is switched from the first state to the second state, A is compared with B, and switching of the state of the four-way valve is controlled and the opening degree of the throttling element is adjusted according to the comparison result, or switching of the state of the four-way valve is controlled according to the comparison result, or the opening degree of the throttling element is adjusted according to the comparison result.

Abstract: A system and method for proximate vehicle intention prediction for autonomous vehicles are disclosed. A particular embodiment is configured to: receive perception data associated with a host vehicle; extract features from the perception data to detect a proximate vehicle in the vicinity of the host vehicle; generate a trajectory of the detected proximate vehicle based on the perception data; use a trained intention prediction model to generate a predicted intention of the detected proximate vehicle based on the perception data and the trajectory of the detected proximate vehicle; use the predicted intention of the detected proximate vehicle to generate a predicted trajectory of the detected proximate vehicle; and output the predicted intention and predicted trajectory for the detected proximate vehicle to another subsystem.

Abstract: The subject matter discloses a relay, including a housing, static contact bridges, a moving contact bridge, a pushing mechanism and a detection assembly.

Abstract: A magnetically driven hopping soft robot based on magnetically programmed temperature-sensitive hydrogels includes first moving bodies and a second moving body. Several first moving bodies are distributed evenly on a bottom portion of the second moving body. The first moving bodies are made of a temperature-responsive hydrogel containing magnetic particles. An alternating magnetic field is applied to the first moving bodies to cause the first moving bodies to deform due to magnetocaloric effect. The first moving bodies have a two-layered structure. A first layer is made of a double-network cross-linked hydrogel and a second layer is made of a magnetic temperature-responsive hydrogel with added magnetic nanoparticles. An alternating magnetic field is applied to the first moving bodies in a manner that an amount of deformation of the second layer is greater than that of the first layer. The second layer is made of a temperature-responsive hydrogel with added magnetic nanoparticles.

Abstract: A system and method for proximate vehicle intention prediction for autonomous vehicles are disclosed. A particular embodiment is configured to: receive perception data associated with a host vehicle; extract features from the perception data to detect a proximate vehicle in the vicinity of the host vehicle; generate a trajectory of the detected proximate vehicle based on the perception data; use a trained intention prediction model to generate a predicted intention of the detected proximate vehicle based on the perception data and the trajectory of the detected proximate vehicle; use the predicted intention of the detected proximate vehicle to generate a predicted trajectory of the detected proximate vehicle; and output the predicted intention and predicted trajectory for the detected proximate vehicle to another subsystem.

Abstract: A relay includes: a housing, a base plate, and a driving device, connected to the base. At least one stationary contact group is provided on the housing. The stationary contact group includes two stationary contacts insulated from each other. At least one stationary contact in the stationary contact group includes an upper terminal and a lower contact are included. The upper terminal and the lower contact are isolated from each other and electrically connected by a fuse. The base plate is provided in the housing and can switch between on and off positions. The base plate, when being in the on position, contacts the stationary contact group for the electrical conduction of the two stationary contacts in the stationary contact group, and, when being in the off position, is isolated from the stationary contact group for disconnecting the electrical conduction of the two stationary contacts in the stationary contact group.

Abstract: The present disclosure provides a method, an apparatus and a system for multi-module scheduling, capable of solving the problem associated with inconsistency in data inputted to a computing module in the multi-module scheduling technique in the related art.

Abstract: A method for performing retrospective magnetic resonance imaging (MRI) artifact correction includes receiving, as input, an MRI image having at least one artifact; using a trained adversarial network for performing retrospective artifact correction on the MRI image, wherein the trained adversarial network is trained using unpaired artifact-free MRI images and artifact-containing MRI images; and outputting, by the trained adversarial network, a derivative MRI image related to the input, wherein the at least one artifact is corrected in the derivative MRI image.

Abstract: Provided are a control method of a heat pump system and a heat pump system. The heat pump system includes a throttling element and a four-way valve. The four-way valve has a first state in a case that the heat pump system operates for refrigerating and a second state in a case that the heat pump system operates for heating. The control method includes that: before the four-way valve is switched from the first state to the second state, A is compared with B, and switching of the state of the four-way valve is controlled and the opening degree of the throttling element is adjusted according to the comparison result, or switching of the state of the four-way valve is controlled according to the comparison result, or the opening degree of the throttling element is adjusted according to the comparison result.