Abstract: Systems and methods for Mixed Reality (MR) applications in a head-mounted display. In implementations, an ambient light sensor (ALS) or world-side camera capture an ambient light measurement of an environment of a world-side scene. In some aspects, based on the ambient light measurement, one or more processing logic may be configured to adjust a brightness and/or color temperature of pass-through images and virtual images to harmonize a user's viewing experience while using the head-mounted display.

Abstract: A display of a head-mounted display renders a video-viewing window. A bias lighting boundary is rendered between the video-viewing window and a background. The bias lighting boundary reduces a contrast between the video-viewing window and the background.

Abstract: An electronic device may include a display, an ambient light sensor, and control circuitry. The control circuitry may use a mesopic vision model to compensate images that are displayed in low light conditions when the measured ambient light brightness is below a threshold. The mesopic vision model may use a tone mapping process and a color mapping process to compensate for the reduced color sensitivity of the retina in low light conditions. The control circuitry may iteratively adjust weights associated with the tone mapping process and the color mapping process until a perceived (retinal) version of the compensated image in the measured ambient light conditions closely matches a perceived (retinal) version of the original image in reference ambient light conditions. The control circuitry may use a joint optimization process that balances the contrast and color of the compensated image.

Abstract: Systems and methods for improving perceptual consistency of imaging data displayed on a wearable mobile device may include determining ambient light intensity in an operating environment of a mobile device. The systems and methods may include storing image data on the mobile device. The image data number of pixels, and each of the number of pixels includes color characteristics. The systems and methods may include adjusting the color characteristics of the image data based on the intensity level of the light. Adjusting the color characteristics may include applying a color perception model to the image data to generate adjusted image data. The color perception model is configured to adjust hue color characteristics and tone color characteristics of the image data. The systems and methods may include displaying the adjusted image data on a display of the mobile device.

Abstract: Systems and methods are provided for displaying augmented reality image content perceived as being overlaid on background image content viewed through a light-transmissive viewing surface. Image processing circuitry may receive input augmented reality image data corresponding with a pixel position on the display panel, determine a perceived background brightness metric indicative of background brightness level at the pixel position based at least in part on captured background image data and an ambient lighting metric, determine a target tone mapping based at least in part on the perceived background brightness metric, and determine display augmented reality image data to be used by a display panel to display the augmented reality image content least in part by applying the target tone mapping to the input augmented reality image data.

Abstract: An electronic device may include a display, an ambient light sensor, and control circuitry. The control circuitry may use a mesopic vision model to compensate images that are displayed in low light conditions when the measured ambient light brightness is below a threshold. The mesopic vision model may use a tone mapping process and a color mapping process to compensate for the reduced color sensitivity of the retina in low light conditions. The control circuitry may iteratively adjust weights associated with the tone mapping process and the color mapping process until a perceived (retinal) version of the compensated image in the measured ambient light conditions closely matches a perceived (retinal) version of the original image in reference ambient light conditions. The control circuitry may use a joint optimization process that balances the contrast and color of the compensated image.

Abstract: The present invention relates to a clustering method based on iterations of neural networks, which comprises the following steps: step 1, initializing parameters of an extreme learning machine; step 2, randomly choosing samples of which number is equal to the number of clusters, each sample representing one cluster, forming an initial exemplar set and training the extreme learning machine; step 3, using current extreme learning machine to cluster samples, which generates a clustering result; step 4, choosing multiple samples from each cluster as exemplars for the cluster according to a rule; step 5, retraining the extreme learning machine by using the exemplars for each cluster obtained from step 4; and step 6, going back to step 3 to do iteration, otherwise obtaining and outputting clustering result until clustering result is steady or a maximal limit of the number of iterations is reached.

Abstract: A method for outputting a video frame is disclosed, and the method includes: acquiring video images from multiple view angles; fusing and stitching, according to view angle information provided by a user terminal, video images of corresponding view angles to form a local video frame matching the view angle information; and providing the local video frame to the user terminal.

Abstract: A multi-image adjusting method and device and a Multipoint Controller Unit (MCU) are provided. The method includes that: the MCU receives code streams sent by multiple terminals, and synthesizes a multi-image after decoding videos; the MCU receives an adjustment request for a sub-image in the multi-image, and adjusts a display parameter of a corresponding sub-image according to the adjustment request; and the MCU codes and sends the adjusted multi-image to a corresponding terminal.

