Abstract: There is provided an object tracking apparatus that realizes robust object detection and tracking even for movement fluctuation and observation noise, an object tracking method and a computer program. An object cracking apparatus 1 is an apparatus tracking an object in video, the object tracking apparatus 1 including: a deep learning discriminator 2 which is a discriminator by deep learning; and a particle filter function unit 3 tracking an object by applying a multi-channel feature value of video including feature values by the deep learning discriminator 2 to likelihood evaluation by a particle filter, according to a distance between position information about the multi-channel feature value and position information about each particle.

Abstract: A deposit detection device according to an embodiment includes a calculation module, an extraction module, and a decision module. The calculation module calculates a brightness average for each of small regions into which a predetermined region of an image captured by an imaging device is divided. The extraction module extracts, as a high-brightness region, the small region in which the brightness average calculated by the calculation module is equal to or larger than a predetermined value. The decision module decides on a brightness threshold value for detecting a deposit region corresponding to a deposit adhering to the imaging device, based on the area of the high-brightness region extracted by the extraction module.

Abstract: In one embodiment, a computer-implemented method is for providing lymph node information. The method includes receiving medical imaging data; receiving atlas data spatially relating lymph node stations to at least one non-lymphatic anatomical structure; determining a lymph node position in the medical imaging data; generating the lymph node information, the lymph node information being indicative of a lymph node station, to which the lymph node position is anatomically allocated, by applying an algorithm onto the medical imaging data, the atlas data and the lymph node position; and providing the lymph node information.

Abstract: The present invention provides a method for estimating high-quality depth map based on depth prediction and enhancement sub-networks, belonging to the technical field of image processing and computer vision. This method constructs depth prediction subnetwork to predict depth information from color image and uses depth enhancement subnetwork to obtain high-quality depth map by recovering the low-resolution depth map. It is easy to construct the system, and can obtain the high-quality depth map from the corresponding color image directly by the well-trained end to end network. The algorithm is easy to be implemented. It uses high-frequency component of color image to help to recover the lost depth boundaries information caused by down-sampling operators in depth prediction sub-network, and finally obtains high-quality and high-resolution depth maps. It uses spatial pyramid pooling structure to increase the accuracy of depth map prediction for multi-scale objects in the scene.

Abstract: A physiological signal prediction method includes: collecting a video file, the video file containing long-term videos, and contents of the video file containing data for a face of a single person and true physiological signal data; segmenting a single long-term video into multiple short-term video clips; extracting, by using each frame of image in each of the short-term video clips, features of interested regions for identifying physiological signals so as to form features of interested regions of a single frame; splicing, for each of the short-term video clips, features of interested regions of all fixed frames corresponding to the short-term video clip into features of interested regions of a multi-frame video, and converting the features of the interested regions of the multi-frame video into a spatio-temporal graph; inputting the spatio-temporal graph into a deep learning model for training, and using the trained deep learning model to predict physiological signal parameters.

Abstract: Systems and methods for processing colon image data are provided. Image data related to a first ROI may be obtained, wherein the first ROI may include a soft tissue represented by a plurality of voxels, and each voxel may have a voxel value. A first virtual scene may be visualized based on the image data, wherein the first virtual scene may reveal at least one portion of the first ROI. A collision detection may be performed between at least one portion of the first ROI and a virtual object in the first virtual scene. A feedback force may be determined from at least one portion of the first ROI based on the collision detection. At least one of the plurality of voxels corresponding to a second ROI may be determined based on the feedback force, wherein the second ROI may relate to the soft tissue in the first ROI.

Abstract: A sequence of frames of a video can be received. For a given frame in the sequence of frames, a gradient-embedded frame is generated corresponding to the given frame. The gradient-embedded frame incorporates motion information. The motion information can be represented as disturbance in the gradient-embedded frame. A plurality of such gradient-embedded frames can be generated corresponding to a plurality of the sequence of frames. Based on the plurality of gradient-embedded frames, a neural network such as a generative adversarial network is trained to learn to suppress the disturbance in the gradient-embedded frame and to generate a substitute frame. In inference stage, anomaly in a target video frame can be detected by comparing it to a corresponding substitute frame generated by the neural network.

Abstract: Disclosed herein are systems, devices, and processes for gesture detection. A method includes capturing a series of images. The method includes generating motion isolation information based on the series of images. The method includes generating a composite image based on the motion isolation information. The method includes determining a gesture based on the composite image. The processes described herein may include the use of convolutional neural networks on a series of time-related images to perform gesture detection on embedded systems or devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a data capture application of a computing device that receives image data for an image of a document and uses the image data to capture content on the document while minimizing glare at the document. The data capture application receives user input for positioning an image token provided for display to a user of the data capture application. Positioning the image token causes adjustment of an attribute value of the image data. In response to receiving the user input the data capture application determines whether the attribute value of the image data satisfies a predefined attribute value. Based on the attribute value satisfying the predefined attribute value, the data capture application generates a composite image of the document using the image data received by the data capture application.

