Abstract: In the present invention, a process of receiving an image obtained by capturing a measurement target place with a camera, calculating a number of people in the measurement target place based on the image received, and allocating a car according to the calculated number of people is performed. Here, when an abnormality that an image from the camera cannot be received is determined, a process of referring to a detection value of a sensor or the like installed in a car or in the measurement target place to calculate the number of people in the car or the measurement target place is performed.

Abstract: One or more example embodiments of the present invention relates to a method for transmitting medical video data via a network. According to one more example embodiments, medical video data is provided via at least one of a medical imaging modality or a hospital data system. The medical video data is held in a buffer. Furthermore, a network connection is established in the network from a terminal to the buffer via a web protocol. The medical video data is transmitted from the buffer to the terminal in at least one network data stream via the network connection via the web protocol. The medical video data is displayed on a display apparatus of the terminal. One or more example embodiments of the present invention further relates to a system for transmitting medical video data and a buffer and also a terminal for such a system.

Abstract: A process of collaboration between different agencies for classifying an event captured in a video stream. In operation, a video stream captured by a camera operated by a public-safety agency is analyzed using a first video analytics engine trained using a first set of video analytics data associated with the public-safety agency and an abnormal event with respect to a person or object captured in the video stream is detected. When it is determined that the video stream is captured at a location that is proximity to an operating environment of a non-public-safety agency, a query is transmitted to a second video analytics engine trained using a second set of video analytics data associated with the non-public-safety agency. The abnormal event is reclassified as a normal event when a response from the second video analytics engine indicates that the abnormal event is normal within the operating environment of the non-public-safety agency.

Abstract: A vehicular vision system includes a camera disposed within a cabin of a vehicle equipped with the vehicular vision system and positionable to view within an interior cabin of the vehicle and positionable to view exterior of the vehicle through at least one window of the vehicle. The system includes an actuator disposed at the vehicle and electrically operable to rotate the camera about an axis relative to the vehicle. Multiple frames of image data captured by the camera as the camera rotates about the axis are processed at an ECU for a plurality of vehicle functions. Respective frames of image data of the multiple frames of captured image data are processed for respective vehicle functions of the plurality of vehicle functions based on respective viewing directions of the camera when the respective frames of image data are captured by the camera.

Abstract: An artificial intelligence (AI) entry management (EM) security system includes a camera, a microphone, a motion detector, a speaker, and a software platform. Geofences are utilized to create boundaries around physical areas, such as locations for package delivery or property boundaries. The EM device and other devices connected to the software platform are configured to monitor the geofences and detect a presence of an activity, an event, an object, or a device. At least one license plate reader is utilized to read license plate characters. Voice recognition and voice identification are used to grant or deny permissions for individuals on a property.

Abstract: An event-based analytics tool can obtain, from a data lake, an instance of correlated event data including a first event from a first network device, a second event from a second network device, and data correlating the first event to the second event. The event-based analytics tool can obtain PCAP data from a troubleshooting server via a first application programming interface. The event-based analytics tool can also obtain a log from a searchable log database via a second application programming interface. Based on the correlated event data, the packet capture data, and the log, the event-based analytics tool can generate a prediction model that can be used to predict a cause of a future event.

Abstract: An electronic apparatus includes a processor; and a memory storing a program which, when executed by the processor, causes the electronic apparatus to: acquire an image in which a first image region captured by using a first optical system and a second image region captured by using a second optical system are disposed side by side; display the first image region and the second image region on a display; receive a predetermined operation from a user; and in a case where the predetermined operation is received from the user, control such that a magnified image region, generated by magnifying a part of the first image region, is displayed instead of the second image region.

Abstract: In one embodiment, a computing system may determine a pose of a device held by or attached to a hand of a user based on sensor data captured by the device. The system may determine a pose of a headset worn by the user based on sensor data captured by the headset. The system may determine positions of a first set of keypoints associated with a first portion of a body of the user based on (1) one or more first images captured by one or more cameras of the device, (2) the pose of the device, (3) one or more second images captured by one or more cameras of the headset and (4) the pose of the headset. The system may determine a body pose of the user based at least on the positions of the first set of keypoints.

Abstract: In accordance with an embodiment, described herein are systems and methods for auto-completion of ICS flow using artificial intelligence/machine learning. Next actions prediction is a service that assists users in modeling the flows quickly by predicting and suggesting the next set of actions a user might be thinking of adding. The service also assists the user to follow some of the best practices while creating an integration flow.

