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.

Abstract: A method in a computing device includes: in a facility containing a plurality of support structures, capturing an image of a first support structure; detecting, in the image, a first feature set of the first support structure; selecting obtaining at least one reference feature set by proximity to an estimated location of the mobile computing device in the facility coordinate system, the at least one reference feature set selected from a repository defining feature locations for each of the support structures in a facility coordinate system; comparing the first feature set with the at least one reference feature set; and in response to determining that the first feature set matches the at least one reference feature set, determining a location of the mobile computing device in the facility coordinate system based on the image and the feature locations from the repository.

Abstract: A method for machine learning-based classification may include training a machine learning model with a full training data set, the full training data set comprising a plurality of data points, to generate a first model state of the machine learning model, generating respective embeddings for the data points in the full training data set with the first model state of the machine learning model, applying a clustering algorithm to the respective embeddings to generate one or more clusters of the embeddings, identifying outlier embeddings from the one or more clusters of the embeddings, generating a reduced training data set comprising the full training data set less the data points associated with the outlier embeddings, training the machine learning model with the reduced training data set to a second model state, and applying the second model state to one or more data sets to classify the one or more data sets.

Abstract: A system and method for improving driver situation awareness prediction using human visual sensory and memory mechanism that includes receiving data associated with a driving scene of a vehicle and an eye gaze of a driver of the vehicle. The system and method also include analyzing the data and extracting features associated with objects located within the driving scene and determining a situational awareness score that is associated with a situational awareness of the driver with respect to each of the objects located within the driving scene. The system and method further include communicating control signals to electronically control at least one system of the vehicle based on the situational awareness score that is associated with each of the objects located within the driving scene.

Abstract: A system configured for verification of imaged target detection performs the following: (a) receive information indicative of at least two images of object(s). This information comprises candidate target detection region(s), indicative of possible detection of a target associated with the object(s). Images have at least partial overlap. The candidate region(s) appears at least partially in the overlap area. The images are associated with different relative positions of capturing imaging device(s) and of an imaged portion of the object(s). (b) process the information to determine whether the candidate region(s) meets a detection repetition criterion, the criterion indicative of repetition of candidate region(s) in locations of the images that are associated with a same location on a data representation of the object(s). (c) if the criterion is met, classify the candidate region(s) as verified target detection region(s). This facilitates output of an indication of the verified region(s).

Abstract: A method includes obtaining a color transformation matrix that removes color distortion of an original color histogram of a target color space for an input image of an original color space; obtaining a color transformation image of the original color space from which color distortion of the input image is removed using the color transformation matrix; and obtaining a space transformation image with a minimum target loss value between an output vector of a neural network for one of candidate images and each of a plurality of candidate class vectors of the input image, the candidate images being spaced apart from the color transformation image of the original color space by a distance less than a threshold.

Abstract: Disease detection from medical images is provided. In various embodiments, a medical image of a patient is read. The medical image is provided to a trained anatomy segmentation network. A feature map is received from the trained anatomy segmentation network. The feature map indicates the location of at least one feature within the medical image. The feature map is provided to a trained classification network. The trained classification network was pre-trained on a plurality of feature map outputs of the segmentation network. A disease detection is received from the trained classification network. The disease detection indicating the presence or absence of a predetermined disease.

Abstract: Systems, methods, and computer program products of intelligent image analysis using object detection models to identify objects and locate and detect features in an image are disclosed. The systems, methods, and computer program products include automated learning to identify the location of an object to enable continuous identification and location of an object in an image during periods when the object may be difficult to recognize or during low visibility conditions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting a neural network with additional operations.

Abstract: An object counting system crops images into multiple split images. When a distance between at least one side of a bounding box being associated with a position of a first object in the first split image and at least one side of a bounding box being associated with a position of a second object in the second split image adjacent to the first split image is less than a tolerance value, the processor combines the adjacent first split image and the second split second split image into a merged image, so that the first object and the second object are merged into a merged object. A processor calculates a prediction number of objects based on the objects contained in these split images and the merged objects in the merged image. The object counting system automatically counts the number of bug eggs, to save manpower and provide an accurate count.

