Abstract: Disclosed is a method for detecting Ophiocephalus argus cantor under intra-class occulusion based on cross-scale layered feature fusion, including image collecting, image processing and network model, where collected images are labeled, image sizes are adjusted to obtain input images, and the input images are input into an object detection network, integrated by convolution and inserted into cross-scale layered feature fusion modules, characterized by including dividing all features input into the cross-scale layered feature fusion modules into n layers, composed of s feature mapping subsets, and fusing features of each feature mapping subset with that of other feature mapping subsets, and connecting; carrying out convolution operation, outputting training result; adjusting network parameters by a loss function to obtain parameters for a network model; inputting final output candidate boxes into a non-maximum suppression module to screen correct prediction boxes, so that prediction result is obtained.

Abstract: A mechanical control logic actuator for a vacuum toilet includes: a pneumatic valve assembly configured to control an air path of the vacuum toilet and a sewage tank; a vacuum tank configured to provide vacuum compensation for the sewage tank; a first pressure tank configured to provide a power source for the pneumatic valve assembly; a second pressure tank configured to feed gas into the sewage tank; and a sewage pipe configured to discharge sewage in the sewage tank; wherein the first pressure tank controls the air path to be in a circulation state or in a cut-off state through the pneumatic valve assembly, the vacuum tank provides vacuum compensation for the sewage tank, the sewage in the toilet is pumped into the sewage tank, the second pressure tank feeds gas into the sewage tank, the sewage tank is pressurized and the sewage is discharged through the sewage pipe.

Abstract: A fleet management system coordinates multiple autonomous vehicles (AVs) to transport a group of passengers from one location to another. A single user can submit a request to the fleet management system to provide a ride for the group, the request specifying the number of passengers and the pickup location. The fleet management system determines a number of AVs to transport the group based on the number passengers, and dispatches this number of AVs to the pickup location. The AVs pick up the passengers at the pickup location, drive the passengers to a destination, and drop the passengers off at the destination.

Abstract: A method is described and includes identifying a reflection of an object in a reflective display element on an exterior of an autonomous vehicle (AV), wherein the object is associated with a driving event of the AV; and highlighting the reflection of the object on the at least one reflective display element.

Abstract: Systems and methods are provided for adding stops to an autonomous vehicle route. A passenger can request an intermediate stop during which the passenger can exit the autonomous vehicle. An intermediate stop request may include a stop duration. Autonomous vehicle driving behavior during the intermediate stop may include parking, driving around, and performing a different route.

Abstract: An autonomous vehicle (AV) maintenance system engages a user of an AV to assist in maintenance tasks. A sensor interface receives data captured by a sensor of the AV. An issue detector processes the sensor data to detect an issue in the AV. A user interface module instructs a user to perform a maintenance task addressing the detected issue. A verification module verifies that the user successfully completed the maintenance task.

Abstract: Systems and methods for detecting when a mobile device is left in a vehicle, and returning forgotten devices to owners. Additionally, systems and methods are provided for preventing mobile devices from being left in vehicles. In particular, sensors inside a vehicle as well as sensors on mobile devices can be used to identify when a mobile device remains in a vehicle after the owner has exited the vehicle and ended their trip. Systems and methods are provided for notifying the user of the forgotten device and intelligently returning the device to the user.

Abstract: A charging dock, an electronic product, a charging system and a charging method are provided. The charging dock includes a housing, a first charging terminal, a first magnetic device, a first detection device and a first control circuit. The first charging terminal, the first magnetic device, the first detection device and the first control circuit are in the housing. The first magnetic device is to attract the charging plug near the first magnetic device to enable the charging plug to move in a direction towards the first charging terminal. The first control circuit is to control the first charging terminal to be energized when the first detection device detects that the first charging terminal is electrically coupled to the charging plug.

Abstract: An autonomous vehicle (AV) maintenance system engages a user of an AV to assist in maintenance tasks. A sensor interface receives data captured by a sensor of the AV. An issue detector processes the sensor data to detect an issue in the AV. A user interface module instructs a user to perform a maintenance task addressing the detected issue. A verification module verifies that the user successfully completed the maintenance task.

Abstract: Systems and methods for detecting when a mobile device is left in a vehicle, and returning forgotten devices to owners. Additionally, systems and methods are provided for preventing mobile devices from being left in vehicles. In particular, sensors inside a vehicle as well as sensors on mobile devices can be used to identify when a mobile device remains in a vehicle after the owner has exited the vehicle and ended their trip. Systems and methods are provided for notifying the user of the forgotten device and intelligently returning the device to the user.

