Abstract: Aspects of the technology described herein describe a system for detecting and reducing wear in industrial equipment. Aspects of the technology use 3D image data from a field inspection of industrial equipment to identify and quantify wear. The wear can be detected by providing the images from the field inspection to a computer classifier for recognition. Aspects of the technology also use machine learning to recommend a change to the operation of the equipment to minimize wear. Such a change could include load shedding, lube oil feed rate changes, prompts for maintenance, etc. Through incorporation of the wear data into the control system, the equipment can automatically change operation to improve wear performance and increase the durability and lifetime of the equipment.

Abstract: Determining that a motor vehicle driver is using a mobile device while driving a motor vehicle. Multiple images of a driver of a motor vehicle are captured through a side window of the motor vehicle. Positive images show a driver using a mobile device while driving a motor vehicle. Negative images show a driver not using a mobile device while driving a motor vehicle. Multiple training images are selected from both the positive images and the negative images. The selected training images and respective labels, indicating that the selected training images are positive images or negative images, are input to a machine (e.g. Convolutional Neural Network, (CNN)). The CNN is trained to classify that a test image, captured through a side window of a motor vehicle, shows a driver using a mobile device while driving the motor vehicle.

Abstract: An image recognition method and apparatus based on a systolic array, and a medium are disclosed. The method includes: converting obtained image feature information into a one-dimensional feature vector; converting an obtained weight matrix into a one-dimensional weight vector, and allocating a corresponding weight group to each node in a trained three-dimensional systolic array model; performing multiply-accumulate of the feature vector and a weight value on the one-dimensional feature vector in parallel by using the three-dimensional systolic array model, to obtain a feature value corresponding to each node, the feature values with different values reflecting article categories contained in an image; and determining an article category contained in the image according to the feature value corresponding to each node and a pre-established corresponding relationship between the feature value and the article category.

Abstract: An apparatus for identifying the state of an object includes a processor configured to input, every time obtaining an image from a camera, the image into a first classifier to detect, for each of one or more predetermined objects represented in the image, an object region including the object; determine a predicted object region in a subsequent image to be obtained from the camera for an object whose position in the subsequent image is predictable; and input characteristics into a second classifier to identify the state of an object involving time-varying changes in outward appearance. When the object has a predicted object region, the characteristics are obtained from pixel values of the predicted object region in the subsequent image. On the other hand, when the object does not have a predicted object region, the characteristics are obtained from pixel values of the object region detected from the subsequent image.

Abstract: An evaluation method of a biometric identification function implemented from a candidate biometric data set and a reference biometric data set, the biometric identification function, applied to a candidate biometric data item and a reference biometric data item, returning a match, the method comprising steps of: obtaining pairs of false matches, each pair comprising a candidate biometric data item and a reference biometric data item not associated with a same known individual; determining, for each candidate biometric data item in a pair, a first number associated with said item and equal to the number of pairs of false matches obtained comprising said item, and/or a second number associated with said reference biometric data item and equal to the number of pairs of false matches obtained comprising said item; calculating a bias score based on a maximum of the first numbers and/or based on a maximum of the second numbers.

Abstract: Implementations are described herein for training and applying machine learning models to digital images capturing plants, and to other data indicative of attributes of individual plants captured in the digital images, to recognize individual plants in distinction from other individual plants. In various implementations, a digital image that captures a first plant of a plurality of plants may be applied, along with additional data indicative of an additional attribute of the first plant observed when the digital image was taken, as input across a machine learning model to generate output. Based on the output, an association may be stored in memory, e.g., of a database, between the digital image that captures the first plant and one or more previously-captured digital images of the first plant.

Abstract: In certain embodiments, the systems, apparatus, and methods disclosed herein relate to robotic surgical systems with built-in navigation capability for patient position tracking and surgical instrument guidance during a surgical procedure, without the need for a separate navigation system. Robotic based navigation of surgical instruments during surgical procedures allows for easy registration and operative volume identification and tracking. The systems, apparatus, and methods herein allow re-registration, model updates, and operative volumes to be performed intra-operatively with minimal disruption to the surgical workflow. In certain embodiments, navigational assistance can be provided to a surgeon by displaying a surgical instrument's position relative to a patient's anatomy.

Abstract: Methods, systems, and apparatuses related to autonomous vehicle object detection are described. An autonomous vehicle can capture an image corresponding to an unknown object disposed within a sight line of the autonomous vehicle. Processing resources available to a plurality of memory devices associated with the autonomous vehicle can be reallocated in response to capturing the image and an operation involving the image corresponding to the unknown object to classify the unknown object can be performed using the reallocated processing resources.

Abstract: A vehicle light signal detection and recognition method, system, and computer program product include bounding, using a coarse attention module, one or more regions of an image of an automobile including at least one of a brake light and a signal light generated by automobile signals which include illuminated sections to generate one or more bounded region, removing, using a fine attention module, noise from the one or more bounded regions to generate one or more noise-free bounded regions, and identifying the at least one of the brake light and the signal light from the one or more noise-free bounded regions.

Abstract: Disclosures herein teach applying a set of sections spanning a down-sampled version of an image of a road-scene to a low-fidelity classifier to determine a set of candidate sections for depicting one or more objects in a set of classes. The set of candidate sections of the down-sampled version may be mapped to a set of potential sectors in a high-fidelity version of the image. A high-fidelity classifier may be used to vet the set of potential sectors, determining the presence of one or more objects from the set of classes. The low-fidelity classifier may include a first Convolution Neural Network (CNN) trained on a first training set of down-sampled versions of cropped images of objects in the set of classes. Similarly, the high-fidelity classifier may include a second CNN trained on a second training set of high-fidelity versions of cropped images of objects in the set of classes.

