Abstract: System, methods, and other embodiments described herein relate to tracking dynamic objects in a surrounding environment of a vehicle. In one embodiment, a method includes, in response to acquiring sensor data from at least one sensor, generating a current occupancy map that indicates locations of occupied grid cells as identified by the sensor data. The method includes updating a difference map according to the current occupancy map. The difference map encodes temporal changes in relation to prior states of occupancy of the grid cells to track dynamic objects in the surrounding environment over a defined temporal horizon. The method includes computing dynamics of the dynamic objects according to the difference map. The method includes providing the dynamics to at least one vehicle system within the vehicle.

Abstract: A method for monitoring the shape of teeth including: producing a three-dimensional digital model of at least one portion of an arch of the patient or “initial reference model”; acquiring at least one two-dimensional image of the arches, referred to as “updated image”, under actual acquisition conditions; analysing each updated image and producing an updated map relating to a piece of discriminating information; optionally determining rough virtual acquisition conditions that approximate the actual acquisition conditions; searching each updated image for a final reference model corresponding to the shape of the teeth, and optionally to the positioning of the teeth, during the acquisition of the updated image; and comparing the shapes of the initial reference model and of the reference model obtained at the end of the preceding steps, referred to as “final reference model”, in order to determine the deformation and/or the movement of teeth between steps a) and b).

Abstract: The following provides an exemplary method. An image is generated. Scan data generated by the sensing of a subject brain is received and a sequence of volumetric-images are accessed. For at least some of the voxels in at least some of the volumetric images, a change value is determined for the voxel by comparing the current-intensity value of the voxel to the adjacent-intensity value of the comparison voxel. For at least some of the plurality volumetric images, a first-aggregate is determined using at least a mean value of change values of the volumetric image and a second-aggregate is determined using at least a median value of change values of the volumetric image. At least one, but not all, of the volumetric images is determined as invalid as a result of the aggregates.

Abstract: Provided herein is technology relating to analysis of images and particularly, but not exclusively, to methods and systems for determining the area and/or volume of a region of interest using optical coherence tomography data. Some embodiments provide for determining the area and/or volume of a lesion in retinal tissue using three-dimensional optical coherence tomography data and a two-dimensional optical coherence tomography fundus image.

Abstract: A method for determining a motion vector field is provided, comprising: determining an optical flow of a spatial point in a scene according to different frames of images acquired by an image acquisition unit; determining a movement velocity of the spatial point in a coordinate system of the image acquisition unit according to spatial point data; determining a first order derivative of a projection of the spatial point on an image plane according to the spatial point data; and determining a velocity vector of the spatial point according to intrinsic parameters, a rotation matrix in a global coordinate system, a movement velocity, and an angular velocity, of the image acquisition unit, as well as a pose, the optical flow, the movement velocity in the coordinate system of the image acquisition unit, and the first order derivative of the projection on the image plane, of the spatial point.

Abstract: Method, electronic device, and computer readable medium embodiments are disclosed. In one embodiment, a method includes training a neural network using a first image dataset and a first truth dataset, then using the trained neural network to analyze a second image dataset. The training includes modifying a loss function of the neural network to forego penalizing the neural network when a feature is predicted with higher than a first confidence level by the neural network, and the first truth dataset has no feature corresponding to the predicted feature.

Abstract: Provided is a method for setting an edge blur according to a brightness value including a first step for providing a plurality of target sheets on each of which a reference pattern for detecting a reference line and a grid pattern for detecting an edge position are provided, and in which changes in brightness values included in the grid patterns are different from each other, a second step for capturing images of the target sheets to obtain target sheet images, a third step for analyzing a reference pattern for each corresponding target sheet to estimate the reference line, and analyzing the grid pattern to extract an edge profile provided in the grid pattern, a fourth step for calculating a gradient of a brightness difference between adjacent pixels on the basis of the edge profile, and acquiring a background edge blur parameter and a foreground edge blur parameter on the basis of the gradient according to brightness contrast present in the image, and a fifth step for generating background edge blur predicti

Abstract: A back-propagation significance detection method based on depth map mining, comprising: for an input image Io, at a preprocessing phase, obtaining a depth image Id and an image Cb with four background corners removed of the image Io; at a first processing phase, carrying out positioning detection on a significant region of the image by means of the obtained image Cb with four background corners removed and the obtained depth image Id to obtain the preliminary detection result S1 of a significant object in the image; then carrying out depth mining on a plurality of processing phases of the depth image Id to obtain corresponding significance detection results; and then optimizing the significance detection result mined in each processing phase by means of a back-propagation mechanism to obtain a final significance detection result map. The method can improve the detection accuracy of the significance object.

Abstract: A method and apparatus is provided that uses a deep learning (DL) network to correct projection images acquired using an X-ray source with a large focal spot size. The DL network is trained using a training dataset that includes input data and target data. The input data includes large-focal-spot-size X-ray projection data, and the output data includes small-focal-spot-size X-ray projection data (i.e., smaller than the focal spot of the input data). Thus, the DL network is trained to improve the resolution of projection data acquired using a large focal spot size, and obtain a resolution similar to what is achieved using a small focal spot size. Further, the DL network is can be trained to additional correct other aspects of the projection data (e.g., denoising the projection data).

