Abstract: Provided is a monitoring device including: a captured image acquiring unit configured to acquire an image captured by a monitoring camera; a monitoring logic execution unit configured to generate a monitoring result corresponding to the image captured by the monitoring camera, by using a trained monitoring logic; an image transmitting unit configured to decimate the image captured by the monitoring camera and transmit a result to a learning apparatus performing training processing on another monitoring logic of a same type as the monitoring logic; a monitoring logic receiving unit configured to receive, from the learning apparatus, the other monitoring logic additionally trained by the learning apparatus by using the image from the image transmitting unit; and an updating unit configured to update the monitoring logic executed by the monitoring logic execution unit to the other monitoring logic received by the monitoring logic receiving unit.

Abstract: According to an example embodiment, an object feature extraction device includes a video acquisition means for acquiring a video and generating the acquired video as an image sequence, an object detection means for detecting an object from the generated image and generating a detection result, an object tracking means for tracking the object based on the generated image and the detection result and generating a tracking result, an image storage means for storing the image, a detection result storage means for storing the detection result, a tracking result storage means for storing the tracking result, an object selection means for calculating, based on the detection result and the tracking result, a quality index for predicting the quality of a feature of the object detected at an extraction time, selecting the object to be subjected to feature extraction, and generating object selection information.

Abstract: An information processing apparatus includes a specification unit, a determination unit, and a generation unit. The specification unit specifies a relationship between a plurality of objects detected in a video. The determination unit determines arrangement of motion trajectories of the plurality of objects, the relationship between which has been specified by the specification unit, while maintaining a relative appearance order in the video and avoiding an overlap of the motion trajectories in a temporal direction. The generation unit generates a summary video of the video based on the arrangement determined by the determination unit.

Abstract: According to one embodiment, an information processing apparatus includes processing circuitry. The processing circuitry acquires image data on a predetermined photographed area, generates part movement information on a plurality of parts of an object included in the image data, based on the image data, acquires sensor data from the object, generates sensor operation information on an operation of a sensor, based on the sensor data, and specifies a relationship between the object included in the image data and the sensor, based on the part movement information and the sensor operation information.

Abstract: Aspects of the subject disclosure may include, for example, a method comprising obtaining, by a processing system including a processor, first and second models for a structure of an object, based respectively on ground-level and aerial observations of the object. Model parameters are determined for a three-dimensional (3D) third model of the object based on the first and second models; the determining comprises a transfer learning procedure. Data representing observations of the object is captured at an airborne unmanned aircraft system (UAS) operating at an altitude between that of the ground-level observations and the aerial observations. The method also comprises dynamically adjusting the third model in accordance with the operating altitude of the UAS; updating the adjusted third model in accordance with the data; and determining a 3D representation of the structure of the object, based on the updated adjusted third model. Other embodiments are disclosed.

Abstract: Various embodiments provide systems, methods, devices, and instructions for performing simultaneous localization and mapping (SLAM) that involve initializing a SLAM process using images from as few as two different poses of a camera within a physical environment. Some embodiments may achieve this by disregarding errors in matching corresponding features depicted in image frames captured by an image sensor of a mobile computing device, and by updating the SLAM process in a way that causes the minimization process to converge to global minima rather than fall into a local minimum.

Abstract: Embodiments are directed to a smart camera device that analyzes independent video streams.

Abstract: A biological information measuring apparatus includes a cover member and a hardware processor. The cover member is provided with sensors for detecting biological signals to cover a position of a biological part of a subject. The hardware processor is configured to estimate a positional relation of the position of the biological part of the subject with respect to the cover member at a first time point. The hardware processor superimposes first point cloud and second point cloud. The first point cloud is acquired by a non-contact mechanism front the subject at the first time point and represents a surface of the biological part of the subject in a coordinate system of the sensors. The second point cloud is created based on a morphological image of the subject captured by a biological structure acquiring apparatus and represents the surface of the biological part of the subject.

Abstract: There is provided a moving robot including a light projector, an image sensor and a processing unit. The light projector projects a vertical light segment and a horizontal light segment toward a moving direction. The image sensor captures, toward the moving direction, an image frame containing a first light segment image associated with the vertical light segment and a second light segment image associated with the horizontal light segment. The processing unit recognizes a plush carpet in the moving direction when a vibration intensity of the second light segment image is higher than a predetermined threshold, and an obstacle height calculated according to the first light segment image is larger than a height threshold.

Abstract: There is provided a moving robot including a light projector, an image sensor and a processing unit. The light projector projects a vertical light segment toward a moving direction. The image sensor captures, toward the moving direction, an image frame containing a light segment image associated with the vertical light segment. The processing unit calculates a step distance and a segment feature according to the image frame, outputs a flag signal according to the segment feature to indicate whether the calculated step distance is confident or not, and perform a pixel interpolation in calculating the step distance to improve the identification accuracy.

