Abstract: A communication device is provided for a motor vehicle that works with traffic-relevant information provided through light signals. The communication device comprises a primary imaging optical system to create the input image from the received scenic image, which may comprise a light car2car signal and/or a light car2X signal including traffic-relevant information. It further comprises a DMD array of mirrors for receiving the input image and transmitting it to a primary optical sensor adapted to convert the input optical image to an electric signal for processing, to thereby find out whether and what places of the input image sources of the signals are found in.

Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating a modified digital image by identifying patch matches within a digital image utilizing a Gaussian mixture model. For example, the systems described herein can identify sample patches and corresponding matching portions within a digital image. The systems can also identify transformations between the sample patches and the corresponding matching portions. Based on the transformations, the systems can generate a Gaussian mixture model, and the systems can modify a digital image by replacing a target region with target matching portions identified in accordance with the Gaussian mixture model.

Abstract: The invention provides the techniques and systems that allow for the identification and classification of objects (i.e., humans) in images using a predictive segmentation model. More specifically, human forms are identified within an image by generating pixel-level bounding boxes for each possible object and using offsets and segmentation masking. In some instances, embodiments of the invention use an identified floor plane that intersects with a bounding box to identify a three-dimensional position for the intersection point, which can then be assigned to the human form and represent its depth within the image.

Abstract: Described is a system for classifying objects and scenes in images. The system identifies salient regions of an image based on activation patterns of a convolutional neural network (CNN). Multi-scale features for the salient regions are generated by probing the activation patterns of the CNN at different layers. Using an unsupervised clustering technique, the multi-scale features are clustered to identify key attributes captured by the CNN. The system maps from a histogram of the key attributes onto probabilities for a set of object categories. Using the probabilities, an object or scene in the image is classified as belonging to an object category, and a vehicle component is controlled based on the object category causing the vehicle component to perform an automated action.

Abstract: Examples of techniques for interactive generation of labeled data and training instances are provided. According to one or more embodiments of the present invention, a computer-implemented method for interactive generation of labeled data and training instances includes presenting, by the processing device, control labeling options to a user. The method further includes selecting, by a user, one or more of the presented control labeling options. The method further includes selecting, by a processing device, a representative set of unlabeled data samples based at least in part on the control labeling options selected by the user. The method further includes generating, by a processing device, a set of suggested labels for each of the unlabeled data samples.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automated analysis of petrographic thin section images. In one aspect, a method includes determining a first image of a petrographic thin section of a rock sample, and determining a feature vector for each pixel of the first image. Multiple different regions of the petrographic thin section are determined by clustering the pixels of the first image based on the feature vectors, wherein one of the regions corresponds to grains in the petrographic thin section. The method further includes determining a second image of the petrographic thin section, including combining images of the petrographic thin section acquired with plane-polarized light and cross-polarized light. Multiple grains are segmented from the second image of the petrographic thin section based on the multiple different regions from the first image, and characteristics of the segmented grains are determined.

Abstract: Embodiments relate to tracking and determining a location of an object in an environment surrounding a user. A system includes one or more imaging devices and an object tracking unit. The system identifies an object in a search region, determines a tracking region that is smaller than the search region corresponding to the object, and scans the tracking region to determine a location associated with the object. The system may generate a ranking of objects, determine locations associated with the objects, and generate a model of the search region based on the locations associated with the objects.

Abstract: In one embodiment, a method includes receiving autonomous-vehicle sensor data from a sensor array of an autonomous vehicle. The autonomous-vehicle sensor data indicates an object in an external environment of the autonomous vehicle. The method further includes determining a confidence score for a classification of the object. The method further includes determining an object graphic with a level of detail to visually represent the object. The level of detail of the object graphic is based on the confidence score. The method further includes providing for display a visual representation the object graphic.

Abstract: A ledger document processing device including a display section which displays a live view image captured by an imaging section while waiting for a ledger document to be captured, and a processor which actualizes functions including judging whether a pixel-count size of an area corresponding to the ledger document in an image to be captured and stored in response to an imaging instruction is equal to or larger than a reference pixel-count size while waiting for the ledger document to be captured, notifying a user of a judgment result, and storing in a storage section the image captured by the imaging section in response to the imaging instruction.