Abstract: An image capturing device is provided on a working machine and takes a captured image of surroundings including an object around the working machine. A first setting part sets a detection region in the captured image where the object is detected. A responsive action part executes a predetermined responsive action in a case that the object is in the detection region in the captured image. The first setting part sets a boundary that is a limit of the detection region in the captured image. The boundary extends in a front orthogonal direction and has a certain shape.

Abstract: A refrigerator according to the present embodiment comprises: a cabinet comprising a storage chamber; and a door for opening and closing the storage chamber. The door comprises: a main door comprising an opening and a door storage unit; a sub-door that opens and closes the opening and can rotate about a hinge with respect to the main door; a first camera and a second camera that are provided spaced apart from each other in the sub-door, and capture images of the door storage unit in a state where the sub-door is open; a marker provided on the main door and image-captured by the first camera; and a display unit for displaying result images including at least a portion of images captured by the first and second cameras.

Abstract: An artificial intelligence (AI) entry management (EM) security system includes a camera, a microphone, a motion detector, a speaker, and a software platform. Geofences are utilized to create boundaries around physical areas, such as locations for package delivery or property boundaries. The EM device and other devices connected to the software platform are configured to monitor the geofences and detect a presence of an activity, an event, an object, or a device. At least one license plate reader is utilized to read license plate characters. Voice recognition and voice identification are used to grant or deny permissions for individuals on a property.

Abstract: An information processing apparatus of the present invention detects a queue (20) of objects from video data (12). Further, the information processing apparatus of the present invention generates element information using a video frame (14) in which the queue (20) of objects is detected. The element information is information in which an object area (24) in the video frame (14) occupied by the object (22) included in the queue (20) of objects is associated with an attribute of the object (22). Furthermore, the information processing apparatus of the present invention detects a change in the queue (20) of objects based on the element information and the detection result of the object to video frame (14) generated after the video frame (14) in which the element information is generated. Then, the information processing apparatus of the present invention generates element information for the queue (20) of objects in which a change is detected to update the element information used later.

Abstract: An object to reduce a possibility that a detection target appearing in a captured image is not detected. In order to achieve such an object, an image processing device includes: a first detection unit that is configured to detect a predetermined object and a predetermined part of the predetermined object from an acquired captured image; a setting unit that sets a detection range in the captured image based on a detection result of the first detection unit in a case where only the predetermined object out of the predetermined object and the predetermined part has been detected by the first detection unit; and a second detection unit that attempts to detect the predetermined part in the detection range.

Abstract: A user equipment (UE), for example, used with a Vulnerable Road User, determines a relative position of the UE and sends a report of the relative position to one or more vehicle On-Board Units (OBUs), wherein the report further includes an identification of the one or more reference points. The relative position may be with respect to one or more reference points, which may be stationary or moving. The relative position may be determined and reported based on identifiers for the one or more reference points and distance or distance vectors to each of the one or more reference points. The relative position may be determined based on data from one or more one board sensors, such as radar, lidar, ultrasound, or camera, as well as with wireless transceivers. The relative position may additionally include a heading and a placement with respect to one or more street elements.

Abstract: An information processing apparatus of the present invention detects a queue (20) of objects from video data (12). Further, the information processing apparatus of the present invention generates element information using a video frame (14) in which the queue (20) of objects is detected. The element information is information in which an object area (24) in the video frame (14) occupied by the object (22) included in the queue (20) of objects is associated with an attribute of the object (22). Furthermore, the information processing apparatus of the present invention detects a change in the queue (20) of objects based on the element information and the detection result of the object to video frame (14) generated after the video frame (14) in which the element information is generated. Then, the information processing apparatus of the present invention generates element information for the queue (20) of objects in which a change is detected to update the element information used later.

Abstract: A trained first model is generated through first learning using a first learning image group constituted of a normal image which is a medical image having no region of interest. An input image group including at least the medical image different from the first learning image group is input to the trained first model, and abnormality detection is performed. The extracted image used for learning to prevent erroneous recognition is sorted according to a result of the abnormality detection, and second learning using a second learning image group including at least the extracted image is performed. A second model that detects the region of interest is generated through the second learning.

