Abstract: Methods and systems are provided to detect an instance of a line in a two-dimensional image captured by a vehicle and to determine whether the instance of the line is a lane boundary for a lane that will be used by the vehicle to traverse a route. An instance of a line in a two-dimensional image captured by a vehicle is detected using processing circuitry. The processing circuitry is used to determine that the instance of the line is a lane boundary for a lane associated with the vehicle. A curve fit for the lane boundary based on the instance of the line is determined using the processing circuitry. The processing circuitry is also used to determine a sinuosity of the lane based on the curve fit. Execution of a vehicle action is facilitated using the processing circuitry based on the determined sinuosity.

Abstract: A method for controlling passive infrared sensors includes obtaining a three-dimensional image of a space to be laid out; arranging a plurality of PIR sensors and a plurality of sensor lamps on the three-dimensional image, a distance L between each adjacent two PIR sensors is equal to or less than a sensing radius of the PIR sensor; connecting each PIR sensor to a wireless network including a plurality of wireless sub-networks, each wireless sub-network includes four PIR sensors and at least one sensor lamp; controlling the four PIR sensors to sense living bodies in pairs every detection period, and when sensing data of living body is fed back, determining that there is at least one living body in the wireless sub-network; and determining a working state of the sensor lamp according to whether there is at least one living body in the wireless sub-network.

Abstract: A computer-implemented method for detecting lung abnormalities is provided. The method includes the steps of: acquiring a chest image of a subject; labeling one or more regions of interest (ROIs) in the chest image; segmenting a fine-grained boundary of each of the labeled ROIs; generating a plurality of output matrixes for each of the segmented ROIs; sorting a plurality of prediction scores obtained in the output matrixes, and generating a plurality of recommendations of potential abnormalities for each of the ROIs; and outputting the recommendations, A smart imagery framing and truthing (SIFT) system for implementing the method is also provided.

Abstract: Embodiments are disclosed for generating a gesture reenactment video sequence corresponding to a target audio sequence using a trained network based on a video motion graph generated from a reference speech video. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a first input including a reference speech video and generating a video motion graph representing the reference speech video, where each node is associated with a frame of the reference video sequence and reference audio features of the reference audio sequence. The disclosed systems and methods further comprise receiving a second input including a target audio sequence, generating target audio features, identifying a node path through the video motion graph based on the target audio features and the reference audio features, and generating an output media sequence based on the identified node path through the video motion graph paired with the target audio sequence.

Abstract: A system including one or more processors and one or more non-transitory computer-readable storage media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform: training a neural network detection model with a training dataset comprising synthetic training images by: using a transformation algorithm to create the synthetic training images by appending edge case training images to one or more compliant images; receiving, at the neural network detection model, as trained, at least one image; and determining, using the neural network detection model, as trained, whether the at least one image comprises non-compliant content. Other embodiments are disclosed herein.

Abstract: A photoelectric conversion device including pixels arranged to form rows, a scanning circuit that performs scanning for sequentially outputting a signal from the pixel on a row basis, and a processing circuit that processes a signal output from the pixel. The processing circuit corrects, based on a first reset signal and a second reset signal based on a reset state of the pixel, an optical signal based on incident light. The scanning circuit performs scanning for outputting the optical signal and the first reset signal from the pixel by scans performed in different periods. The scanning circuit performs scanning for outputting the optical signal and the second reset signal from the pixel by a scan. The first reset signal, the second reset signal, and the optical signal are output from the pixel in a frame period in which signals to be used for generating a frame is output.

Abstract: A method includes: performing a plurality of times of first clustering processing on a plurality of training images based on a plurality of target features to obtain a plurality of first clustering results, where each of the plurality of first clustering results corresponds to one silhouette coefficient, and the silhouette coefficient indicates cluster quality; determining a first target clustering result based on the silhouette coefficients, where the first target clustering result includes M clustering categories; and performing second clustering processing on the plurality of training images based on the plurality of target features to obtain a second clustering result, where a quantity of clustering categories included in the second clustering result is M.

Abstract: Methods and systems are disclosed for analyzing one or more images of a textile to determine a presence or absence of defects. In one example, an image of at least a portion of a textile may be obtained and compared to a reference image of a reference textile. Based on the comparison, one or more areas indicative of a height variation between the textile and the reference textile may be determined. An action may be performed based on the one or more areas indicative of the height variation.

Abstract: A prediction device 100 of the present invention includes a detection means 121 for, on the basis of a river image that is an image obtained by capturing a river and associated with capturing position information representing a position where the river is captured, detecting river condition information representing a condition of the river at the position where the river image is captured; and a prediction means 122 for, on the basis of the capturing position information, the river condition information, and topography information representing the topography of the river, predicting a river condition representing a condition of the river at a given point of the river. The given point is different from the position represented by the capturing position information.

Abstract: Systems and methods for improved visual prosthetic and orthodontic treatment planning are provided herein. In some aspects, a method for preparing a tooth of a patient is disclosed. The method may comprise building a model of a dentition of the patient including a model of the initial shape of tooth. The method may also include determining a final prepared shape of the tooth. In some aspects, the method may also include generating a treatment plan comprising a plurality of steps to modify the initial shape of the tooth to the final prepared shape of the tooth. The method may also include rendering visualizations for the plurality of steps of the treatment plan. The visualizations may depict the removal of tooth material to modify the initial shape of the tooth to the final prepared shape of the tooth.