Abstract: An image generation method includes: extracting a content feature of a first image; respectively extracting an overall image style feature of a second image, and an object style feature of a partial image block, which includes an object, in the second image; determining a target style feature at least according to the overall image style feature and the object style feature; and generating a third image according to the content feature and the target style feature.

Abstract: Systems and methods are provided for detecting a flashing light on one or more traffic signal devices. The method includes capturing a series of images of one or more traffic signal elements in a traffic signal device over a length of time. The method further includes, for each traffic signal element, analyzing the series of images to determine one or more time periods at which the traffic signal element is in an on state or an off state, and analyzing the time periods to determine one or more distinct on states and one or more distinct off states. The method further includes identifying one or more cycles correlating to a distinct on state immediately followed by a distinct off state, or a distinct off state immediately followed by a distinct on state, and, upon identifying a threshold number adjacent cycles, classifying the traffic signal element as a flashing light.

Abstract: Methods and systems for setting up care areas (CAs) for inspection of a specimen are provided. One system includes an imaging subsystem configured for generating images of a specimen and a computer subsystem configured for determining a number of defects detected in predefined cells within one or more of the images generated in a repeating patterned area formed on the specimen. The computer subsystem is also configured for comparing the number of the defects detected in each of two or more of the predefined cells to a predetermined threshold and designating any one or more of the two or more of the predefined cells in which the number of the defects is greater than the predetermined threshold as one or more CAs. In addition, the computer subsystem is configured for storing information for the one or more CAs for use in inspection of the specimen.

Abstract: A server includes a controller programmed to obtain information about a first perception model installed in a vehicle. The controller is further programmed to determine a value of updating the first perception model. The controller is further programmed to determine whether the first perception model needs to be updated to a second perception model based on the value of updating the first perception model. The controller is further programmed to transmit the second perception model to the vehicle in response to determining that the first perception model needs to be updated to the second perception model.

Abstract: Systems and methods for efficient lossless compression of captured raw image information are presented. A method can comprise: receiving raw image data from an image capture device, segregating the pixel data into a base layer portion and an enhanced layer portion, reconfiguring the base layer portion expressed in the first color space values from a raw capture format into a pseudo second color space compression mechanism compatible format, and compressing the reconfigured base layer portion of first color space values. The raw image data can include pixel data are expressed in first color space values. The segregation can be based upon various factors, including a compression benefits analysis of a boundary location between the base layer portion and enhanced layer portion. The reconfiguring the base layer portion can include separating the base layer portion based upon multiple components within the raw data; and forming base layer video frames from the multiple components.

Abstract: Systems, apparatuses and methods may provide for technology that processes an inference workload in a first subset of layers of a neural network that prevents or inhibits data dependent branch operations, conducts an exit determination as to whether an output of the first subset of layers satisfies one or more exit criteria, and selectively bypasses processing of the output in a second subset of layers of the neural network based on the exit determination. The technology may also speculatively initiate the processing of the output in the second subset of layers while the exit determination is pending. Additionally, when the inference workloads include a plurality of batches, the technology may mask one or more of the plurality of batches from processing in the second subset of layers.

Abstract: The present disclosure relates to a method for image classes definition and to a method for image multiprocessing and related vision system, which implement said method for image classes definition.

Abstract: An information processing device is provided that includes an operation control unit which controls the operations of an autonomous mobile object that performs an action according to a recognition operation. Based on the detection of the start of teaching related to pattern recognition learning, the operation control unit instructs the autonomous mobile object to obtain information regarding the learning target that is to be learnt in a corresponding manner to a taught label. Moreover, an information processing method is provided that is implemented in a processor and that includes controlling the operations of an autonomous mobile object which performs an action according to a recognition operation. Based on the detection of the start of teaching related to pattern recognition learning, the controlling of the operations includes instructing the autonomous mobile object to obtain information regarding the learning target that is to be learnt in a corresponding manner to a taught label.

Abstract: In one aspect, data characterizing a video feed acquired by a camera oriented toward and including a field of view of a forecourt of a fueling station can be received. The video feed can be monitored for hazards, and the monitoring of the video feed can include performing automatic hazard detection on the video feed using at least one predictive model that predicts a presence of a hazard within the forecourt of the fueling station. A command can be transmitted in response to the detecting of the presence of the hazard within the forecourt of the fueling station. Related apparatus, systems, methods, techniques, and articles are also described.