Abstract: In one embodiment, a method of signaling individual layers in a transport stream includes: determining a plurality of layers in a transport stream, wherein each layer includes a respective transport stream parameter setting; determining an additional layer for the plurality of layers in the transport stream, wherein the additional layer enhances one or more of the plurality of layers including a base layer and the respective layer parameter settings for the plurality of layers do not take into account the additional layer; and determining an additional transport stream parameter setting for the additional layer, the additional transport stream parameter setting specifying a relationship between the additional layer and at least a portion of the plurality of layers, wherein the additional transport stream parameter setting is used to decode the additional layer and the at least a portion of the plurality of layers.

Abstract: The present disclosure is directed to methods and systems for training a classifier for determining the category of a document. In an exemplary aspect, a method comprises obtaining one or more documents belonging to a first category as a training sample for a classifier, determining objects contained in each of the one or more documents, forming, by a hardware processor, a set of features consisting of the objects, constructing the classifier by selecting a classification model and training the classifier based on the set of features, obtaining additional documents belonging to the first category, calculating an error of classification of the additional documents using the classifier and when the error exceeds a given value, obtaining a second set of documents belonging to the first category or one or more new categories, otherwise, determining that the classifier is complete.

Abstract: A device for evaluating the condition of a wooden structure, including: a shaft; a distance sensor coupled to the shaft; and an image capture device coupled to the shaft, the distance sensor being configured to measure a location of the image capture device in the wooden structure.

Abstract: A training system comprises a training device, and a training data creation device. The training device trains a neural network. The training data creation device acquires any one of a positive evaluation indicating that content of the input data coincides with the label, a negative evaluation indicating that content of the input data does not coincide with the label, and an ignorable evaluation indicating exclusion from a training target label, for each label regarding the input data to create training data. In training the neural network for training, the training system adjusts the weight coefficient for the intermediate layer and makes the recognition score of the label with the ignorable evaluation not affect the adjustment of the weight coefficient for the intermediate layer.

Abstract: To create a classifier whose classification accuracy is maintained in consideration of temporal changes in a generation distribution of a sample and a new feature that has not appeared in learning data, a classifier is created in which a feature correlation learning unit learns a correlation between a feature of a sample of labeled learning data, and a feature appearing only in a sample of unlabeled learning data, and a classifier creating unit adds the feature appearing only in the sample of the unlabeled learning data to the feature of the sample of the labeled learning data by using the correlation, and outputs a label associated with an input sample by using the sample of the labeled learning data to which the feature appearing only in the sample of the unlabeled learning data is added.

Abstract: A method is provided for signaling individual layer parameters in a transport stream that includes: indicating, using a supplemental enhancement information (SEI) message in the video stream, operation point information; inserting the operation point information in the transport stream using an operation point descriptor; and providing the operation point descriptor in a Program Map Table (PMT).

Abstract: A method for comparing videos of a surgical procedure is disclosed. The method comprising selecting a plurality of videos from a surgical video database. Each of the plurality of videos including video data of a first surgical procedure comprising a plurality of surgical steps. The method further including identifying a first surgical step included in the plurality of surgical steps within a first video segment in each of the plurality of videos. The method also including warping the first video segment to standardize a dimension of the first video segment in each of the plurality of videos.

Abstract: A method is provided to determine buffer parameter settings for a plurality of layers in a transport stream. Each layer includes a respective transport stream buffer parameter setting. Then, the method provides respective transport stream buffer parameter settings to individual transport stream buffers for respective layers in the plurality of layers. Then, the method buffers the respective layers in the individual transport stream buffers according to the respective transport stream buffer parameter settings. After buffering, the method combines the respective layers to form a combined bit stream.

Abstract: Systems and methods provide for adaptive real-time streaming of Autonomous Vehicle (AV) data. In some embodiments, the AV can receive a request from the remote computing system for real-time streaming of a first type of AV data and adaptively streaming a second type of AV data when one or more streaming conditions are satisfied. The first type of AV data and the second type of AV data can be captured as raw data by sensors, actuators, transducers, and other components of the AV. The AV can stream the first type of AV data to the remote computing system in real-time for a first time period. When the AV determines the streaming conditions are satisfied, the AV can automatically determine the second type of AV data to stream to the remote computing system in real-time for a second time period.

Abstract: An electronic device is provided. The electronic device includes a first camera, a second camera having a different view angle from the first camera, and at least one processor configured to obtain a first image set for an external object using the first camera and a second image set for the external object using the second camera, identify motion corresponding to the first camera for a part of a time during which the first image set and the second image set are obtained, obtain a correction area using at least some images of the first image set based on at least the motion corresponding to the first camera, identify a compensation area in at least some images of the second image set based on at least the correction area or the motion corresponding to the first camera, and obtain a motion-corrected image for the external object using the correction area and the compensation area. Other various embodiments are possible as well.

