Abstract: Method and system for geometric correction based on image tracking, the method including: obtaining a plurality of projection images of a geometric model, each of the projection images including a projection marker corresponding to an original marker in the geometric model; obtaining an initial correspondence between the original markers in the geometric model and the projection markers in one of the projection images; determining a target correspondence between the original markers in the geometric model and the projection markers in the tracked projection image by tracking, based on a correlation of the projection images and the initial correspondence, the projection markers in the projection images; performing, based on the target correspondence, a geometric correction.

Abstract: Provided are a lane line recognition method, an electronic device and a storage medium, relating to a technical field of artificial intelligence, in particular to technical fields of intelligent transportation, automatic driving and deep learning. The lane line recognition method includes: extracting a basic feature of an original image; recognizing at least one lane line node in the original image by using the basic feature of the original image; extracting a local feature from the basic feature of the original image by using the at least one lane line node; fusing the basic feature and the local feature; and recognizing a lane line in the original image based on a fused result.

Abstract: Provided are an anti-ST2 antibody or a fragment thereof. The antibody or the fragment thereof can be specifically bound to human ST2, for inhibiting combination of IL-33 and human ST2, blocking an IL-33/ST2 intracellular signaling pathway, and inhibiting the promoting effect of different forms of IL-33 in cell-derived IL5, IL6 and 118 production. Compared with a known anti-ST2 antibody, this anti-ST2 antibody has higher biological activity, and can be used for preventing, treating or alleviating diseases related to ST2 expression or IL-33/ST2 pathway disorders.

Abstract: Provided are a high-precision map construction method, an electronic device, and a storage medium, relating to the field of high-precision map technology and, in particular, to autonomous driving technology. The implementation solution includes: calculating a pose of a camera at each position point according to a pre-acquired video; calculating an absolute depth of each keypoint in the pre-acquired video according to the pose of the camera at each position point; constructing, according to the absolute depth of each keypoint in the video, a corresponding three-dimensional point cloud of each pixel point in the pre-acquired video; and constructing, according to the corresponding three-dimensional point cloud of each pixel point in the pre-acquired video, a high-precision map corresponding to the pre-acquired video.

Abstract: A method of rectifying a text image, a training method, an electronic device, and a medium, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision, deep learning technology, intelligent transportation and high-precision maps. An exemplary implementation includes: performing, based on a gating strategy, a plurality of first layer-wise processing on a text image to be rectified, so as to obtain respective feature maps of a plurality of layer levels, wherein each of the feature maps includes a text structural feature related to the text image to be rectified, and the gating strategy is configured to increase an attention to the text structural feature; and performing a plurality of second layer-wise processing on the respective feature maps of the plurality of layer levels, so as to obtain a rectified text image corresponding to the text image to be rectified.

Abstract: A method for detecting a road change is provided. The method includes: obtaining a road image comprising a road to be detected; extracting a road region in the road image as a target region, wherein the road region corresponds to where the road to be detected is located; obtaining a target geographical location of the target region; determining a reference region for the target region from pre-stored road regions based on the target geographical location; calculating a similarity between the target region and the reference region; and determining, based on the similarity, whether a passability of the road to be detected is changed. By applying the solution provided by the embodiments of the present disclosure, efficiency of road change detection can be improved.

Abstract: Provided are a method and apparatus for correcting positioning information, an electronic device and a storage medium, which relate to the field of artificial intelligence, in particular, to intelligent transportation technology and image processing technology. The specific implementation solution includes steps described below. A to-be-corrected image and positioning information of the to-be-corrected image are acquired. A target candidate reference image matching the to-be-corrected image is selected from candidate reference images having accurate positioning information. The positioning information of the to-be-corrected image is corrected according to accurate positioning information of the target candidate reference image. According to the solution of the present disclosure, the positioning information of the to-be-corrected image can be quickly corrected, and a guarantee is provided for accurately updating a navigation map by using the to-be-corrected image subsequently.

Abstract: A point cloud registration method, apparatus, device, and storage medium are provided. The method includes: acquiring target point cloud data; dividing the target point cloud data into a plurality of point cloud sets; determining a coincidence degree between every two point cloud sets and determining a fixed point cloud set and a registration point cloud set from two point cloud sets with a coincidence degree between the two point cloud sets being greater than a preset threshold; determining a target registration matrix between the fixed point cloud set and the registration point cloud set; and performing registration of the fixed point cloud set with the registration point cloud set according to the target registration matrix.

Abstract: The present disclosure provides a method and apparatus for processing an image. A specific implementation includes: acquiring a top view of a road; identifying a position of a lane line from the top view; cutting the top view into at least two areas, and determining, according to the position of the lane line in each area, a width of a lane in the each area and an average width of the lane in the top view; calculating a first perspective correction matrix by optimizing a first loss function, the first loss function being used to represent a difference between the width of the lane in the each area and the average width of the lane in the top view; and performing a lateral correction on the top view through the first perspective correction matrix to obtain a first corrected image.

