Abstract: The present disclosure relates to a patient motion tracking system for automatic generation of a region of interest on a 3D surface of a patient positioned in a radiotherapy treatment room. More particularly, the disclosure relates to an assistive approach of a motion tracking system, by which a region of interest (ROI) is automatically generated on a generated 3D surface of the patient. Furthermore, a method for automatically generating a ROI on the 3D surface of the patient is described. In particular, all the embodiments refer to systems integrating methods for automatic ROI generation in a radiotherapy treatment setup.

Abstract: An obstacle detection method and device, an apparatus and a storage medium are provided, which are related to a field of intelligent transportation. The specific implementation includes: acquiring position information of a two-dimensional (2D) detection frame and position information of a three-dimensional (3D) detection frame of an obstacle in an image; converting the position information of the 3D detection frame of the obstacle into position information of a 2D projection frame of the obstacle; and optimizing the position information of the 3D detection frame of the obstacle by using the position information of the 2D detection frame, the position information of the 3D detection frame and the position information of the 2D projection frame of the obstacle in the image. Accuracy of results of predicting a 3D position of an obstacle by a roadside, on-board sensing device, or other sensing devices may be improved.

Abstract: The present disclosure provides systems and methods that makes use of one or more image sensors of a device to provide users with information relating to nearby points of interest. The image sensors may be used to detect features and/or objects in the field of view of the image sensors. Pose data, including a location and orientation of the device is then determined based on the one or more detected features and/or objects. A plurality of points of interest that are within a geographical area that is dependent on the pose data are then determined. The determination may, for instance, be made by querying a mapping database for points of interest that are known to be located within a particular distance of the location of the user. The device then provides information to the user indicating one or more of the plurality of points of interest.

Abstract: The present teaching relates to method, system, medium, and implementations for trailer pose estimation. At least a dimension of a trailer connected to a vehicle is obtained where the vehicle and the trailer have respective opposing surfaces facing one another. A first set of feature points is identified from a first image of a target present on one the opposing surfaces acquired at a first time instant by a sensor deployed on the other the opposing surfaces. A second set of corresponding feature points is identified from a second image of the target acquired at a subsequent time instant by the sensor. Based on the first and second sets of feature points, a first transformation is determined and used to compute a second transformation that the trailer undergoes from the first to the second time instants. A pose of the trailer at the second time instant is estimated based on the second transformation and the dimension.

Abstract: Computing devices and methods are provided to automatically characterize a localization system tracker for a procedure. A starting tracker definition is refined until convergence using an iterative process and measured features of the tracker in images provided by a localization system camera. In each iteration, poses are determined from the measured features using a current tracker definition. The current definition is then refined using the poses and an optimization function. Tracker images may be captured passively, when performing other procedure steps. In a robotic context, command trajectories move a robot may be to respective poses where images to characterize the tracker are captured. An updated trajectory may be commanded to optimize convergence, additionally using the measured features at the updated pose in the iterative process. A robot kinematic model may be defined, refining a starting model using tracker poses from the localization system and sensor positions from the robot system.

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Abstract: A remote-controlled weapon system, mounted in a moving platform, includes at least one processor that implements: a first posture calculator that calculates a first pixel movement amount corresponding to a posture change amount of a camera during a time interval between a first image and a second image, received after the first image; a second posture calculator that calculates a second pixel movement amount corresponding to a control command for changing a posture of the camera to match a moving target, detected from the second image, with an aiming point; and a region of interest (ROI) controller that calculates a third pixel movement amount corresponding to vibration of the camera based on the first pixel movement amount and the second pixel movement amount, and estimate a location of an ROI that is to be set on the moving target of the second image, based on the third pixel movement amount.

Abstract: The invention relates to a method for calculating three-dimensional information of food received within a cavity of a food preparation entity, the method comprising the steps of: capturing at least one image of said food received within the cavity by a plenoptic camera, said image comprising information regarding the light intensity and the direction of light rays traveling in space; or capturing at least two images of said food received within the cavity, said images being taken from different positions during movement of a camera; or capturing at least two images of said food received within the cavity using a camera, said images comprising different focus points; and processing the at least one image in order to establish three-dimensional information of said food received within the cavity.

Abstract: Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

Abstract: The disclosed method encompasses reconstruction of a three-dimensional position of a tracking structure (which may comprise a target of radiation treatment) as reconstructed tracking structure data from pairs of two-dimensional tracking images which are input as tracking image data. Each tracking image contained in a pair of tracking images is compared to a tracking representation of the tracking structure contained in a search template image generated from the same perspective onto the tracking structure as the associated tracking image and input as search template data. The tracking image having the highest at local degree of similarity to its associated search template image is selected as a starting point (the first tracking image) for computing a corresponding image position (a complement point) in the other tracking image (the second tracking image) on the basis of applying epipolar geometry outgoing from the position in the first tracking image associated with the highest local degree of similarity.