Abstract: Methods and systems are provided for scatter correction in Positron Emission Tomography (PET) imaging. In one embodiment, a method comprises performing an emission scan to acquire emission data, identifying outliers in a tail region of the emission data, discarding a portion of the outliers from the emission data, calculating a linear fit to remaining emission data in the tail region, and correcting the emission data based on the linear fit. In this way, scatter coincidence events can be eliminated even if the emission data is spatially misaligned with transmission data.

Abstract: A method of establishing a 3D saliency model based on 3D contrast and depth weight, includes dividing left view of 3D image pair into multiple regions by super-pixel segmentation method, synthesizing a set of features with color and disparity information to describe each region, and using color compactness as weight of disparity in region feature component, calculating feature contrast of a region to surrounding regions; obtaining background prior on depth of disparity map, and improving depth saliency through combining the background prior and the color compactness; taking Gaussian distance between the depth saliency and regions as weight of feature contrast, obtaining initial 3D saliency by adding the weight of the feature contrast; enhancing the initial 3D saliency by 2D saliency and central bias weight.

Abstract: A method of establishing a 3D saliency model based on 3D contrast and depth weight, includes dividing left view of 3D image pair into multiple regions by super-pixel segmentation method, synthesizing a set of features with color and disparity information to describe each region, and using color compactness as weight of disparity in region feature component, calculating feature contrast of a region to surrounding regions; obtaining background prior on depth of disparity map, and improving depth saliency through combining the background prior and the color compactness; taking Gaussian distance between the depth saliency and regions as weight of feature contrast, obtaining initial 3D saliency by adding the weight of the feature contrast; enhancing the initial 3D saliency by 2D saliency and central bias weight.

Abstract: The present invention relates to a clustering method based on iterations of neural networks, which comprises the following steps: step 1, initializing parameters of an extreme learning machine; step 2, randomly choosing samples of which number is equal to the number of clusters, each sample representing one cluster, forming an initial exemplar set and training the extreme learning machine; step 3, using current extreme learning machine to cluster samples, which generates a clustering result; step 4, choosing multiple samples from each cluster as exemplars for the cluster according to a rule; step 5, retraining the extreme learning machine by using the exemplars for each cluster obtained from step 4; and step 6, going back to step 3 to do iteration, otherwise obtaining and outputting clustering result until clustering result is steady or a maximal limit of the number of iterations is reached.

Abstract: The present invention discloses a method for detecting a salient region of a stereoscopic image, comprising: step 1) calculating flow information of each pixel separately with respect to a left-eye view and a right-eye view of the stereoscopic image; step 2) matching the flow information, to obtain a parallax map; step 3) selecting one of the left-eye view and the right-eye view, dividing it into T non-overlapping square image blocks; step 4) calculating a parallax effect value for each of the image blocks of the parallax map; step 5) for each of the image blocks of the selected one of the left-eye view and the right-eye view, calculating a central bias feature value and a spatial dissimilarity value, and multiplying the three values, to obtain a saliency value of the image block; and step 6) obtaining a saliency gray scale map of the stereoscopic image from saliency values of the image blocks.

Abstract: The present invention discloses a method for detecting a salient region of a stereoscopic image, comprising: step 1) calculating flow information of each pixel separately with respect to a left-eye view and a right-eye view of the stereoscopic image; step 2) matching the flow information, to obtain a parallax map; step 3) selecting one of the left-eye view and the right-eye view, dividing it into T non-overlapping square image blocks; step 4) calculating a parallax effect value for each of the image blocks of the parallax map; step 5) for each of the image blocks of the selected one of the left-eye view and the right-eye view, calculating a central bias feature value and a spatial dissimilarity value, and multiplying the three values, to obtain a saliency value of the image block; and step 6) obtaining a saliency gray scale map of the stereoscopic image from saliency values of the image blocks.

Abstract: The present invention discloses a method for retrieving a similar image based on visual saliencies and visual phrases, comprising: inputting an inquired image; calculating a saliency map of the inquired image; performing viewpoint shift on the saliency map by utilizing a viewpoint shift model, defining a saliency region as a circular region which taking a viewpoint as a center and R as a radius, and shifting the viewpoint for k times to obtain k saliency regions of the inquired image; extracting a visual word in each of the saliency regions of the inquired image, to constitute a visual phrase, and jointing k visual phrases to generate an image descriptor of the inquired image; obtaining an image descriptor for each image of an inquired image library; and calculating a similarity value between the inquired image and each image in the inquired image library depending on the image descriptors by utilizing a cosine similarity, to obtain an image similar to the inquired image from the inquired image library.