Abstract: A method for training a generator network that is configured to generate images with multiple objects. The method includes providing a set of training images, a generator network, and a discriminator network; drawing noise samples and target counts of objects; mapping, by the generator network, the noise samples and target counts of objects to generated images; randomly drawing images from a pool comprising generated images and training images; supplying the randomly drawn images to the discriminator network, thereby mapping them to a combination of: a decision whether the respective image is a training image or a generated image; optimizing discriminator parameters, optimizing generator parameters, and optimizing both the generator parameters and the discriminator parameters with the goal of improving the match between the predicted count of objects on the one hand, and the actual or target count of objects on the other hand.

Abstract: An image processing system (IPS), comprising an input interface (IN) for receiving a projection image from a plurality of projection images of a movable object (PAT) acquired along different directions by an imaging apparatus (XA), the projection images defined in a projection domain spanned by a radiation sensitive surface of the detector (D). The system includes a motion checker (MC) configured to operate in the projection domain to decide whether the projection image is corrupted by motion of the object during acquisition.

Abstract: This application provides an image recognition method and apparatus, an electronic device, and a computer-readable storage medium, and relates to the field of artificial intelligence technologies. The method includes obtaining feature information corresponding to a target object in an image to be recognized, the feature information comprising blur degree information, local feature information, and global feature information; determining a category of the target object based on the feature information, and determining a confidence level corresponding to the target object; and obtaining target information corresponding to the image to be recognized according to the category of the target object and the confidence level.

Abstract: Hybrid deep learning systems and methods allow for detecting anomalies in objects, such as electrical printed circuit board (PCB) components, based on image data. In one or more embodiments, a hybrid deep learning model comprises a Graph Attention Network (GAT) that uses spatial properties of the PCB components to extract latent semantic information and generate an output set of hidden representations. The GAT treats each of the electrical components as a node and each connection between them as edges in a graph. The hybrid system further comprises a Convolutional Neural Network (CNN) that uses pixel data to obtain its own output set of hidden representations. The hybrid deep learning model concatenates both sets to detect anomalies that may be present on the PCB.

Abstract: A system accesses content structure that includes a first attribute table including a first list of attributes of a first object, and a first mapping including first attribute values. The first list of attributes of the first object also includes a quality attribute indicating a first quality. After a request to modify quality is received, the system searches a plurality of content structures for a suitable second content structure that comprises a second attribute table including a second list of attributes of a second object. The suitable content structure has another attribute that matches a corresponding attribute of the first list of attributes of the first object and a quality attribute indicating a second quality. The system modifies the first attribute table to include the second list of attributes of the second object. In this way content is generated that is of higher or lower quality than the original content.

Abstract: An image processing method, where a target area and a background area are determined in an image by performing mask segmentation on the image. Different color processing modes are applied to the target area and the background area, such that luminance of the target area is greater than luminance of the background area, or chrominance of the target area is greater than chrominance of the background area, and a main object corresponding to the target area is more prominently highlighted. This enables a terminal user to have a movie special effect during photographing or video photographing, and improves photographing experience of the user. In addition, the present disclosure further provides a flicker elimination method, such that a color change of video content is smoother and more natural.

Abstract: The present disclosure provides a transformer-based driver distraction detection method and apparatus, belonging to the field of driving behavior analysis. The method includes: acquiring districted driving image data; building a driver distraction detection model FPT; inputting the acquired distracted driving image data into the driver distraction detection model FPT, analyzing the distracted driving image data by using the driver distraction detection model FPT, and determining a driver distraction state according to an analysis result. The present disclosure proposes a new network model, i.e., a driver distraction detection model FPT, based on Swin, Twins, and other models. Compared with a deep learning model, the FPT model compensates for the drawback that the deep learning model can only extract local features; the FPT model improves the classification accuracy and reduces the parameter quantity and calculation amount compared with the transformer model.

Abstract: Systems and methods for object detection. The methods include, by a computing device: obtaining a plurality of intensity values denoting at least a difference in a first location of at least one object in a first image and a second location of the at least one object in a second image; converting the intensity values to 3D position values; inputting the 3D position values into a classifier algorithm to obtain classifications for data points of a 3D point cloud (each of the classifications comprising a foreground classification or a background classification); and using the classifications to detect at least one object which is located in a foreground or a background.

Abstract: Aspects of the present disclosure describe DFOS systems, methods, and structures that advantageously extract road traffic from DFOS vibration patterns such that anomaly detection is possible. Sensed vibration data is represented accurately as a set of points, where each point is denoted as a tuple with elements indicating a time stamp, a location along a length of a DFOS optical sensing cable, and vibration strength detected at the location at the time. Traffic pattern detection is based on a progressive probabilistic Hough transform (PPHT) that exploits global information from an entire spatial-temporal data snapshot to assess a cause of detected vibrations.

Abstract: A method for generating images with high dynamic range (HDR) based on multiple images captured at different aperture values, under different conditions, or at different shutter speeds is applied in a device. The method inputs the original multiple images into a predetermined model and aligns the multiple images. The method further confirms object images that need to be attended among multiple aligned images and obtains a merge weighting for each of the object images, and merges the images for a generated HDR according to the merge weighting of each image. The device utilizing the method is also disclosed.