Abstract: There is provided an image processing apparatus and an image processing method that make it possible to reduce the transmission amount of data. The image processing apparatus includes a segmentation section configured to generate, for a plurality of point-of-view images of an object from a plurality of points of view, a plurality of segmentation images each of which is narrowed to a region that includes the object. The present technology can be applied to an encoding device, a decoding device and so forth of a system that performs generation and display of a bird view video, for example, on the basis of a plurality of point-of-view images captured from a plurality of points of view or a plurality of point-of-view images that are CG images from a plurality of points of view.

Abstract: Imaging methods, imaging apparatus and computer program products are disclosed. An imaging method comprises: receiving image data of a 3-dimensional object; and allocating a confidence level to at least a portion of an image frame of the image data using a machine-learning algorithm, the confidence level indicating a likelihood of that image frame having a specified element imaged on a specified plane through the 3-dimensional object. In this way, particular elements when imaged in a desired way can be identified from image data of the 3-dimensional object.

Abstract: Disclosed are devices, systems and methods for incorporating a smoothness constraint for camera pose estimation. One method for robust camera pose estimation includes determining a first bounding box based on a previous frame, determining a second bounding box based on a current frame that is temporally subsequent to the previous frame, estimating the camera pose by minimizing a weighted sum of a camera pose function and a constraint function, where the camera pose function tracks a position and an orientation of the camera in time, and where the constraint function is based on coordinates of the first bounding box and coordinates of the second bounding box, and using the camera pose for navigating the vehicle. The method may further include generating an initial estimate of the camera pose is based on a Global Positioning System (GPS) sensor or an Inertial Measurement Unit (IMU).

Abstract: A method for improving robustness of a visual-inertial navigation system includes: determining a reference frame; correcting the reference frame; and performing non-linear optimization for frames other than the reference frame and an oldest frame according to the oldest frame and the corrected reference frame.

Abstract: A method and a device for detecting an object stacking state, and an intelligent shelf are disclosed. The method comprises capturing a color image and a depth image that are aligned with each other above a reference plane in which the object is located, identifying the object and an area occupied by the object in the color image, converting the depth image into a height map relative to the reference plane, determining a reference height of the object based on the height map and the area occupied by the object, acquiring an actual height of the object based on the identified object, and comparing the reference height of the object with the actual height of the object and judging a stacking state of the object based on a result of the comparing.

Abstract: A plurality of remote sensing images of a scene are received. A potential target object can be identified in one of the images, wherein the target object has a low signal-to-noise ratio (SNR). A candidate motion path of the target object can be generated based upon the images. A predicted position of the target object along the candidate motion path is determined for each of the remote sensing images. An image chip is extracted from each of the images, where each image chip is centered about the predicted position of the target object in its corresponding image. A sum image chip is generated based upon the image chips. An indication that the potential target object is an actual object in the images is output based upon a value of a center pixel of the sum image chip.

Abstract: Provided is an information processing apparatus including a determination unit that determines at least whether a photographed image is a non-skin region image obtained by photographing a non-skin region, and an output unit that performs, in the case where the photographed image is determined to be the non-skin region image, a predetermined first output.

Abstract: An attached object detection apparatus includes a setting part, a calculator, and a detector. A setting part sets a plurality of divided regions within a captured image captured by an image capturing apparatus. A calculator calculates, for each of the plurality of divided regions and based on luminance of pixels in the divided region, a representative luminance value and an amount of luminance dispersion. A detector detects, as an attached region that has an attached object, a divided region among the plurality of divided regions that satisfies the following conditions: i) a first difference is equal to or smaller than a first predetermined difference, ii) a second difference is equal to or smaller than a second predetermined difference, and iii) the representative luminance value of the current divided region is equal to or smaller than a first predetermined value.

Abstract: A method includes identifying one or more objects in one or more images of real-world scenes associated with a user, adding the identified one or more objects to a list of real-world objects associated with the user, assigning each object in the list of real-world objects to an object class based on object recognition, and providing a notification to the user that a content item has been associated with an object class assigned to one of the objects on the list of real-world objects associated with the user. A computer readable storage medium stores one or more computer programs, and an apparatus includes a processor-based device.

Abstract: Described herein are systems and methods that allow for dense depth map estimation given input images. In one or more embodiments, a neural network model was developed that significantly differs from prior approaches. Embodiments of the deep neural network model comprises more computationally efficient structures and fewer layers but still produces good quality results. Also, in one or more embodiments, the deep neural network model may be specially configured and trained to operate using a hardware accelerator component or components that can speed computation and produce good results, even if lower precision bit representations are used during computation at the hardware accelerator component.

Abstract: Methods for compressing shape data for a set of electronic designs include inputting a set of shape data, where the shape data represents a set of shapes for a device fabrication process. A convolutional autoencoder is used on the set of shape data, the convolutional autoencoder having a pre-determined set of convolution layers including a kernel size and filter size for each convolution layer. The set of shape data is encoded to compress the set of shape data, using the pre-determined set of convolution layers of the convolutional autoencoder, to create a set of encoded shape data. The set of shape data comprises an SEM image, and the encoded set of shape data identifies a mask defect.