Abstract: An automatic real-time basketball box score recording and analysis system with videos captured from arbitrary angles is applied to a basketball game. A shot analyzing step is performed to analyze the videos to determine whether one of the videos is a real shot event to generate a shot analysis result. A data calculating step is performed to analyze the videos to determine that the real shot event is a three-point shot, a two-point shot or a free throw to generate a scoring result, and then calculate a game data according to the shot analysis result and the scoring result. A player analyzing step is performed to analyze the videos to obtain a posture analysis data of a shooter. The posture analysis data is configured to evaluate a performance of the shooter when shooting. An interface device is configured to modify and display the game data.

Abstract: A method for generating a traffic event video includes the following. Map alignment of a set of moving trajectory coordinates corresponding to a moving video with an electronic map is performed, and a set of trajectory map information corresponding to the moving trajectory coordinates is obtained from the electronic map. At least one event map information conforming to an event trajectory model from the set of trajectory map information and a plurality of image frame information of the moving video corresponding to the image frame information of the trajectory map information are obtained, and a plurality of location information of a virtual object is generated according to the event trajectory model. A video segment is extracted from the moving video based on the image frame information, and the virtual object and the video segment are synthesized based on the location information to generate a traffic event video corresponding to the event trajectory model.

Abstract: A processor of a computer-aided design system reads and executes a software stored in a memory to input first digital data of a first component of the composite object, input second digital data of a second component of the composite object, analyze the first digital data and the second digital data with first criterion to obtain a plurality of first surfaces and a plurality of second surfaces respectively, calculate a distance between one of the plurality of the first surfaces and one of the plurality of the second surfaces, and output a first result when the distance is greater than or equal to the first threshold; otherwise, output a second result.

Abstract: A team sports vision training system based on extended reality, voice interaction and action recognition is configured to train vision and an action of a user. A head-mounted display device includes a task scenario player and a speech sensing module. An action capture device generates an action message. A computing server stores a scenario setting parameter group and includes a task scenario generating module, a speech recognition module and an action recognition module. The task scenario generating module generates a virtual task scenario image and a task parameter group according to the scenario setting parameter group. The speech recognition module generates a speech recognition result and a vision training result. Then action recognition module generates an action recognition result and a sport training result. The vision training result and the sport training result are configured to judge whether the user meets a training requirement.

Abstract: The disclosure provides a method for generating training data and an electronic device. The method includes: obtaining an object model of a specific object; obtaining a first image when the object model is positioned at a first angle and a first silhouette corresponding to the first image; retrieving a first object image representing the specific object positioned at the first angle from the first image based on the first silhouette; embedding the first object image into a first background image to generate a first training image; generating a first labeled data of the first object image in the first training image; and defining the first training image and the first labeled data as a first training data of the specific object.

Abstract: A computer-implemented method of creating a two dimensional code comprises providing a two dimensional code comprising a cell, providing a picture comprising a patch corresponding to the cell of the two dimensional code, providing a plurality of cell patterns different from each other, wherein each cell pattern comprises a plurality of sub-cells, and determining one of the plurality of cell patterns for the cell of the two dimensional code according to the patch of the picture.

Abstract: A computer-implemented method of creating a two dimensional code comprises providing a two dimensional code comprising a cell, providing a picture comprising a patch corresponding to the cell of the two dimensional code, providing a plurality of cell patterns different from each other, wherein each cell pattern comprises a plurality of sub-cells, and determining one of the plurality of cell patterns for the cell of the two dimensional code according to the patch of the picture.