Abstract: A method and an apparatus for visual positioning based on mobile edge computing are provided. In the method, the mobile edge computing node receives an environment image captured by a to-be-positioned device in an area covered by the mobile edge computing node; the mobile edge computing node determines a target image matching the environment image from multiple candidate images, and calculates the position and pose information of the to-be-positioned device based on the position and pose information of the device for capturing the target image; and the mobile edge computing node sends the position and pose information of the to-be-positioned device to the to-be-positioned device, so that the to-be-positioned device determines the positioning information in an electronic map according to the position and pose information.

Abstract: A method and an apparatus for visual positioning based on mobile edge computing are provided. In the method, the mobile edge computing node receives an environment image captured by a to-be-positioned device in an area covered by the mobile edge computing node; the mobile edge computing node determines a target image matching the environment image from multiple candidate images, and calculates the position and pose information of the to-be-positioned device based on the position and pose information of the device for capturing the target image; and the mobile edge computing node sends the position and pose information of the to-be-positioned device to the to-be-positioned device, so that the to-be-positioned device determines the positioning information in an electronic map according to the position and pose information.

Abstract: The present disclosure relates to a radio-frequency coil for a magnetic resonance device, comprising: antenna units, conductor end ring segments connecting the antenna units, and capacitors. Here, a single antenna unit is curved in a plane parallel to a direction of a static magnetic field B0 (the positive direction of the z axis); the cross sections of all the antenna units in a x-y plane are spaced apart from each other at an angle and distributed symmetrically in a radial array; adjacent antenna units are connected with the end ring segments and the capacitors at two ends; the coil as a whole is an open dome shape surface structure and is sufficiently conformal to the surface of an object to be scanned.

Abstract: Disclosed are a method and a device for cartilage regeneration. The method for cartilage regeneration comprises: applying a pulse magnetic field with a magnetic pulse device to a body part of a mammal in which an injured cartilage tissue is located, wherein the magnetic pulse device comprises a magnetic pulse generator and a coil, and by applying a magnetic pulse with a frequency of from 10 Hz to 200 Hz to the coil, a uniform magnetic field distribution is produced in a region of the body part covered by the coil, thereby achieving a uniform magnetically induced electrical excitation. The method can effectively facilitate articular cartilage regeneration, and is convenient to operate, having a broad prospect in clinical applications.

Abstract: The present disclosure relates to a radio-frequency coil for a magnetic resonance device, comprising: antenna units, conductor end ring segments connecting the antenna units, and capacitors. Here, a single antenna unit is curved in a plane parallel to a direction of a static magnetic field B0 (the positive direction of the z axis); the cross sections of all the antenna units in a x-y plane are spaced apart from each other at an angle and distributed symmetrically in a radial array; adjacent antenna units are connected with the end ring segments and the capacitors at two ends; the coil as a whole is an open dome shape surface structure and is sufficiently conformal to the surface of an object to be scanned.

Abstract: The present invention discloses a frame assembly of movable stowage device and its application as a transport vehicle. The frame assembly moving stowage comprises a frame, a rolling chute, a drive sprocket, a driven sprocket, a transmission chain, a towing hook device, a towing hook guide-rail and a power device. The frame assembly can be used to load and unload a dustbin with a transfer vehicle. No special lifting equipment is required when the frame assembly is used. The automatic and modern transport vehicle of present invention makes the transportation of garbage faster and more efficient, which meets the desired requirements of logistics for the transportation of garbage.

Abstract: In a blood pressure monitor, when a main unit is mounted on a mounting surface such as a desk, a bulging region of a first tube and a bulging region of a second tube, both located at a rear surface of the main unit, come into contact with the mounting surface. This can avoid the main unit from sliding even when the main unit is pulled by the first and second tubes. Consequently, a blood pressure monitor has a configuration in which the main unit is less likely to slide over the mounting surface even when the main unit is pulled by tubes connected to the main unit.

Abstract: A network device configures a unique ring number for each interface in a ring network and stores the ring number. The network device receives a RSVP confirmation packet from a next-hop network device, storing a route object record contained in the RSVP confirmation packet. The network device parses the route object record of the primary tunnel, searches for an end network device on the primary tunnel in the same ring network, sets the end network device as a destination network device of a protection tunnel of the network device, sets the network device as a start network device of the protection tunnel, and store path information of the protection tunnel. An interface of the end network device has the same ring number with an egress interface of the network device.

Abstract: A method of reducing voltage variations in a power supply may include generating an intermediate voltage and setting a first-transistor gate voltage at a first-transistor gate of a first transistor of the power supply based on the intermediate voltage. The method may also include setting an output voltage at an output node of the power supply based on a second-transistor gate voltage at a second-transistor gate of a second transistor. Additionally, the method may include setting the second-transistor gate voltage based on the first-transistor gate voltage such that the output voltage is based on the intermediate voltage, a first-transistor threshold voltage of the first transistor, and a second-transistor threshold voltage of the second transistor and such that variations in the first-transistor threshold voltage and the second-transistor threshold voltage at least partially cancel each other out.