Abstract: This application describes an AI-powered Cloud-native Network Video Recorder (NVR) apparatus. This apparatus features multiple Power over Ethernet (PoE) ports, processors, computer-readable memories, and firmware implementing a camera-integration module, an Artificial Intelligence (AI) module, and a cloud-access module. The camera-integration module enables efficient connection and video data reception from heterogeneous cameras. The AI module processes the video data, identifying and generating clips of interest, optimizing surveillance efficiency. Finally, the cloud-access module facilitates the uploading of these clips to cloud storage, ensuring accessible and secure data management. This innovative NVR apparatus enables users to deploy a cloud-native video surveillance system using existing camera devices, significantly lowering the cost of adoption.

Abstract: A system and method for compressing and restoring data using a hierarchical multi-level autoencoder architecture and correlation network. The system compresses data using a cascade of autoencoders, each focusing on different scales or features, allowing for efficient representation across various resolutions. Data restoration employs a corresponding hierarchical decoder structure and a correlation network, trained on cross-correlated data sets. This approach leverages inter-data relationships at multiple scales, potentially recovering more lost information than traditional single-scale methods. The hierarchical structure adapts to diverse data types, achieving higher compression ratios while maintaining data quality, applicable to fields such as remote sensing, IoT data processing, and multimedia compression.

Abstract: A video camera includes a camera for capturing a video stream and a controller that is operably coupled to the camera. The controller, which includes processing resources, is configured to determine a current utilization of one or more of the processing resources and to determine which of a plurality of video analytics algorithms should be executed based at least in part on the determined current utilization of the one or more processing resources. The controller is configured to execute two or more of the plurality of video analytics algorithms on the video stream to identify one or more events in the video stream, wherein the controller executes the two or more of the plurality of video analytics algorithms, and sends an alert in response to identifying one or more events in the video stream.

Abstract: In one embodiment, a method includes maintaining a video communication between client devices with each being associated with a respective video stream, which is associated with a respective match scale measured based on a height of frames of the video stream and a depth of subjects within the frames, determining a respective scaling factor and cropping for each video stream, wherein the respective scaling factor is calculated based on the match scale associated with the corresponding video stream and a target match scale determined from the match scales associated with all video streams, and wherein the respective cropping is determined based on a uniformity of positions of the subjects within the frames across all video streams, generating a merged video stream from each video stream based on the respective scaling factor and cropping, and sending instructions for presenting the merged video stream to one or more of the client devices.

Abstract: A system includes a sensor detecting entry/exit of a person to/from a toilet and a sensor detecting leaving/sitting on a toilet seat installed on a toilet bowl; acquires excretion information indicating at least a start and an end of excretion, based on imaging data captured by an image capture apparatus installed in such a way as to include, in an image capture range, an excretion range of excrement in the bowl; authenticates a person performed entry/exit, and determines whether the person is a person to be assisted as a user of the toilet or a helper; outputs notification information to a notification destination, based on a detection event indicated by the excretion information, entry/exit information, leaving/sitting information, and an authentication result, and a notification condition; and stores, as the notification condition, necessity of notification, and the notification information and the notification destination when notification is necessary, for each events.

Abstract: The present invention discloses a vehicle remote control system that includes a user interface including an input portion receiving an input of vehicle control from a user, a communication portion wirelessly communicating with a vehicle control unit, and an informing portion outputting information, and an information control unit commanding the informing portion of the user interface to output information at start time or end time of drive control or specific event occurrence time during the drive control when the drive control including start control or move control of the vehicle is performed by the vehicle drive control unit being controlled through the user interface.

Abstract: A video doorbell system operable to generate a chime sound, comprises a transformer, operable to convert a premise's power supply to a suitable. The video doorbell system further includes a video doorbell having a processor, a video camera and a wireless communication module. The video doorbell is electrically connected to the transformer by a two-wire interface. The processor within the video doorbell operable to generate a chime signal using power supplied from the two-wire interface when a doorbell button is depressed. The video doorbell system further includes a chime controller, electrically connected to the transformer and the video doorbell by the two-wire interface. The video doorbell system continues to provide sufficient power to the video doorbell from the transformer via the two-wire interface so as to be able to operate the processor, video camera and wireless communication module while the doorbell button is currently depressed.

Abstract: An own-position estimating device for estimating an own-position of a moving body by matching a feature extracted from an acquired image with a database in which position information and the feature are associated with each other in advance, includes an estimating unit estimating the own-position of the moving body by matching the feature extracted by the extracting unit with the database, and a determination threshold value adjusting unit adjusting a determination threshold value for extracting the feature, in which the determination threshold value adjusting unit acquires the database in a state in which the determination threshold value is adjusted, and adjusts the determination threshold value on the basis of the determination threshold value linked to each of the position information items in the database, and the extracting unit extracts the feature from the image by using the determination threshold value adjusted by the determination threshold value adjusting unit.

