Abstract: A method for establishing a tire information recognition model, a tire information recognition method, and a tire information recognition system. In the method for establishing the model, images of tire side surfaces taken from various angles are obtained for creating a tire image training dataset. Positions of the tires are identified from each of the images, and a tire image can be segmented from the images for generating a tire image set. A fixed tire image set is obtained through geometry fixing. An object detection model is used to detect objects in each of the images in the fixed tire image set. Multiple regions of interest can be created in each of the images, and the regions of interest are labeled so as to form a labeled tire image training dataset used to train the object detection model in order to establish the tire information recognition model.

Abstract: The present disclosure relates to a system, a method and a computer-readable medium for video processing. The method includes displaying a live video of a first user in a first region on a user terminal and displaying a video of a second user in a second region on the user terminal. A portion of the live video of the first user extends to the second region on the user terminal. The present disclosure can improve interaction during a conference call or a group call.

Abstract: The subject application relates to a method and server for handling streaming data, and includes: Obtaining a request for entering the live streaming as an invisible viewer; in response to obtaining the request, starting to provide a first user terminal of a first viewer with the streaming data for the live streaming while setting information on the first viewer invisible to other viewers and a streamer; and in response to detecting a first action of the first viewer in the live streaming, setting at least a part of the information visible to at least a part of the other viewers and the streamer. According to the subject application, it is possible to encourage further communication between the streamer and the viewer, and enhance user-user interactions through the live streaming.

Abstract: An identification method and an identification system for a license plate are provided. The method includes: obtaining images in sequence; decomposing each image into a vehicle image and a license plate image, inputting the vehicle image into a vehicle detection model to detect a vehicle through first processing stages; inputting the detected vehicle into a vehicle metadata identification model to obtain vehicle metadata through second processing stages; inputting the license plate image into the license plate recognition model to identify license plate information through third processing stages; and merging and processing the license plate information and vehicle metadata to generate a license plate recognition result. The first processing stages and the second processing stages form a first pipeline architecture, the third processing stages form a second pipeline architecture, and the first pipeline architecture and the second pipeline architecture are executed simultaneously.

Abstract: An edge-computing method and an edge-computing system for automatic license plate recognition are provided. The edge-computing method is performed in a terminal system of a vehicle. The edge-computing system includes a photographing module and a computing circuit. A streaming video is generated by the photographing module. An object-detection model is used to identify a license plate in each frame of the video and recognize characters from an image of the license plate. A confidence algorithm is used to calculate a confidence level of each of the characters and a confidence score of all of the characters. Confidence scores of the license plate in continuous frames within a period of time are calculated, and the frame having a highest confidence score is stored in a memory. Afterwards, a classification model is used to recognize features of vehicle, such as a vehicle jurisdiction, a color, a brand, and a model.

Abstract: A method for tracking an object in a dynamic scene and a system are provided. The object-tracking system acquires continuous frames and identifies one or more objects in each of the frames. A target object is chosen from a first frame. An object distance between the target object and each of the objects identified in a second frame is calculated. Word strings on the target object and every object identified in the second frame are recognized. A string similarity between the string on the target object and the string on each of the objects in the second frame is calculated. An overall score of the object distance and the string similarity is calculated and is referred to for determining if the target object is present in the second frame. Object-tracking is implemented when the target object is determined to be present in the second frame and subsequent frames.

Abstract: The subject application relates to a method and server for handling streaming data, and includes: Obtaining a request for entering the live streaming as an invisible viewer; in response to obtaining the request, starting to provide a first user terminal of a first viewer with the streaming data for the live streaming while setting information on the first viewer invisible to other viewers and a streamer; and in response to detecting a first action of the first viewer in the live streaming, setting at least a part of the information visible to at least a part of the other viewers and the streamer. According to the subject application, it is possible to encourage further communication between the streamer and the viewer, and enhance user-user interactions through the live streaming.

Abstract: The present disclosure relates to a system, a method and a computer-readable medium for rendering a streaming on a user terminal. The method includes rendering the streaming in a first mode, receiving an environment parameter of the user terminal, receiving a timing when the user terminal closes the streaming, determining a threshold value of the environment parameter based on the timing the user terminal closes the streaming, receiving an updated environment parameter of the user terminal, and rendering the streaming in a second mode if the updated environment parameter meets the threshold value. The second mode includes fewer data objects than the first mode or includes a downgraded version of a data object in the first mode for the rendering. The present disclosure can customize the rendering mode for each user and maximize the satisfaction of viewing streaming for each user.

Abstract: A method, comprising: detecting an outage of at least one functionality in a live streaming; performing an first operation toward a second user terminal; storing data of the first operation in a database of the first user terminal; and displaying an effect corresponding to the first operation during the outage. The present disclosure may store the data of operation performed by the user terminal during outage and process the operation after the outage is recovered. Therefore, the streamers and viewers may feel interested and satisfied, instead of feeling anxious, and the user experience may be enhanced.