Abstract: A migration system of a learning model for cell image analysis is a system that migrates a learning model from a first learning device to a second learning device, in which the second learning device includes an algorithm consistency determination unit that determines, based on second algorithm specification information and first algorithm specification information, whether or not consistency is established between a first algorithm and a second algorithm, and a learning model parameter setting unit that sets a first parameter to be used together with the second algorithm.

Abstract: Watermarking is used to track and identify digital images. One claim includes acts of: processing obtained imagery to yield local image information, the local image information being inadequate to reveal a subject depicted in said obtained imagery, using the local image information, resolving geometric distortion of the imagery, the geometric distortion comprising scale and rotation, said resolving yielding geometrically resolved imagery, and detecting the encoded signal from the geometrically resolved imagery using secret detecting information. A great variety of other features and arrangements are also detailed.

Abstract: A high-speed optical tracking with compression and CMOS windowing for tracking applications that require high-speed and/or low latency when delivering pose (orientation and position) data. The high-speed optical tracking with compression and CMOS windowing generally includes an optical tracking system (10) that sense fiducial (22) and by extension markers (20). The markers can either be integrated on tools (20) handled by an operator (e.g. surgeon) (50) or fixed on the subject to track (e.g. patient) (40). The low-level processing (101, 107, 140) is realized within the tracking system to reduce the overall data to be transferred and considerably reduce the processing efforts. Pose data (127) are finally computed and transferred to a PC/monitor (30,31) or to tablet (60) to be used by an end-user application (130).

Abstract: Systems, apparatus, and methods for piggyback camera calibration. Existing piggybacked capture techniques use a “beauty camera” and an “action camera” to capture raw footage. The user directly applies the EIS stabilization track of a piggybacked action camera to the cinematic footage to create desired stable footage. Unfortunately, since the action camera may have been slightly offset from the cinematic video camera, the EIS stabilization data will only roughly approximate the necessary corrections. In other words, the user must manually fine tune the corrections. The disclosed embodiments use a calibration sequence to estimate a physical offset between the beauty camera and the action camera. Then, the estimated physical offset can be used to calculate an offset camera orientation for stabilizing the beauty camera. The foregoing process can be performed in-the-field before actual capture. This allows the user to check their set-up and fix any issues before capturing the desired footage.

Abstract: Systems and methods may be used for estimating instantaneous patient motion (a patient state). The patient state may be estimated based on a 3D reference volume and a stream of images, for example from an image acquisition device. The stream of images may be received in real-time, for example during a radiation therapy treatment. An example method may include encoding the 3D reference volume using a 3D encoder branch of a patient state generator network, encoding the stream of images using a 2D encoder branch of the patient state generator network, and combining the encoded 3D reference volume and the encoded real-time stream of images. The method may include estimating a 3D spatial transform that maps the 3D reference volume to a current patient state by decoding the combined encoding using a 3D decoder branch of the patient state generator network.

Abstract: Described herein is an information processing apparatus, including: a graph image acquisition unit configured to acquire a graph image; a graph classification unit configured to classify the graph image acquired by the graph image acquisition unit by graph type; a probability map generation unit configured to generate, from the graph image, a probability map that is of a different type by the graph type using a single neural network; a component extraction unit configured to extract a component in the graph image based on the probability map generated by the probability map generation unit; a value extraction unit configured to extract a value of the component of the graph image extracted by the component extraction unit; and an output unit configured to output the value of the component extracted by the value extraction unit.

Abstract: A system (100) comprising one or more processors (110) and one or more storage devices (120) is configured to obtain biology-related image-based input data (107) and generate a high-dimensional representation of the biology-related image-based input data (107) by a trained visual recognition machine-learning algorithm executed by the one or more processors (110). The high-dimensional representation comprises at least 3 entries each having a different value. Further, the system is configured to at least one of store the high-dimensional representation of the biology-related image-based input data (107) together with the biology-related image-based input data (107) by the one or more storage devices (120) or output biology-related language-based output data (109) corresponding to the high-dimensional representation.

Abstract: A method and device for digital signal processing are provided, particularly relating to video image processing. The device obtains image data comprising a plurality of pixels. The image data comprises a plurality of sequentially captured images. The device estimates, for a target image, a set of backward motion vector fields (backward MVFs) based on the target image, and a first set of images captured before the target image. The device further estimates a set of forward MVFs based on the target image and a second set of images captured after the target image. Depending on the estimating for the target image, the device generates an output image based on a merging procedure of the target image and the first set of images and the set of backward MVFs, and/or the second set of images and the set of forward MVFs.

Abstract: Embodiments of this application disclose a method and apparatus for training an image region segmentation model, and an image region segmentation method and apparatus. The method includes acquiring a sample image set, and each image of the sample image set having first annotation information; generating graph structure data corresponding to a sample image in the sample image set, the graph structure data comprising multiple nodes, and each node comprising at least one pixel in the sample image; determining second annotation information of each node according to the graph structure data and the first annotation information corresponding to the sample image by using a graph convolutional network model, a granularity of the second annotation information being smaller than a granularity of the first annotation information, the graph convolutional network model being a part of an image segmentation model; and training the image segmentation model according to the second annotation information.

Abstract: The present invention generally relates to the field of automated and flexible information extraction and protection for graphical data. In particular, the invention provides a unique platform for analyzing, classifying, extracting, and processing information from images using deep learning image detection models. Embodiments of the inventions are configured to provide an end to end automated solution for intelligently hiding or obscuring private data from graphical displays via the use of embedded steganographic image data techniques.