Abstract: A method and a system for detecting rough handling. The system has a camera and a computing device. The computing device is configured to: receive a video stream captured by the camera; detect persons and packages from video frames of the video stream; construct person and package trajectories based on the detected persons and packages; recognize an action between one person trajectory and one package trajectory, where the action includes the one person picks up, holds, and drops off the one package; and determine existence of a rough handling when, within a predetermined frames after drop-off of the one package, a motion distance of the one package is greater than a threshold distance, and a motion speed of the one package is greater than a threshold speed.

Abstract: Embodiments of the present disclosure provide a method and apparatus for detecting a target object, an electronic device, and a computer readable storage medium. The method may include: acquiring a to-be-detected image; processing the to-be-detected image using an object detection model including a deformable convolutional layer to obtain an offset prediction result of the deformable convolutional layer; and adjusting a size of an anchor point using the offset prediction result, and determining position information of the target object in the to-be-detected image using the anchor point of the adjusted size.

Abstract: A tracking device includes a processor including hardware. The processor is configured to: set a start frame and an end frame in a video including multiple frames; perform forward tracking in frames subsequent to the start frame based on a region of a tracking target in the start frame; perform backward tracking in frames previous to the end frame based on a region of the tracking target in the end frame; and generate a combined mask image by combining a forward mask image based on the forward tracking with a backward mask image based on the backward tracking.

Abstract: A method includes receiving video data that includes a series of frames of image data. Here, the video data is representative of an actor performing an activity. The method also includes processing the video data to generate a spatial input stream including a series of spatial images representative of spatial features of the actor performing the activity, a temporal input stream representative of motion of the actor performing the activity, and a pose input stream including a series of images representative of a pose of the actor performing the activity. Using at least one neural network, the method also includes processing the temporal input stream, the spatial input stream, and the pose input stream. The method also includes classifying, by the at least one neural network, the activity based on the temporal input stream, the spatial input stream, and the pose input stream.

Abstract: An information processing apparatus (10) includes an event detection unit (110), an input reception unit (120), and a processing execution unit (130). The event detection unit (110) detects a specific event from video data. The input reception unit (120) receives, from a user, input for specifying processing to be executed. The processing execution unit (103) executes first processing specified by input received by the input reception unit (120), and executes second processing of generating learning data used for machine learning and storing the generated learning data in a learning data storage unit (40).

Abstract: Described herein are various technologies pertaining to text extraction from a document. A computing device receives the document. The document comprises computer-readable text and a layout, wherein the layout defines positions of the computer-readable text within a two-dimensional area represented by the document. Responsive to receiving the document, the computing device identifies at least one textual element in the computer-readable text based upon spatial factors between portions of the computer-readable text and contextual relationships between the portions of the computer-readable text. The computing device then outputs the at least one textual element.

Abstract: A video query method includes obtaining a media feature of a query media and a static image feature corresponding to a candidate video. The query media includes the target object, and the candidate video includes the moving object. A video feature of the candidate video is determined according to the static image feature and motion time sequence information of the moving object in the candidate video. Whether the moving object in the candidate video is related to the target object in the query media can be determined according to the media feature and the video feature.

Abstract: A system is provided for identifying damages of a vehicle. During operation, the system can obtain a set of digital images associated with a set of tagged digital images as training data. Each tagged digital image in the set of tagged digital images may include at least one damage object. Based on the training data, the system can train a damage identification model by reducing noise associated with the damage object; generating a set of feature vectors for the training data; and using the set of feature vectors to optimize a set of parameters associated with the damage identification model to obtain a trained damage identification model. The system can then apply the trained damage identification model to obtain a damage category prediction result and determine a repair solution based on the damage category prediction result.

Abstract: A method for using a multi-hop reasoning framework to perform multi-step compositional long-term reasoning is presented. The method includes extracting feature maps and frame-level representations from a video stream by using a convolutional neural network (CNN), performing object representation learning and detection, linking objects through time via tracking to generate object tracks and image feature tracks, feeding the object tracks and the image feature tracks to a multi-hop transformer that hops over frames in the video stream while concurrently attending to one or more of the objects in the video stream until the multi-hop transformer arrives at a correct answer, and employing video representation learning and recognition from the objects and image context to locate a target object within the video stream.

Abstract: A video processing apparatus includes a video analyzer that analyzes video data captured by a surveillance camera, detects an event belonging to a specific category, and outputs a detection result, a display controller that displays, together with a video of the video data, a category setting screen for setting a category of an event included in the video, and a learning data accumulator that accumulates, as learning data together with the video data, category information set in accordance with an operation by an operator to the category setting screen. The video analyzer performs learning processing by using the learning data accumulated in the learning data accumulator.