Abstract: A saliency detection explicitly models complementary information between appearance, or color, and depth information in images. A mutual-information minimization is used as a regularizer to reduce the redundancy between appearance features from RGB and geometric features from depth in the latent space. Then the latent features of each of the appearance and geometric modalities are fused to achieve multi-modal feature fusion for saliency detection.

Abstract: Systems and methods are provided for classifying an abnormality in a medical image. An input medical image depicting a lesion is received. The lesion is localized in the input medical image using a trained localization network to generate a localization map. The lesion is classified based on the input medical image and the localization map using a trained classification network. The classification of the lesion is output. The trained localization network and the trained classification network are jointly trained.

Abstract: A display device includes a control device configured to divide a display period of each frame of an image to be displayed into a first time period and a second time period; and send a light source control signal and a modulation signal corresponding to each pixel in the image to be displayed, according to original image data of each frame of the image to be displayed; a light source system configured to emit light source light according to the light source control signal, the light source light including first light and second light; and a light modulation device configured to modulate the first light according to the modulation signal to generate first image light of the image to be displayed, and modulate the second light according to the modulation signal to generate second image light of the image to be displayed.

Abstract: A display system includes: a light source system configured to emit light beams; a scanner configured to scan the light beams on the surface of a spatial light modulator in the form of a light spot, the light spot corresponding to multiple pixels of the spatial light modulator; a spatial light modulator configured to modulate, according to an image modulation signal from a processing and control system, the light spot projected onto the spatial light modulator by the scanner to output image light; a processing and control system configured to output a light source timing modulation signal to a light source modulation device according to an input image signal and output an image modulation signal to the spatial light modulator; and a light source modulation device configured to adjust the output brightness of the light source system according to the light source timing modulation signal.

Abstract: The present invention relates to compositions and methods of using those compositions for the diagnosis and treatment of immune related diseases.

Abstract: Provided is a projection display device for displaying a time period of one frame of stereo image as a first modulation period. The projection display device includes: a light source for emitting illumination light; a spatial light modulator for modulating the illumination light according to a plurality of frames of two-dimensional images corresponding to a stereo image to be displayed, and sequentially emitting, within the first modulation period, image light corresponding to the plurality of frames of the two-dimensional images; an angle deflection apparatus arranged in an emergent optical path of the image light and used for deflecting the image light corresponding to the plurality of frames of two-dimensional images to different angles for emission; and a projection screen for displaying the image light deflected by the angle deflection apparatus.

Abstract: Receive, by a price calculation microservice, tenant user input from a particular tenant of a multi-tenant system. Generate, by the price calculation microservice, a particular charge model based on the tenant user input. Detect, by a usage microservice, a usage event associated with a customer of the particular tenant of the multi-tenant system. Receive, by a rating microservice, a rating request, the rating request being received in response to the detecting the usage event. Calculate, by the price calculation microservice in response to the receiving the rating request, a usage charge for the usage event based on the particular charge model. Store, by the rating microservice, the usage charge. Generate an invoice based on the usage charge stored by the rating microservice. Provide the invoice to the customer of the particular tenant of the multi-tenant system.

Abstract: The display device comprises a light source device, an image pre-processing controller, and a light modulation device. The light source device emits first light and second light, wherein a color gamut range of the second light is wider than that of the first light. The image pre-processing controller acquires a color gamut range of the image to be displayed and a brightness value of each pixel based on original image data of an image data to be displayed, and determines a current color gamut range and controls the light source device to emit first light and the second light corresponding to amount of light required in the current color gamut range. The light modulation device modulates the light emitted by the light source device to generate image light of the image to be displayed based on image data corresponding to the current color gamut range.

Abstract: An automated parking system for a vehicle includes a camera configured to obtain images of objects proximate the vehicle, and a controller configured to review the obtained images of objects proximate the vehicle to classify an environment proximate the vehicle, determine a type of parking lot associated with the classified location and initiate an automated parking function of the vehicle corresponding to the determined type of parking lot.

Abstract: An automated vehicle parking system for a motor vehicle is disclosed and includes at least one camera obtaining images proximate a vehicle, at least one sensor array detecting objects proximate the vehicle, and a controller configured to generate a mask of an area proximate the vehicle from the images obtained by the at least one camera including labeled features identified within the obtained images and project the generated mask onto an occupancy grid generated with information from the at least one sensor array, wherein the controller is configured to locate a parking space responsive to open spaces defined within the generated mask.

Abstract: An automated parking system for a vehicle according to an exemplary embodiment of this disclosure includes, among other possible things, a camera configured to obtain images of objects proximate the vehicle, and a controller configured to review the obtained images of objects proximate the vehicle to classify a location of the vehicle, determine a height of overhead objects associated with the classified location and initiate an automated parking function of the vehicle that corresponds to the determined height of the overhead objects.