Abstract: A leather inspection apparatus is provided for detecting inconsistencies on both upper and lower surfaces of a hide. It includes a first camera assembly movably coupled to a support frame and capable of movement along the upper surface of the hide and a second camera assembly movably coupled to the support frame and capable of movement along the lower surface of the hide. A computing device is coupled to the first camera assembly and the second camera assembly, such that the first camera assembly detects the locations of inconsistencies in the upper surface of the hide and the second camera assembly detects the locations of inconsistencies in the lower surface of the hide. The computing device digitally stores the locations of the inconsistencies of the upper surface of the hide and the locations of the inconsistencies of the lower surface of the hide.

Abstract: Systems and methods are provided for navigating an autonomous vehicle. In one implementation, a system for navigating a vehicle includes at least one processing device programmed to receive, from an image capture device, a plurality of images associated with an environment of the vehicle, analyze at least one of the plurality of images to identify a navigable region in the environment of the vehicle, identify, based on the at least one of the plurality of images, at least one barrier associated with an edge of the navigable region, and determine a type of the at least one barrier. The at least one processing device is also programmed to determine a navigational path of the vehicle based on the determined type of the at least one barrier, and cause the vehicle to travel on at least a portion of the determined navigational path.

Abstract: A position estimating apparatus includes a memory that stores a reference image, an interface circuit configured to communicate with a movable apparatus, and a processor. The processor is configured to, upon receipt of at least one image captured by the movable apparatus via the interface circuit, calculate an evaluation value for each of a plurality of regions of the image, and determine a current position of the movable apparatus by comparing the regions of the captured image where the calculated evaluation value exceeds a first threshold with the reference image.

Abstract: Embodiments disclose apparatus, methods and software for performing biological screening and analysis implemented using an instrument platform capable of detecting a wide variety of cell-based secretions, expressed proteins, and other cellular components. The platform may be configured for simultaneous multiplexed detection of a plurality biological components such that a large number of discrete samples may be individually sequestered and evaluated to detect or identify constituents from the samples in a highly parallelized and scalable manner.

Abstract: Techniques for distinguishing objects (e.g., an individual or an individual pushing a shopping cart) are disclosed. An object is detected in images of a scene. A height map is generated from the images, and the object is represented as height values in the height map. Based on height properties associated with another object, it is determined whether the other object is associated with the object. If so determined, the objects are classified separately.

Abstract: Provided are an image difference-based method and system for tracking a transparent object, first by training a convolutional neural network based on sample data, to generate a transparent object detection model; then inputting visible light image data acquired in real time and infrared thermal image data acquired in real time to the transparent object detection model, to acquire a visible light image transparent pixel identifier and an infrared thermal image transparent pixel identifier; then calculating three-dimensional point cloud information of each pixel marked by the infrared thermal image transparent pixel identifier, in the infrared thermal image data, wherein the three-dimensional point cloud information is in a coordinate system of an infrared thermal imaging camera; wherein the infrared thermal imaging camera is a camera for acquiring the infrared thermal image data, thereby acquiring, according to the three-dimensional point cloud information, corresponding position coordinates of each pixel, whi

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Abstract: A system for updating training data includes an interface and a processor. The interface is configured to receive a set of vehicle data. The set of vehicle data includes images and assigned labels associated with the images. The processor is configured to determine a set of training data and a set of test data from the set of vehicle data; train a model with the set of training data; determine a set of predicted labels for the set of vehicle data using the model; identify a set of potential mislabeled data using the set of predicted labels and the assigned labels; and determine an updated set of training data by relabeling the set of potential mislabeled data and replacing the set of potential mislabeled data with a relabeled set of data.

Abstract: A landing tracking control method comprises the following contents: a tracking model training stage and an unmanned aerial vehicle real-time tracking stage. The landing tracking control method extracts a network Snet by using a lightweight feature and makes modification, so that an extraction speed of the feature is increased to better meet a real-time requirement. Weight allocation on the importance of channel information is carried out to differentiate effective features more purposefully and utilize the features, so that the tracking precision is improved. In order to improve a training effect of the network, a loss function of an RPN network is optimized, a regression precision of a target frame is measured by using CIOU, and meanwhile, calculation of classified loss function is adjusted according to CIOU, and a relation between a regression network and classification network is enhanced.

Abstract: A simultaneous localization and mapping device is provided. The device includes an image obtaining device configured to capture color images and depth images of a surrounding environment; an initial pose estimating device configured to estimate an initial pose based on the color images and the depth images; a map constructing device configured to construct a three-dimensional map based on the depth images and the color images; and a pose determining device configured to determine a final pose based on the initial pose and the three-dimensional map.