Abstract: In one aspect, there is provided a method that includes receiving, by a control system having (i) a first camera configured to obtain an image of a scene, (ii) a winch controller, and (iii) a feeding system configured to deliver a feed to aquaculture, instructions to initiate a calibration of the first camera, determining a calibration state of the first camera, determining a sequence of calibration steps based on the calibration state of the first camera, and executing the sequence of calibration steps to calibrate the first camera.

Abstract: Methods and apparatus for the application of machine learning to radiographic images of animals. In one embodiment, the method includes receiving a set of radiographic images captured of an animal, applying one or more transformations to the set of radiographic images to create a modified set, segmenting the modified set using one or more segmentation artificial intelligence engines to create a set of segmented radiographic images, feeding the set of segmented radiographic images to respective ones of a plurality of classification artificial intelligence engines, outputting results from the plurality of classification artificial intelligence engines for the set of segmented radiographic images to an output decision engine, and adding the set of segmented radiographic images and the output results from the plurality of classification artificial intelligence engines to a training set for one or more of the plurality of classification artificial intelligence engines.

Abstract: A product authentication system includes one or more image capture devices that provide video data representative of an enhanced safety environment. The product authentication system can determine the continuous presence of a designated product during a time period, for example, during performance of a task in an enhanced safety environment. The video data can be spatiotemporally sliced according to multiple orientations with respect to the time axis and the two spatial axes. A plurality of data streams are created where the slices of each respective data stream have the same orientation. The data streams are processed according to one or more machine learning models, such as convolutional neural networks trained to determine whether the designated product is continuously present in the video data. An indicator of the continuous presence of the designated product can be provided to a downstream system and used to indicate whether functions of the downstream system are to be performed.

Abstract: A controller includes an acquisition unit that acquires image data captured by an imaging device for photographing disposed in a moving body, and a calculation unit that calculates a relative position of a position of a subject, which is detected by a plurality of distance-measuring imaging devices provided in the moving body, based on the subject included in the image data.

Abstract: There is provided a method of re-classifying a clinically significant feature of a medical image as an artifact, comprising: feeding a target medical image captured by a specific medical imaging sensor at a specific setup into a machine learning model, obtaining a target feature map as an outcome of the machine learning model, wherein the target feature map includes target features classified as clinically significant, analyzing the target feature map with respect to sample feature map(s) obtained as an outcome of the machine learning model fed a sample medical image captured by at least one of: the same specific medical imaging sensor and the same specific setup, wherein the sample feature map(s) includes sample features classified as clinically significant, identifying target feature(s) depicted in the target feature map having attributes matching sample feature(s) depicted in the sample feature map(s), and re-classifying the identified target feature(s) as an artifact.

Abstract: An image-based classification workflow uses unsupervised clustering to help a user identify subpopulations of interest for sorting. Labeled cell images are used to fine-tune the supervised classification network for a specific experiment. The workflow allows the user to select the populations to sort in the same manner for a variety of applications. The supervised classification network is very fast, allowing it to make real-time sort decisions as the cell travels through a device. The workflow is more automated and has fewer user steps, which improves the ease of use. The workflow uses machine learning to avoid human error and bias from manual gating. The workflow does not require the user to be an expert in image processing, thus increasing the ease of use.

Abstract: A head-mounted device (HMD) can be configured to determine a request for recognizing at least one content item included within content framed within a display of the HMD. The HMD can be configured to initiate a head-tracking process that maintains a coordinate system with respect to the content, and a pointer-tracking process that tracks a pointer that is visible together with the content within the display. The HMD can be configured to capture a first image of the content and a second image of the content, the second image including the pointer. The HMD can be configured to map a location of the pointer within the second image to a corresponding image location within the first image, using the coordinate system, and provide the at least one content item from the corresponding image location.

Abstract: An automatic generation system of a training image and a method thereof are provided. The disclosure generates a training image and records the target category and the target position. The disclosure adds the target image to the container image as a candidate image, calculates a reliability of the candidate image, and repeatedly executes the process until the reliability of the candidate image meets a threshold condition for generating the training image. The disclosure is able to generate the training images automatically, and the recognition difficulty of the training image is adjustable by the user, so as to be suitable for customized recognition training.

Abstract: A method for semantic annotation of sensor data may include obtaining sensor data representing an image of a geographic area. The boundary points defining a first polygon in the image of the geographic area may be determined based on the sensor data. An overlap between the first polygon and a second polygon in the image of the geographic area may be detected based at least on the boundary points defining the first polygon. At least one of the first polygon or the second polygon may be modified to remove the overlap between the first polygon and the second polygon. An annotation corresponding to the first polygon may be generated based on the modifying of at least one of the first polygon or the second polygon. The annotation may identify a physical feature within the geographic area. Related systems and computer program products are also provided.

Abstract: A method includes receiving a first image that is captured at a first time. The method also includes detecting a location of a first object in the first image. The method also includes determining a region of interest based at least partially upon the location of the first object in the first image. The method also includes receiving a second image that is captured at a second time. The method also includes identifying the region of interest in the second image. The method also includes detecting a location of a second object in a portion of the second image that is outside of the region of interest.