Abstract: Systems and methods of the present disclosure provide processes for determining how much to adjust machine-learning parameter values in a direction of a gradient for gradient-descent steps in training processes for machine-learning models. Current parameter values of a machine-learning model are vector components that define an initial estimate for a local extremum of a cost function used to measure how well the machine-learning model performs. The initial estimate and the gradient of the cost function for the initial estimate are used to define an auxiliary function. A root estimate is determined for the auxiliary function of the gradient. The parameters are adjusted in the direction of the gradient by an amount specified by the root estimate.

Abstract: There is provided a distance detecting apparatus. An acquisition unit acquires a first image captured from a first point of view and a second image captured from a second point of view that is different from the first point of view A selection unit configured to select a representative pixel from the first image, based on a color of an object. A detection unit configured to detect a position in the second image corresponding to the representative pixel and thereby to detect a distance to the object corresponding to the position of the representative pixel.

Abstract: An imaging device includes a plurality of image sensors configured to capture a plurality of images, and processing circuitry. The processing circuitry is configured to determine whether a difference in brightness between the plurality of images exceeds a predetermined threshold. Based on a determination that the difference in brightness exceeds the predetermined threshold, the processing circuitry arranges the plurality of images side by side in one direction to be output as an output image.

Abstract: The disclosure relates to an apparatus for encoding a video signal, wherein the video signal is a two-dimensional projection of a panoramic video signal and comprises a plurality of successive frames, including a reference frame and a current frame, wherein each frame of the plurality of successive frames comprises a plurality of video coding blocks and wherein each video coding block comprises a plurality of pixels.

Abstract: A system and method for human motion detection and tracking (10) are disclosed. In one embodiment, an optical sensing instrument (16) monitors a stage (24). A memory (182) is accessible to a processor (180) and communicatively coupled to the optical sensing instrument (16). The system (10) captures a depth frame (150) from the optical sensing instrument (16). The depth frame (150) is converted into a designated depth frame format (152), which includes at each image element second coordinate values relative to the depth frame (150). Probability distribution models are applied to the designated depth frame format (152) to identify a respective plurality of body parts. The position of each of the respective plurality of body parts in the designated depth frame format (152) is calculated as is the position of each of the respective plurality of body parts in the depth frame (150).

Abstract: A computer-implemented method for determining an information on whether at least one hand of a vehicle driver cooperates with a manual steering element of a vehicle, wherein the method comprises: taking at least one image by means of at least one sensor mounted on the vehicle, wherein the at least one image captures at least a manual steering element of the vehicle; and determining, on the basis of the at least one image, an information on whether at least one hand of a vehicle driver cooperates with the manual steering element.

Abstract: One general aspect includes a system to modify an image feed from a second camera of a vehicle, the system includes a memory configured to include one or more executable instructions and a processor configured to execute the executable instructions, where the executable instructions enable the processor to receive a first image feed from a first camera located on the vehicle; monitor one or more image characteristics of the first image feed; receive the second image feed from the second camera located on the vehicle; and based on the monitored one or more image characteristics of the first image feed, modify the second image feed such that one or more image characteristics of the second image feed are substantially similar to the monitored one or more image characteristics of the first image feed.

Abstract: An image processing device includes a hardware processor configured to: acquire items of image information; determine lateral image information as a particular state of luminance when a first region of interest exhibits luminance of a first given value or more and a difference in luminance between the first region of interest and a second region of interest is a second given value or more, the first region of interest and the second region of interest being included in a vehicular front region and a vehicular rear region of the lateral image information, respectively; set, in the particular state of luminance, a first correction value in accordance with luminance of the vehicular front region and set a second correction value in accordance with luminance of rear image information; and set, according to the first second correction values, an individual correction value for correcting luminance of a region between the first and second regions of interest.

Abstract: Video coding according to the disclosure of the present application includes generating a predictive signal of a target object either by means of intra-prediction or inter-prediction. The generated predictive signal of the target object then undergoes filtering to smooth out a transition of pixel signals from a neighboring block to the target block. In the disclosure of the present application, the filtering is performed only when the filtering is necessary. A parameter indicating whether to execute or not to execute the filtering is sent from the encoder to the decoder. The present application also discloses provision of multiple types of transformation processes. A selection signal is used to select one type of transformation process from the multiple types of transformation processes. Alternatively, one type of transformation process is selected according to whether to execute or not to execute the filtering.

Abstract: A hand-held digital camera has a touch-sensitive display screen (“touch screen”) for image preview and user control of the camera, and a user-selectable panorama mode. Upon entering panorama mode the camera superimposes upon the touch screen a horizontal rectangular bar whose width and/or height are user-adjustable by interaction with the touch screen to select a desired horizontal sweep angle. After the sweep angle is set the camera automatically captures successive horizontally overlapping images during a sweep of the device through the selected sweep angle. Subsequently the camera synthesises a panoramic image from the successively captured images, the panoramic image having a width corresponding to the selected sweep angle.