Abstract: Systems and methods of tracking objects around an ego vehicle, using state estimation of the objects, where state estimation may include an estimate of a position, velocity, acceleration and bounding box size of the tracked object are disclosed. An object may be detected at one or more poses over time. For each pose, a first bounding box may be generated. The largest bounding box may be determined. For each pose, the first bounding box may be expanded to an expanded bounding box. The expanded bounding box may match the largest bounding box. For each pose, the center of the expanded bounding box may be determined. The object may be tracked according to the center of the expanded bounding box.

Abstract: Techniques for scanning physical media on physical items and providing information about those physical items are provided. In one technique, based on a printed medium of a physical item, a mobile device generates digital scan data that reflects multiple individual items that are referenced on the printed medium. The mobile device sends, over a computer network, to a remote server, the digital scan data or data that identifies individual items. The remote server determines a toxicity metric for each individual item. The remote server generates, based solely on each toxicity metric, a safeness rating of the physical item. Rating data is generated based on the safeness rating and presented on a screen of the mobile device in association with data that identifies the physical item.

Abstract: A system and method for three-dimensional (3D) object detection is disclosed. A particular embodiment can be configured to: receive image data from a camera associated with a vehicle, the image data representing an image frame; use a machine learning module to determine at least one pixel coordinate of a two-dimensional (2D) bounding box around an object in the image frame; use the machine learning module to determine at least one vertex of a three-dimensional (3D) bounding box around the object; obtain camera calibration information associated with the camera; and determine 3D attributes of the object using the 3D bounding box and the camera calibration information.

Abstract: A computer-implemented method is provided for improving image quality with shortened acquisition time. The method comprises: determining an accelerated image acquisition scheme for imaging a subject using a medical imaging apparatus; acquiring a medical image of the subject according to the accelerated image acquisition scheme using the medical imaging apparatus; applying a deep network model to the medical image to improve the quality of the medical image; and outputting an improved quality image of the subject, for analysis by a physician.

Abstract: An image evaluation device includes a determination result acquisition unit acquires a result of determining the presence or absence of a difference between an object image that is one of a plurality of images that include three or more images obtained by imaging substantially the same spatial region and each of reference images that are images other than the object image among the plurality of images and an evaluation index acquisition unit configured to acquire an evaluation index for the plurality of images on the basis of at least one of the number of determinations of the presence of the difference between the object image and each reference image and the number of determinations of the absence of the difference between the object image and each reference image.

Abstract: A system for monitoring a patient in a patient area having one or more detection zones, the system comprising one or more cameras, a user interface, and a computing system configured to receive a chronological series of frames from the one or more cameras, identify liquid candidates by comparing a current frame with a plurality of previous frames of the chronological series, determine locations of the liquid candidates, identify thermal signatures of the liquid candidates, determine types of liquids of the liquid candidates based on the locations and thermal signatures of the liquid candidates, and generate an alert with the user interface corresponding to the determined types of liquids.

Abstract: Provided is an image processing device including a matching unit that performs matching processing between a predetermined pattern on a surface of a 3D model of a biological tissue including an operating site generated on the basis of a preoperative diagnosis image and a predetermined pattern on a surface of the biological tissue included in a captured image during surgery, a shift amount estimation unit that estimates an amount of deformation from a preoperative state of the biological tissue on the basis of a result of the matching processing and information regarding a three-dimensional position of a photographing region which is a region photographed during surgery on the surface of the biological tissue, and a 3D model update unit that updates the 3D model generated before surgery on the basis of the estimated amount of deformation of the biological tissue.

Abstract: A method and a system for image-guided intervention such as a percutaneous treatment or diagnosis of a patient may include at least one of a pre-registration method and a re-registration method. The pre-registration method is configured to permit for an efficient virtual representation of a planned trajectory to target tissue during the intervention, for example, as a holographic light ray shown through an augmented reality system. In turn, this allows the operator to align a physical instrument such as a medical probe for the intervention. The re-registration method is configured to adjust for inaccuracy in the virtual representation generated by the pre-registration method, as determined by live imaging of the patient during the intervention. The re-registration method may employ the use of intersectional contour lines to define the target tissue as viewed through the augmented reality system, which permits for an unobstructed view of the target tissue for the intervention.

Abstract: Machine learning technologies are used to identify and separating abnormal and normal subjects and identifying possible disease types with images (e.g., optical coherence tomography (OCT) images of the eye), where the machine learning technologies are trained with only normative data. In one example, a feature or a physiological structure of an image is extracted, and the image is classified based on the extracted feature. In another example, a region of the image is masked and then reconstructed, and a similarity is determined between the reconstructed region and the original region of the image. A label (indicating an abnormality) and a score (indicating a severity) can be determined based on the classification and/or the similarity.

Abstract: A processing device receives, from a three-dimensional (3D) motion capture system, initial data representing an initial orientation of a subject user's body in an initial position. The processing device further receives x-ray data representing at least the portion of the subject user's body in the initial position. The processing device determines an actual orientation of at least one bone or joint from the portion of the subject user's body in the initial position as represented in the x-ray data and calibrates the initial orientation of the 3D motion capture system to reflect the actual orientation of the at least one bone or joint in the initial position.

