Methods and systems for providing a bitstream comprising video data encoded by an encoder apparatus are described, wherein the method may include: a processor of the encoder apparatus determining a current motion vector of a current block of a current video frame of a sequence of video frames comprising video data, the current motion vector defining a spatial offset of the current block relative to a prediction block of a previously encoded reference video frame stored in a memory of the encoder apparatus; the processor determining or receiving motion information associated with the current video frame, the motion information signaling the processor whether at least part of the offset defined by the current motion vector is associated with non-uniform motion in the video data of the current video frame; the processor determining a motion vector predictor candidate based on the motion information, at least a first motion vector predicator algorithm and a second motion vector predictor algorithm; and, the processor determining a motion vector difference based on the selected motion vector predictor candidate and the current motion vector; and, the processor using an encoding process to encode a residual block, the motion vector difference, an indication of the selected motion vector predictor candidate, and at least part of the motion information into a bitstream, wherein the residual block defines a difference between the current block and the prediction block.

Diagnosis is assisted by acquiring microscopical observation image data while specifying the position, classifying the image data into histological types with the use of AI, and reconstructing the classification result in a whole lesion. There is provided a pathological diagnosis assisting method that can provide an assistance technology which performs a pathological diagnosis efficiently with satisfactory accuracy by HE staining which is usually used by pathologists. Furthermore, there are provided a pathological diagnosis assisting system, a pathological diagnosis assisting program, and a pre-trained model.

This disclosure relates to a model training method and apparatus and an image processing method and apparatus. The model training method includes: obtaining a first sample image and a first standard region proportion corresponding to a first object in the first sample image; obtaining a standard region segmentation result corresponding to the first sample image based on the first standard region proportion; and training a first initial segmentation model based on the first sample image and the standard region segmentation result, to obtain a first target segmentation model.

Accurate tissue segmentation is performed without a priori knowledge of tissue type or other extrinsic information not found within the subject image, and may be combined with classification analysis so that diseased tissue is not only delineated within an image but also characterized in terms of disease type. In various embodiments, a source image is decomposed into smaller overlapping subimages such as square or rectangular tiles. A predictor such as a convolutional neural network produces tile-level classifications that are aggregated to produce a tissue segmentation and, in some embodiments, to classify the source image or a subregion thereof.

A high efficiency method of processing images to provide perceptual high-contrast output. Pixel intensities are calculated by a weighted combination of a fixed number of static bounding rectangle sizes. This is more performant than incrementally growing the bounding rectangle size and performing expensive analysis on resultant histograms. To mitigate image artifacts and noise, blurring and down-sampling are applied to the image prior to processing.

A pattern recognition system including an image gathering unit that gathers at least one digital representation of a field, an image analysis unit that pre-processes the at least one digital representation of a field, an annotation unit that provides a visualization of at least one channel for each of the at least one digital representation of the field, where the image analysis unit generates a plurality of image samples from each of the at least one digital representation of the field, and the image analysis unit splits each of the image samples into a plurality of categories.

A motion detection method includes providing a buffer including a first buffer associated with a background image and a second buffer associated with a foreground image; checking first similarity between the gray level of an input pixel and the first gray level of the first buffer; determining the input pixel as a still pixel if the first similarity is true; checking second similarity between the gray level and the second gray level of the second buffer; determining the input pixel as a moving pixel if the second similarity is false; determining the input pixel as the moving pixel if the second count value is less than the first count value; and determining the input pixel as the still pixel and swapping the first buffer with the second buffer, if the second count value is not less than the first count value.

A method includes steps of: capturing an image of a container; recognizing at least one object in the container based on the image; determining at least one first coordinate set corresponding to the at least one object; determining at least one second coordinate set that corresponds to target one (s) of the at least one first coordinate set and that relates to a fixed picking device of a robotic arm; adjusting position(s) of unfixed picking device(s) of the robotic arm if necessary; controlling the robotic arm to pick up one (s) of the at least one object that correspond(s) to the at least one second coordinate set with the fixed picking device and/or at least one unfixed picking device.

A method to culling parts of a 3D reconstruction volume is provided. The method makes available to a wide variety of mobile XR applications fresh, accurate and comprehensive 3D reconstruction data with low usage of computational resources and storage spaces. The method includes culling parts of the 3D reconstruction volume against a depth image. The depth image has a plurality of pixels, each of which represents a distance to a surface in a scene. In some embodiments, the method includes culling parts of the 3D reconstruction volume against a frustum. The frustum is derived from a field of view of an image sensor, from which image data to create the 3D reconstruction is obtained.

There is provided a method for creating artificial vision with an implantable visual stimulation device. The method comprises receiving image data comprising, for each of multiple points of the image, a depth value, performing a local background enclosure calculation on the input image to determine salient object information, and generating a visual stimulus to visualise the salient object information using the visual stimulation device. Determining the salient object information is based on a spatial variance of at least one of the multiple points of the image in relation to a surface model that defines a surface in the input image.