Abstract: A training data generation device includes a virtual scene generation unit, an orthographic virtual camera, an object-occlusion determination unit, an object-occlusion determination unit and a perspective virtual camera. The virtual scene generation unit is configured for generating a virtual scene, wherein the virtual scene comprises a plurality of objects. The orthographic virtual camera is configured for capturing a vertical projection image of the virtual scene. The object-occlusion determination unit is configured for labeling an occluded-state of each object according to the vertical projection image. The perspective virtual camera is configured for capturing a perspective projection image of the virtual scene. The training data generation unit is configured for generating a training data of the virtual scene according to the perspective projection image and the occluded-state of each object.

Abstract: An object pose estimation system, an execution method thereof and a graphic user interface are provided. The execution method of the object pose estimation system includes the following steps. A feature extraction strategy of a pose estimation unit is determined by a feature extraction strategy neural network model according to a scene point cloud. According to the feature extraction strategy, a model feature is extracted from a 3D model of an object and a scene feature is extracted from the scene point cloud by the pose estimation unit. The model feature is compared with the scene feature by the pose estimation unit to obtain an estimated pose of the object.

Abstract: A gripping device and a gripping method are provided. The gripping device includes a gripping component and an imaging element. The imaging element is configured to obtain an imaged result of an object. An action of the gripping component is generated through a training model according to the imaged result and at least one parameter. The gripping component grasps the object according to the action. A first parameter and a third parameter of the at least one parameter refer to the same axis, and a second parameter and the first parameter of the at least one parameter refer to distinct axes.

Abstract: A classification method includes the following steps. Firstly, a classification module including a deep neural network (DNN) is provided. Then, to-be-classified sample is obtained. Then, the DNN automatically extracts a feature response of the to-be-classified sample. Then, whether the feature response of the to-be-classified sample falls within a boundary scope of several training samples is determined; wherein the training samples are classified into several categories. Then, if the feature response of the to-be-classified sample falls within the boundary scope, the DNN determines that to-be-classified sample belongs to which one of the categories according to the training samples.

Abstract: A classification method includes the following steps. Firstly, a classification module including a deep neural network (DNN) is provided. Then, to-be-classified sample is obtained. Then, the DNN automatically extracts a feature response of the to-be-classified sample. Then, whether the feature response of the to-be-classified sample falls within a boundary scope of several training samples is determined; wherein the training samples are classified into several categories. Then, if the feature response of the to-be-classified sample falls within the boundary scope, the DNN determines that to-be-classified sample belongs to which one of the categories according to the training samples.

Abstract: A near-field antenna measurement method and a measurement system using the same is disclosed. The measurement method chooses a measurement block to measuring an antenna signal emitted by an antenna under test on the measurement block. Firstly, a plurality of initial measurement points is chosen on measurement block and initial electric field values of the antenna signal at the initial measurement points are measured. Then, a plurality of initial interpolation points cooperating with the initial measurement points on the measurement block is chosen to comply with the sampling theorem. Interpolation is performed on the initial electric field values to obtain initial electric field interpolation values respectively corresponding to the initial interpolation points. Finally, the initial electric field values and the initial electric field interpolation values are processed to obtain electric filed convergence values of the antenna signal at the initial measurement points and the initial interpolation points.

Abstract: An autofocus method for obtaining clear images characterized by: adjusting the lens position with an initial dataset of focus values to obtain a estimated lens position; moving the lens to the estimated lens position and acquiring the corresponding focus value; determining whether the estimated lens position is sufficiently proximate to the prior estimated lens position, wherein, if it is, the autofocus process stops, and, if not, repeating the above-described steps until a lens position having an optimal focus value is obtained, thereby obtaining the clearest image with increased focusing speed and reduced time of lens movement and without the need of empirical parameters.

Abstract: An autofocus method for obtaining clear images characterized by: adjusting the lens position with an initial dataset of focus values to obtain a estimated lens position; moving the lens to the estimated lens position and acquiring the corresponding focus value; determining whether the estimated lens position is sufficiently proximate to the prior estimated lens position, wherein, if it is, the autofocus process stops, and, if not, repeating the above-described steps until a lens position having an optimal focus value is obtained, thereby obtaining the clearest image with increased focusing speed and reduced time of lens movement and without the need of empirical parameters.