Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

Abstract: A vehicle can include various sensors to detect objects in an environment. In some cases, the object may be within a planned path of travel of the vehicle. In these cases, leaving the planned path may be dangerous to the passengers so the vehicle may, based on dimensions of the object, dimensions of the vehicle, and semantic information of the object, determine operational parameters associate with passing the object while maintaining a position within the planned path, if possible.

Abstract: Disclosed herein are methods of treating age-related retinal diseases by administering to the subject a therapeutically effective amount of a purine nucleoside phosphorylase (PNPase) inhibitor and/or a PNPase purine nucleoside substrate. In some examples, the subject can have AMD or glaucoma.

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.

Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

Abstract: A vehicle can include various sensors to detect objects in an environment. In some cases, the object may be within a planned path of travel of the vehicle. In these cases, leaving the planned path may be dangerous to the passengers so the vehicle may, based on dimensions of the object, dimensions of the vehicle, and semantic information of the object, determine operational parameters associate with passing the object while maintaining a position within the planned path, if possible.

Abstract: The present disclosure relates to the field of intelligent lawn mowers and logic control technologies thereof, and discloses a path planning method for an intelligent lawn mower. The path planning method includes: starting a touch panel of the intelligent lawn mower; entering a path planning setting interface, which displays a schematic diagram of a region to be mowed, a path angle indicating image and a path angle setting image; receiving a touch input of a user with respect to the path angle setting image to set a path angle; adjusting, based on the set path angle, the path angle indicating image for display; and re-planning a path of the intelligent lawn mower based on the set path angle and a preset algorithm. The present disclosure further provides a path planning system for the intelligent lawn mower.

Abstract: A computer vision processor of a camera extracts attributes of persons or vehicles from hyperzooms generated from image frames. The hyperzooms represent traffic patterns. The extracting is performed using a feature extractor of an on-camera convolutional neural network (CNN) including an inverted residual structure. The attributes include at least colors of clothing of the persons or colors of the vehicles. Mobile semantic segmentation models of the CNN are generated using the hyperzooms and the attributes. Attribute analytics are generated by executing the mobile semantic segmentation models while obviating network usage by the camera. The attribute analytics are stored in a key-value database located on a memory card of the camera. A query is received from the server instance specifying one or more of the attributes. The attribute analytics are filtered using the one or more of the attributes to obtain a portion of the traffic patterns.

Abstract: The Invention relates to a method for preparing a multichannel hollow fiber membrane. According to a certain ratio, ceramic powder, a macromolecular polymer, an organic solvent, and a dispersant are mixed evenly to prepare a membrane casting solution; and after bubble removing processing is performed on the membrane casting solution, a membrane green body is formed with the cooperation of a multichannel hollow fiber die and phase inversion. After the membrane green body is roasted at a high temperature, a multichannel ceramic hollow fiber membrane is formed. The multichannel ceramic hollow fiber membrane has an asymmetric structure and a skeleton structure in an inner cavity and can meet the strength and flux requirements of a ceramic hollow fiber membrane.

Abstract: Techniques for determining an object contour are discussed. Depth data associated with an object may be received. The depth data, such as lidar data, can be projected onto a two-dimensional plane. A first convex hull may be determined based on the projected lidar data. The first convex hull may include a plurality of boundary edges. A longest boundary edge, having a first endpoint and a second endpoint, can be determined. An angle can be determined based on the first endpoint, the second endpoint, and an interior point in the interior of the first convex hull. The longest boundary edge may be replaced with a first segment based on the first endpoint and the interior point, and a second segment based on the interior point and the second endpoint. An updated convex hull can be determined based on the first segment and the second segment.

Abstract: Techniques for collision avoidance using an object contour are discussed. A trajectory associated with a vehicle may be received. Sensor data can be received from a sensor associated with the vehicle. A bounding contour may be determined and associated with an object represented in the sensor data. Based on the trajectory, a simulated position of the vehicle can be determined. Additionally, a predicted position of the bounding contour can be determined. Based on the simulated position of the vehicle and the predicted position of the bounding contour, a distance between the vehicle and the object may be determined. An action can be performed based on the distance between the vehicle and the object.

Abstract: A method of treating retinal degeneration in a subject includes administering to the subject a therapeutically effective amount of a compound of formula (I).

Abstract: The present disclosure discloses a method for path planning after removing an obstacle from a lawn to be mowed, the method including: starting a boundary editing interface for the lawn to be mowed to display inner boundary information; detecting an obstacle selection and removal instruction of a user; deleting information data that is stored in a memory and/or database and associated with the information mark of the obstacle to be removed; reloading all currently-stored boundary information; and displaying the updated schematic diagram of the lawn and the updated path planning information on a display screen. The present disclosure also discloses a method and system for path planning after adding an obstacle to a lawn to be mowed, and a system for path planning after removing an obstacle from a lawn to be mowed.

Abstract: This application relates to compounds and methods of treating retinal degeneration associated with inherited rhodopsin mutations in the ocular tissue of a subject. The retinal degeneration, can include, for example, macular degeneration, a including age-related macular degeneration, Stargardt disease, and retinitis pigmentosa. The retinitis pigmentosa can include autosomal dominate retinitis pigmentosa associated with a P23H RHO mutation. A method of treating retinal degeneration in a subject includes administering to the subject a therapeutically effective amount of a compound of formula (I), wherein the compound of formula (I) acts as a chaperone of rhodopsin.

Abstract: A serum microRNA (miRNA) marker suitable for early screening and diagnosis of ossification of posterior longitudinal ligament (OPLL) and its application in the diagnostic reagent or kit for the OPLL. Biomarker miRNA-563, miRNA-196b, miRNA-10a and miRNA-129 have high diagnostic value for OPLL, and the development and application of the related serum miRNA biomarker detection reagent kit. It can be applied in the screening of ossification of posterior longitudinal ligament disease, supporting the diagnosis of OPLL more quickly and accurately, evaluate the patient's ossification condition, and may lay down the foundation for improving clinical therapeutic effect.

Abstract: A vehicle can include various sensors to detect objects in an environment. In some cases, the object may be within a planned path of travel of the vehicle. In these cases, leaving the planned path may be dangerous to the passengers so the vehicle may, based on dimensions of the object, dimensions of the vehicle, and semantic information of the object, determine operational parameters associate with passing the object while maintaining a position within the planned path, if possible.