Abstract: A method of visual-inertial odometry for a ground vehicle is disclosed and includes obtaining an initial set of images with a camera on-board a vehicle, identifying features within the initial set of images, determining a three-dimensional pose using the visual features in the initial set of images, obtaining information indicative of vehicle movement with an inertial measurement unit, obtaining information indicative of vehicle movement with wheel speed sensors and a steering wheel angle sensor, fusing the identified features within the images, the vehicle movement from the IMU, and vehicle sensors within a two-dimensional plane, and determining a vehicle position relative to an initial start location based on the visual features in the images and the vehicle movement information from the IMU, wheel speed sensors, and the steering wheel angle.

Abstract: A method determining an angle of a trailer relative to a vehicle. The method includes generating a projection on a trailer with a projector. An image is obtained of the projection on the trailer with a camera. An angle of the trailer relative to a vehicle is determined by comparing the image of the projection with a known pattern of the projection.

Abstract: The display device provided in the present application comprises: a light source; a light modulator, comprising a digital micro-lens array comprising a plurality of micro reflective lenses, being arranged on the light path of the light emitted by the light source, and being used for modulating the light emitted by the light source on the basis of a target image and the light emission brightness of the light source in order to obtain a greyscale image; and a control apparatus, used for controlling a drive current of the light source, such that the light emission brightness of the light source is adjusted in separate time periods within the time of one image frame, and the drive current of the light source is overshot in at least some of the time periods in order to increase the display bit depth of the greyscale image from n to n+i (i?1 and i being an integer), each time period corresponding on a one-to-one basis with a bit plane of the greyscale image.

Abstract: A display device, including: a light source, used for emitting light source light; a control unit, used for controlling a drive current for the light source, the modulation period of each frame of image to be displayed comprising at least one pulse modulation period, and within the pulse modulation period, the drive current for the light source being an overshoot current so that the average luminous brightness of the light source in the modulation period reaches preset brightness; and a light modulation unit, used for modulating the light source light according to image data of the image to be displayed and the luminous brightness of the light source to obtain a modulated image.

Abstract: A method for determining a position of a tow ball in an image. The method includes obtaining at least one real-time image from a vehicle. The at least one real-time image is processed with a controller on the vehicle to obtain a feature patch (f) describing at least one real-time image. A convolution is performed of the feature patch (f) and each filter (h) from a set of filters (H) with the filter (h) being based on data representative of known tow hitches fixed to the vehicle. A location of a tow ball on the tow hitch is identified in the at least one real-time image is based on the convolution between the feature patch (f) and each filter (h) from the set of filters (H).

Abstract: A method of determining a tow hitch position. The method includes obtaining a two-dimensional image of a tow hitch in a three-dimensional scene. A model tow hitch is obtained in three dimensions. A three-dimensional rendering of a scene is generated that includes the model tow hitch. The model tow hitch in the three-dimensional rendering is positioned in an orientation corresponding with an orientation of the tow hitch in the three-dimensional scene.

Abstract: A display system includes a light source system including a light source array formed from multiple light source units, and used to emit a light beam, wherein the light source array can be divided into I×J sub-regions; a display unit disposed on an emergent light path of the light source system, and used to modulate a light spot on a surface thereof according to a light spot modulation signal, so as to generate image light; and a dynamic control module for obtaining the light spot modulation signal and a current modulation signal according to an image signal, dynamically updated chromaticity information and maximum brightness information of the light source units, and a correlation curve between a modulation current and brightness, wherein the current modulation signal is used to adjust the light source system.

Abstract: A method for autonomously parking a vehicle-trailer system is provided. The method includes receiving sensor system data from a sensor system supported by the vehicle. The sensor system data includes images of surroundings along a driving path of the vehicle-trailer system. The method includes determining a local map based on the sensor system data. The local map includes surroundings along the driving path. The method includes receiving a user selection of an image location within the images. The image location representing a position in the local map associated with a selected location within the surroundings. The method includes determining a parking path from a current location of the vehicle-trailer system to the position based on the local map and instructing a drive system to execute an autonomous parking behavior causing the vehicle-trailer system to autonomously drive along the parking path and autonomously park in the selected location.

Abstract: A display apparatus comprises a light source device, an image data processing module, a light modulating device and an image synthesizing device. The light source device is configured to emit first light and second light. The image data processing module is configured to receive original image data of an image to be displayed, wherein the original image data of the image to be displayed is based on image data within a second color gamut range and comprises original control signal values of m colors of each pixel; the second color gamut range covers a first color gamut range and has a portion that exceeds the first color gamut range. The image data processing module is further configured to map the original control signal values of the m colors into m corrected control signal values corresponding to the first light and n corrected control signal values corresponding to the second light.