Abstract: An onboard camera image application system includes multiple vehicles, an information providing system, and a PC. In the information providing system, a collection server collects image data captured by onboard cameras of the vehicles. An analysis server extracts, from the image data captured around one location, feature information associated with an extraction item for a person or a vehicle around the location. The analysis server also classifies the extracted feature information by classification item. A providing server sends the classified feature information to the PC of a user. The user is able to set a location to be processed, through the PC, and is also able to set the extraction item or the classification item.

Abstract: A system and method detect a change within an agricultural field during a growing season. The system and method involve the computation of correlation coefficients between pairs of images in a time series of images over an area, for example an agricultural field. Through comparisons of correlation coefficients over time, sudden field changes can be detected. When these field changes meet specified criteria (such as a minimum value threshold), a notification (alert) can be sent to an agricultural grower, informing them of the change in crop condition, and allowing them to view the changes in the field.

Abstract: The image processing device acquires feature quantities (maximum value, minimum value, average value, histogram, etc.) of the entire area (GA) of the image and feature quantities of each local area (LA) of the image from the input image, and calculates a plurality of modulation gain values (gamma correction curves) for GA and each LA. Furthermore, the image processing device determines the correction intensity for each LA from the feature quantity of the GA and the feature quantity of each LA, and creates the LA correction intensity map. Finally, the image processing device finally applies the result of combining a plurality of modulation gain values based on the LA correction intensity map to the input image.

Abstract: In a road parameter estimation apparatus, a marker-based estimator extracts, based on markers extracted by a marker extractor, at least one lane line that demarcates a road into plural regions in a width direction of the road, and estimates, based on the extracted at least one lane line, a value of at least one feature parameter of the road as a maker-based estimation result. The at least one feature parameter of the road represents at least one feature of the road. A model-based estimator estimates, based on the at least one model-based demarcation line, a value of the at least one feature parameter of the road parameter as a model-based estimation result. A determiner compares the at least one lane line with the model-based demarcation line to accordingly determine whether to use the marker-based estimation result or the model-based estimation result.

Abstract: According to some embodiments, disclosed are systems and methods for a novel framework of real-time event alert detection and communication. The disclosed framework operates by analyzing live-feeds of captured video at location and determining whether events lend towards a dangerous activity, then automatically alerting the users involved as to potential and/or imminent harm awaiting their actions. Rather than alerting one user, or a manger, as in conventional systems, the disclosed technology may evidence a communication relay among devices at a location, devices of users involved, as well as devices (and devices of users) overseeing operations within which the dangerous activity is anticipated or detected. This may lead to improved safety at and/or around workplace environments, as well as improved operational efficiency, thereby leading to reduced costs, reduced overhead and a reduction in resource expenditure.

Abstract: Aspects of the present disclosure relate to multi-spectrum visual object recognition. A first image corresponding to visible light and a second image corresponding to invisible light with respect to an object can be obtained. A first contour of the object can be identified based on the first image. A second contour of the object can be identified based on the second image. The first contour of the object and the second contour of the object can be integrated to generate a multi-spectrum contour of the object. The object can be recognized using the multi-spectrum contour of the object.

Abstract: A tiptoe position estimating device includes: a camera configured to capture an image of an interior of a vehicle; and a human body information acquisition unit configured to acquire, from a captured image obtained by capturing an image of a person seated on a seat in the interior by the camera, position information of skeleton points at a plurality of positions of a body of the person. The human body information acquisition unit is configured to acquire thigh information which is position information of a skeleton point of a thigh of the person, and lower leg information which is position information of a skeleton point of a lower leg of the person. The human body information acquisition unit includes a tiptoe position estimating part configured to estimate a tiptoe position of a foot of the person based on the acquired thigh information and the acquired lower leg information.

Abstract: The present disclosure is directed to apparatuses, systems and methods for automatically classifying images of occupants inside a vehicle. More particularly, the present disclosure is directed to apparatuses, systems and methods for automatically classifying images of occupants inside a vehicle by comparing current image feature data to previously classified image features.

Abstract: A method for determining a safe state for a vehicle includes disposing a camera at a vehicle and disposing an electronic control unit (ECU) at the vehicle. Image data is captured via the camera and provided to the ECU. An image processor of the ECU processes captured image data. A condition is determined via processing at the image processor of the ECU captured image data. The condition comprises a shadow present in the field of view of the camera within ten frames of captured image data or a damaged condition of the imager within two minutes of operation of the camera. The condition is indicative of a condition where processing of captured image data degrades in performance. The ECU determines a safe state for the vehicle responsive to determining the condition.

Abstract: A driving assistance device includes: a line-of-sight direction detection unit that detects a direction of a line of sight of a driver of a moving body; an obstacle detection unit that detects a position of an obstacle in environs of the moving body; an assessment criteria determination unit that determines assessment criteria of a look at the obstacle by the driver based on at least one of time, location, weather, a state of the moving body, and a state of the driver; and a warning processing unit that obtains an assessment result by applying, to the assessment criteria, a score computed based on the direction of the line of sight of the driver and the position of the obstacle, the warning processing unit determining at least one of whether or not a warning needs to be issued to the driver and a level of the warning, based on the assessment result.