Abstract: A nitride-based semiconductor device includes a first nitride-based semiconductor layer, a second nitride-based semiconductor layer, a third nitride-based semiconductor layer, a passivation layer, a gate insulator layer, and a gate electrode. The first nitride-based semiconductor layer includes at least two doped barrier regions defining an aperture between the doped barrier regions. The second nitride-based semiconductor layer is disposed over first nitride-based semiconductor layer. The third nitride-based semiconductor layer is disposed on the second nitride-based semiconductor layer and has a bandgap higher than a bandgap of the second nitride-based semiconductor layer. The passivation layer is disposed over the third nitride-based semiconductor layer, in which a vertical projection of the passivation layer on the first nitride-based semiconductor layer is spaced apart from the aperture. The gate insulator layer is disposed over the third nitride-based semiconductor layer.

Abstract: An instance segmentation method and apparatus are provided. A to-be-trained segmentation network performs the following processing on each instance group that is in a sample original image and that is of pixels of a marked instance, where each instance group includes at least one marked instance, and the processing includes: predicting at least two different first basic feature maps and a first attention feature map corresponding to each first basic feature map; performing weighted processing on the at least two first basic feature maps and pixel values of respective first attention feature maps corresponding to the at least two first basic feature maps, to obtain a first feature fusion map; and training the to-be-trained segmentation network based on the first feature fusion map and the sample original image. A segmentation model can precisely determine pixels of an instance in an original image.

Abstract: This application discloses an image segmentation method in the field of artificial intelligence. The method includes: obtaining an input image and a processing requirement; performing multi-layer feature extraction on the input image to obtain a plurality of feature maps; downsampling the plurality of feature maps to obtain a plurality of feature maps with a reference resolution, where the reference resolution is less than a resolution of the input image; fusing the plurality of feature maps with the reference resolution to obtain at least one feature map group; upsampling the feature map group by using a transformation matrix W, to obtain a target feature map group; and performing target processing on the target feature map group based on the processing requirement to obtain a target image.

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.

Abstract: This invention concerns the tracking of objects in video data for artificial vision; for instance for a bionic eye. More particularly, the invention concerns a vision enhancement apparatus for a vision-impaired user. In other aspects, the invention concerns a method for enhancing vision and software to perform the method. The image processor operates to process video data representing images of a scene. Automatically detect and track a user selected object, such as a face, in the images. And, automatically modify the video data, by reserving a user selected area of the displayed images for displaying the tracked object as a separate video tile within the scene. The separate video tile remains in the selected area despite movement of the camera relative to the scene, or movement of the user relative to the object or the scene.