Abstract: State of the art image processing techniques such as background subtraction, and Convolutional Neural Network based approaches, when used for change detection, fail to support certain datasets. The disclosure herein generally relates to semantic change detection, and, more particularly, to a method and system for semantic change detection using a deep neural network feature correlation approach. An adaptive correlation layer is used by the system, which determines extent of computation required at pixel level, based on amount of information at pixels, and uses this information in further computation done for the semantic change detection. Information on the determined extent of computation required is then used to extract semantic features, which is then used to compute one or more correlation maps between the at least one feature map of a test image and corresponding reference image. Further the semantic changes are determined from the one or more correlation maps.

Abstract: An image processing method and a related apparatus are provided. The method is applied to an image processing device, and includes: obtaining an original image, the original image including a foreground object; extracting a foreground region from the original image through a deep neural network; identifying pixels of the foreground object from the foreground region; forming a mask according to the pixels of the foreground object, the mask including mask values corresponding to the pixels of the foreground object; and extracting the foreground object from the original image according to the mask.

Abstract: Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

Abstract: A system and method for identifying presence of digital ghosting artifacts in videos is disclosed. The method comprises estimating a blending parameter (?) for a current image using a previous image and a next image of a digital video stream. Successively, a blended image (B) is created by mixing contents of the previous image and the next image based on the estimated blending parameter (?). Thereafter, a first similarity is computed between the blended image (B) and a de-interlaced image (C), based on a Normalized Cross Correlation (NCC) between multiple blocks of the blended image (B) and the de-interlaced image (C). Successively, a second similarity is computed between the blended image (B) and the de-interlaced image (C), based on values of standard deviation of an absolute difference frame determined between the blended image (B) and the de-interlaced image (C).

Abstract: A technique relates to tracking a foodstuff. A device images human consumable code formed on the foodstuff, the human consumable code being part of the foodstuff, the foodstuff being unpackaged. A coding associated with the human consumable code is determined. Product information of the foodstuff is retrieved from a computer system by using the coding. The product information of the foodstuff is provided on the device.

Abstract: The present disclosure discloses a fingerprint recognition method and apparatus, and a mobile terminal, which are related to the field of information recognition technologies, and are used to reduce power consumption of the mobile terminal while implementing timely fingerprint collection. According to embodiments of the present disclosure, the mobile terminal determines a first fingerprint recognition area of a touchscreen according to a first user interface, and detects a touch operation of a user on the touchscreen; activates a fingerprint recognition function of the first fingerprint recognition area when a touch position corresponding to the touch operation is located in the first fingerprint recognition area, and obtains corresponding first fingerprint information according to the touch operation; and executes at least one function when the first fingerprint information matches preset fingerprint information.

Abstract: Edge-Loss-based image construction is enabled by a method including generating a reconstructed image from a first edge image with a generator, extracting a second edge image from the reconstructed image with an edge extractor, smoothing the first edge image and the second edge image, discriminating between the reconstructed image and an original image corresponding to the first edge image with a discriminator to obtain an adversarial loss, and training the generator by using an edge loss and the adversarial loss, the edge loss being calculated from the smoothed first edge image and the smoothed second edge image.

Abstract: Methods of determining whether an environment is suitable or acceptable for performing a three-dimensional (3D) scan are provided. The methods may include performing one or more checks on captured image data of the environment, wherein performing each of the one or more checks comprises determining whether the environment satisfies a respective criterion. The method may further include determining that the environment is suitable or unsuitable for performing the 3D scan based on a result of each performed check. Determining that the environment is suitable for performing the 3D scan may include determining that the environment satisfies each of the respective criteria of the performed one or more checks. Determining that the environment is unsuitable for performing the 3D scan may include determining that the environment does not satisfy at least one criterion of the performed one or more checks. Related devices and computer program products are also provided.

Abstract: A method and system for receiving a dental radiographic image that includes an oral structure, and in an image processor, selecting a segmenter and an object detector, predicting masks and points of the oral structure using the segmenter and the object detector to become part of image metadata. The dental radiographic image and image metadata are further provided to a measurement processor for selecting at least one measurement method of a set of measurement methods according to the dental radiographic image and the image metadata, calculating a sensor pixel to mm (millimeter) ratio using the measurement method, and calculating a calibrated measurement of the oral structure.

Abstract: An image processing apparatus comprises a detection circuit that, by referencing dictionary data acquired by machine learning corresponding to a target photographic subject to be detected in an obtained image, detects the target photographic subject; a selection unit that selects one of a plurality of dictionary data items corresponding to the target photographic subject; and a control circuit that, in a case where a detection evaluation value in a case where the photographic subject is detected by using the dictionary data selected by the selection unit is lower than a predetermined value, controls the detection circuit to detect the target photographic subject by using the selected dictionary data and dictionary data different to the selected dictionary data.

Abstract: Certain aspects relate to systems and techniques for navigation-assisted medical devices. Some aspects relate to correlating features of depth information generated based on captured images of an anatomical luminal network with virtual features of depth information generated based on virtual images of a virtual representation of the anatomical luminal network in order to automatically determine aspects of a roll of a medical device within the luminal network.