Abstract: The present disclosure provides an image processing method, device and apparatus, and a computer-readable storage medium. The image processing method includes: obtaining an image and detecting multiple targets in the image; obtaining categories of multiple detected targets and first parameters of a detection frame corresponding to each detected target, and ranking all detected targets according to the first parameters in a descending order to obtain a dataset; obtaining a target with a highest first parameter in the dataset as a first detected target, and detecting whether the first parameter of a first detection frame corresponding to the first detected target satisfies a preset category condition of a category to which the first detected target belongs; detecting whether the first detection frame corresponding to the first detected target overlaps with a detection frame corresponding to a respective one of the plurality of detected targets except the first detected target.

Abstract: The present disclosure discloses an abrasive water jet full-section cutting type cutter head and application devices. The cutter head includes a cutter head body and a rotor eccentrically arranged on a working surface of the cutter head body. The rotor revolves with the cutter head body and also rotates about its own axis. At least one first nozzle is arranged on an edge of a working surface of the rotor. At least one group of second nozzles and at least one third nozzle are arranged on the working surface of the cutter head body, and the second nozzles and the third nozzle cooperate during the rotation of the cutter head body and the rotor, then a material to be cut is cut into a plurality of concentric rings, and the first nozzle cuts off the ring material to form fragments.

Abstract: A method for rejoining a network after network disconnection of a mobile terminal and related devices are provided. The method includes: a gateway determining whether to disconnect from a target mobile terminal; if yes, feeding back network disconnection information of the target mobile terminal to a server; receiving a supplementary broadcast frame instruction sent by the server; and the gateway sending a supplementary broadcast frame according to the supplementary broadcast frame instruction.

Abstract: Systems and methods for determining a passenger destination given a destination type. In particular, based on one or more conditions, a rideshare application selects one or more destination options for the user, and presents the one or more destination options to the user. The conditions can include user input criteria such as type of destination, pricing, and popularity, and external factors such as time of day and traffic.

Abstract: Systems and methods for detecting when a mobile device is left in a vehicle, and returning forgotten devices to owners. Additionally, systems and methods are provided for preventing mobile devices from being left in vehicles. In particular, sensors inside a vehicle as well as sensors on mobile devices can be used to identify when a mobile device remains in a vehicle after the owner has exited the vehicle and ended their trip. Systems and methods are provided for notifying the user of the forgotten device and intelligently returning the device to the user.

Abstract: The present invention relates to a high-current plug-in connector component and a high-current plug-in connector. The high-current plug-in connector component comprises a plug body provided with a center hole and a cable connecting hole in an inner cavity thereof, a silver cap which is welded to an outer side of an opening of the center hole, an elastic rubber arranged in the center hole, and a preset soldering tin arranged at a bottom of an inner side of the cable connecting hole, wherein the plug is slotted into three to six petals so that the plug is expanded to form an expansion plug; a head of the high-current plug-in connector component and a heel part of the plug are in a plugging engagement with a socket component of a corresponding plug-in connector, so that the high-current plug-in connector component is in electrical contact with corresponding plug-in connector component.

Abstract: A tuning method for active metamaterials using IGZO Schottky diodes, wherein the IGZO Schottky diode comprises a substrate, a Schottky electrode, amorphous IGZO active layer, and an ohmic electrode from the bottom up. The method comprises steps as follows: (1) Metamaterials are used as the Schottky electrodes, and amorphous IGZO active layers are used to fully cover the capacitive gap structures in the metamaterials; such capacitive structures in the metamaterials are bonded to the amorphous IGZO active layers to form Shottky barriers; (2) The resulting IGZO Schottky diodes from step (1) are used to tune the metamaterials dynamically.

Abstract: The disclosure relates to system and method for image quality detection. The method may include: obtaining an image acquired by a camera; obtaining an image quality detection model, the image quality detection model being provided by training a machine learning model using a plurality of training samples; determining a detection result of the image using the image quality detection model; and in response to a determination that the detection result includes a quality anomaly of the image, generating a strategy in response to the quality anomaly.

Abstract: The present application discloses a method of controlling a rear-view mirror for a vehicle. The method includes determining a gaze position and a gaze direction of a user; and controlling the rear-view mirror based on the user's gaze position and gaze direction.

Abstract: A commodity detection terminal is disclosed, the commodity detection terminal includes: an image segmentation unit configured to obtain position information of each grid of a goods shelf in an image of the goods shelf based on a first image, which is an image of the goods shelf not placed with commodities; a detector unit configured to obtain a current grid where each commodity is located and a current quantity of each commodity based on a second image, which is a current image of the goods shelf placed with commodities; and a determination unit configured to compare the current grid and the current quantity with a preset grid and a preset quantity of the each commodity, so as to determine whether a status of each commodity satisfies a preset condition. A commodity detection method, an intelligent goods shelf system, a computer device, and a readable medium are also disclosed.