Abstract: The present disclosure relates to a system, a method and a computer-readable medium for rendering a streaming on a user terminal. The method includes rendering the streaming in a first mode, receiving an environment parameter of the user terminal, receiving a timing when the user terminal closes the streaming, determining a threshold value of the environment parameter based on the timing the user terminal closes the streaming, receiving an updated environment parameter of the user terminal, and rendering the streaming in a second mode if the updated environment parameter meets the threshold value. The second mode includes fewer data objects than the first mode or includes a downgraded version of a data object in the first mode for the rendering. The present disclosure can customize the rendering mode for each user and maximize the satisfaction of viewing streaming for each user.

Abstract: The subject application relates to a method and server for handling streaming data, and includes: Obtaining a request for entering the live streaming as an invisible viewer; in response to obtaining the request, starting to provide a first user terminal of a first viewer with the streaming data for the live streaming while setting information on the first viewer invisible to other viewers and a streamer; and in response to detecting a first action of the first viewer in the live streaming, setting at least a part of the information visible to at least a part of the other viewers and the streamer. According to the subject application, it is possible to encourage further communication between the streamer and the viewer, and enhance user-user interactions through the live streaming.

Abstract: The present disclosure relates to a system, a method and a computer-readable medium for rendering a streaming on a user terminal. The method includes rendering the streaming in a first mode, receiving an environment parameter of the user terminal, receiving a timing when the user terminal closes the streaming, determining a threshold value of the environment parameter based on the timing the user terminal closes the streaming, receiving an updated environment parameter of the user terminal, and rendering the streaming in a second mode if the updated environment parameter meets the threshold value. The second mode includes fewer data objects than the first mode or includes a downgraded version of a data object in the first mode for the rendering. The present disclosure can customize the rendering mode for each user and maximize the satisfaction of viewing streaming for each user.

Abstract: The present disclosure relates to a system, a method and a computer-readable medium for video processing. The method includes displaying a live video of a first user in a first region on a user terminal and displaying a video of a second user in a second region on the user terminal. A portion of the live video of the first user extends to the second region on the user terminal. The present disclosure can improve interaction during a conference call or a group call.

Abstract: An automated inspection system includes a machine-vision inspection device, a repair station and an artificial intelligence module connected to the machine-vision inspection device, and a processing platform connected to the repair station and the artificial intelligence module. The machine-vision inspection device obtains an image of a to-be-inspected object and displays the image on an operation screen of the repair station, the artificial intelligence module retrieves the image of the to-be-inspected object to perform inference for classification, the processing platform automatically overlaps result data of classification inference for the image of the to-be-inspected object on the operation screen of the repair station, and intercepts and transmits result data of manual review, which is inputted by an operator through a user interface, to the repair station.

Abstract: An automatic test method for a computer includes the following steps: reading a keyboard signal or mouse signal and a delay time in an event file in a system test directory; sending the keyboard signal or mouse signal to a to-be-tested system according to the delay time; the to-be-tested system that operates according to the keyboard signal or mouse signal sending at least one response; and verifying the response by comparing the response, which is in the form of a character string, with a character string in a correct text file in the system test directory, or sending an image acquisition signal to the to-be-tested system according to the at least one response, to acquire a screenshot, converting the screenshot into a screenshot image file, and verifying the screenshot image file corresponding to the to-be-tested system by comparing the screenshot image file with a correct screenshot image file in the system test directory.

Abstract: The present invention provides intelligent test robot system, which operation platform of intelligent robot body connected storage module for storing test script, operation platform respectively connected signal output unit and image input unit, further connected network communication module linked remote console computer. When operation platform automatically performs tests accordance test script, e.g., power switches, string inputs through keyboard, mouse cursor movements, clicks etc., it is possible to send instructions contained test script to test object via signal output unit for action controls, image input unit receives images outputted by test object and returns them to operation platform, then automatic graphic recognitions can be performed on captured images according to image recognition instructions in test script.

Abstract: An automatic test method for a computer includes the following steps: reading a keyboard signal or mouse signal and a delay time in an event file in a system test directory; sending the keyboard signal or mouse signal to a to-be-tested system according to the delay time; the to-be-tested system that operates according to the keyboard signal or mouse signal sending at least one response; and verifying the response by comparing the response, which is in the form of a character string, with a character string in a correct text file in the system test directory, or sending an image acquisition signal to the to-be-tested system according to the at least one response, to acquire a screenshot, converting the screenshot into a screenshot image file, and verifying the screenshot image file corresponding to the to-be-tested system by comparing the screenshot image file with a correct screenshot image file in the system test directory.

Abstract: A method for intellectual asset management and analysis is provided, including a method of combining intellectual asset and an expert and artificial intelligence hinting method, wherein the former includes a process of key word combination, a process of self-determined combination and a process of recombination. The process of key word combination includes acquiring a document with key words from an intellectual asset according to a key word and a pre-determined search condition to form a key word document set. The process of self-determined combination includes acquiring a self-determined index document from an intellectual asset according to a self-determined index to form a self-determined index document set. The process of recombination includes reassembling the existing key word document set or the existing self-determined index document set according to a pre-determined sifting condition. The hinting method provides a word related to the key word, acquired in a comparative related word database.