Abstract: A method for gating in tomographic imaging system includes steps of: (a) performing a tomographic imaging on an object with a target moving periodically along a first axis for acquiring projection images; (b) obtaining projected curves by summing up pixel values along a direction of a second axis perpendicular to the first axis in each projection image; (c) determining a target zone on the projection images, wherein a central position on the first axis of the target zone is corresponding to a position having the largest variation in the projected curves on the first axis; (d) calculating parameter values of pixel values in the target zones and obtaining a curve of a moving cycle of the target according to the parameter values; and (e) selecting the projection images under the same state in the moving cycle for image reconstruction according to the curve of the moving cycle of the target.

Abstract: A computer-implemented method for evaluating colonoscopy performance includes: (S1) splitting a video acquired during a colonoscopy examination into a plurality of colonoscopy images; (S2) assigning each of the colonoscopy images into a fold-inspection group or a non-fold-inspection group according to a first classification criterion and a second classification criterion, wherein the first classification criterion comprises at least one of clarity, exposure, level of tissue wrinkling, and level of occlusion in each of the colonoscopy images; and the second classification criterion comprises at least one of an amount of haustrum, an amount of colonic lumen, and a position of the colonic lumen in each of the colonoscopy images; and (S3) determining a performance rating of the colonoscopy examination according to an elapsed time of the fold-inspection group.

Abstract: An imaging system includes a light source for emitting visible light and infrared light and a camera head unit configured to capture visible light image data so as to generate a visible light image frame and configured to capture infrared image data so as to generate an infrared image frame. A camera control unit is configured to extract a structural data from the visible light image frame. The camera control unit is further configured to apply the structural data to the infrared image frame so as to enhance the infrared image with structural data.

Abstract: A method and a system for determining a tooth trajectory for a given tooth of a subject are provided. The method comprises: generating, by executing an optimization algorithm, based on a 3D model of the given tooth, a plurality of segments defining a tooth trajectory of the given tooth from its initial position to its target position. The executing comprises: determining, based on the stress values range, an initial force to be applied to the given tooth, the initial force causing a maximum displacement of the 3D model of the given tooth from the start position associated with the given segment towards the target position associated with the given tooth, thereby identifying an end position associated with the given segment. The method further comprises determining a respective force applied to at least one other 3D model by the maximum displacement of the 3D model of the given tooth.

Abstract: Optical sensors and optical markers are placed on components in a medical system to provide calibration and alignment, such as on a patient transportation mechanism and spatially separated medical diagnostic devices. Image processing circuitry uses the data captured by these optical devices to coordinate their movements and/or position. This enables scans that were captured in multiple medical diagnostic devices to be accurately aligned.

Abstract: According to an embodiment, an electronic device includes a camera, and at least one processor configured to: determine, from an image including a face of a user obtained via the camera, skin information indicating a skin condition of the user, generate control information for controlling a skin-care device to perform care based on the determined skin information and information regarding the skin-care device, and provide the control information to the skin-care device.

Abstract: A method and apparatus comprising generating a dynamic personalized webpage is disclosed. At least two webpages are loaded in a fashion that is hidden from the user. Content from the at least two webpages is extracted based on classification “of interest” by an artificial intelligence algorithm. A dynamic personalized webpage comprising extracted content is then generated and displayed to the user. In the preferred embodiment, the user's dynamic personalized webpage will be filled with advertisements tailored to the user and the user would receive at least some revenue from advertisements.

Abstract: The present invention relates to a device for skin condition analysis and skin disease diagnosis. The skin condition analysis and skin disease diagnosis device according to the present invention is an all-in-one type device that can perform not only cosmetic skin condition analysis but also diagnosis of medical skin disease items.

Abstract: According to various embodiments, an image analysis server for determining whether an image is suitable for skin analysis may include a DB management unit for obtaining a captured image from a skin measurement device and storing the captured image; a user detector for detecting a user's face based on the obtained image; an image suitability determination unit for determining whether the obtained image is suitable for skin analysis; a skin analyzer for analyzing skin corresponding to the detected user's face based on the image determined to be suitable for skin analysis; and a service providing unit for calculating a skin score according to the analysis and providing the calculated skin score to a user terminal.

Abstract: An ultrasound diagnostic apparatus includes an image memory, an operation unit, a measurement item designation receiving unit for receiving a designation of a measurement item, a detection measurement algorithm setting unit that sets a detection measurement algorithm, a frame designation receiving unit that receives a designation of a frame to be used for the measurement among a plurality of frames in the image memory, a measurement position designation receiving unit that receives a designation of a position of a measurement target on a first measurement frame received by the frame designation receiving unit, a measurement position setting unit that sets the position of the measurement target on a frame other than the first measurement frame, a measurement unit that detects the measurement target on the plurality of frames to calculate the measurement value, and a final measurement value calculation unit that calculates a final measurement value.