Abstract: A device for obtaining an image includes a projector configured to project light having a preset pattern to an object, a first camera configured to sense light reflected and fed back by the object to obtain a depth image, a second camera configured to obtain a color image of the object, a motion sensor configured to sense a motion of the device. The device also includes and a processor configured to obtain a color image and a plurality of depth images of the object, by changing a parameter about the projected light and the light sensed by the first camera. When the motion of the device is less than a threshold, the processor is configured to merge pieces of depth information respectively obtained from the plurality of depth images with each other, and obtain a 3D image of the object, based on the merged depth information and the color image.

Abstract: An image processing apparatus is configured to extract an object region from an image. The image processing apparatus includes: a setting unit configured to set a plurality of reference points in the image; an obtaining unit configured to obtain a contour of the object region corresponding to each of the plurality of reference points as an initial extraction result based on a characteristic of the object region; and an extraction unit configured to extract the object region from the image based on an integration result obtained by integrating values of pixels in a plurality of initial extraction results.

Abstract: An improved machine learning system is provided. For example, a content management server may provide real-time analysis of a user's handwriting to assess the user's knowledge of a language, including using a convolution neural network method. The convolution neural network method may be executed to normalize at least some identified strokes in the user's handwritten user input. Normalization may be performed by translating a window comprising a subset of pixels in a digital representation of the handwritten user input amongst a plurality of pixels in the digital representation.

Abstract: A system for providing location information and an electronic device supporting the same are provided. The system includes a network interface, at least one processor, and at least one storage device. The storage device may store instructions of enabling the processor to, at its execution, execute receiving, through the network interface, a plurality of photographs including one or more objects, together with position information associated with the photographs, identifying the one or more objects from the plurality of photographs, and transmitting information on the identified one or more objects to an external device, in relation with the position information.

Abstract: A method for fill level determination, which can include receiving a set training set, training a neural network, selecting reference images, and/or determining a container fill level. A system for fill level determination, which can include a computing system, one or more containers, and/or one or more content sensors.

Abstract: An interactive seating system includes first seats in a first section, a first sensor device, second seats in a second section, a second sensor device, a first processing unit, a second processing unit, and an output device. The first sensor device and the second sensor device observe the first seats and the second seats, respectively. The first processing unit receives data from the first sensor device and the second sensor device and interprets an emotional state of occupants in the first and second seats based on the received data from the first and second sensor device, respectively. The second processing unit receives the interpreted emotional states, and compares the interpreted emotional states between the first and second sections. The output device automatically produces an output, that is observable by the occupants, based on the comparison.

Abstract: Applying an image effect within an image processing application. An image processing application receives a selection of an image effect to be applied to an image. The image includes image layers, each of which has a layer property and is created based on an application of a first effect. The application selects a template from a set of predefined templates. The selection is based on the image effect and the template. The template includes template layers. The application matches each of the image layers to a corresponding template layer having a template property corresponding to the layer property. The application determines from the matching that no conflicts exist between the image layers and the template. The application merges the image layers with the template layers and applies the image effect.

Abstract: An inspection apparatus configured to inspect a target for defects, including: an image capturing unit capable of capturing an image of the target as image information having color information including RGB values; and a determination unit configured to determine presence or absence of defects in the target based on the color information of the image information of the image captured by the image capturing unit, wherein the determination unit is configured to define, for each pixel, criteria for determining presence or absence of defects in each pixel of the image information, based on the color information in a defect-free region of the target captured by the image capturing unit, and to filter all pixels in the image information of the image captured by the image capturing unit so as to determine presence or absence of defects in each pixel, based on the defined criteria.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for displaying a video. A video stream including a plurality of image frames, wherein at least some image frames include an overlay, is received by a video management system. The video management system determines a position of the overlay within an image frame. The video management system applies an image adjustment function to the image frame to create an adjusted image frame. The image adjustment function uses the determined position of the overlay to adjust the image while keeping the appearance of the overlay essentially unchanged, and the video stream including the adjusted image frame is displayed.

Abstract: The present invention relates to an image processing method for orthodontic planning, a device and a recording medium therefor. The image processing method according to the present invention corrects the patient image to be horizontal and provides grids for analyzing the facial symmetry of the patient. According to the method, it decreases time for processing the patient image and inconvenience of the user and it helps to make the orthodontic plan considering the symmetry.

Abstract: An imaging apparatus includes a clamp level is multiplied by a first feedback gain, and correct a signal of a part of photoelectric conversion portions of a unit pixel in an opening region based on a result of multiplication in which an error amount between a signal of a part of a photoelectric conversion portions of the unit pixel in a light-shielded region and a clamp level is multiplied by a second feedback gain, and thus the signal of the unit pixel can be corrected precisely.