Abstract: Described is a method for extraction of a region of interest (ROI) from a composite synthetic aperture radar (SAR) phase history data. The method comprising receiving, with a system comprising a processor, the composite SAR phase history data of a plurality of backscattered return signals produced by a SAR system illuminating a scene with a SAR beam. The method also comprises obtaining a location of a first ROI within the scene and extracting from the composite SAR phase history data a first component SAR phase history data corresponding to the ROI at the location of the ROI.

Abstract: Systems, devices, computer-implemented methods, and/or computer program products that can facilitate pedestrian detection via a boundary cylinder model are addressed. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer-executable components can comprise a bounding cylinder model component that determines numerical values for height and radius parameters of a three-dimensional bounding cylinder model representing a pedestrian, and that generates the three-dimensional bounding cylinder model representing the pedestrian based on the numerical values.

Abstract: In an embodiment, a method includes obtaining radiation emitted from a radiation source. The method includes modulating the radiation with a time-varying modulation to generate a time-varying illumination pattern with a known modulation. The illumination pattern includes a time-varying intensity for each of a plurality of spatial locations. The method includes illuminating a target volume with the illumination pattern. The method includes collecting a signal generated by one or more objects within the target volume in response to illumination by the illumination pattern. The method includes estimating a location of each of the one or more objects based on the collected signal and the known modulation.

Abstract: A video management apparatus 100a includes: an abnormality video registration unit 135 configured to associate a plurality of abnormality video data obtained in a respective plurality of first worksites at an abnormality occurrence time with the respective pieces of first worksite information related to safety of the respective first worksites, and to register the plurality of abnormality video data in an abnormality video database 125, in response to obtaining each of a plurality of pieces of abnormality occurrence information indicating abnormalities that have occurred at the respective plurality of first worksites; a notification processing unit 137 configured to notify a second terminal associated with a second worksite, of information related to the registration of these abnormality video data; and a video distribution processing unit 139 configured to distribute the abnormality video data associated with the second worksite from among the plurality of abnormality video data to the second terminal.

Abstract: An information display device for displaying activity schedule of an assigned user provided with one of seats in advance, detects position and direction of the information display device; acquires distance from the information display device to a display target seat of an assigned user whose activity schedule is to be displayed; uses the position, the direction, and the distance to calculate display seat position of the display target seat; extracts, from a table which registers assigned user information of assigned users of the seats in association with registration seat position of the seats, one piece of the assigned user information registered in association with one piece of the registration seat position which is closest to the display seat position; acquires current activity schedule registered in association with the one piece of the assigned user information; and displays the acquired activity schedule on a display unit.

Abstract: A work machine includes a manipulation device, a surrounding area monitoring device, and a controller. The manipulation device outputs a manipulation signal to operate the work machine. The surrounding area monitoring device serves as a device for detecting whether an object to be recognized is present or not inside a set region that is set in a surrounding area of the work machine. The controller controls the work machine. The controller is capable of switching a setting of an object sensing function between execution and non-execution, the object sensing function being to restrict movement of the work machine when it is detected that the object is present inside the set region. When the manipulation signal is detected in a state where the object sensing function is set at non-execution, the controller switches the setting of the object sensing function to execution.

Abstract: A system and method for real-time monitoring of personal protective equipment (PPE) compliance at a worksite. The system includes a processor, a host memory, a graphical processing unit (GPU), a GPU memory, a storage device, an input device, a plurality of cameras, and a display device. The system creates multiple inference engines and loads input frames from the storage device for pre-processing. The pre-processed frames are processed to obtain annotations and generate an output file. The system also includes a preparatory area and an operations area with cameras configured to capture and transmit video frames. The system can process input frames at a rate of at least 15 frames per second, providing real-time PPE compliance information.

Abstract: A monitoring system for obtaining a video related to medication adherence of a user, includes: a wireless communication device comprising a motion sensor, an ambient light sensor, a first transceiver transmitting data to an external device, and a first controller configured to control the motion sensor, the ambient light sensor, and the first transceiver, the wireless communication device having an attaching portion for being attached to an object containing a medication; and a wearable device including a camera, a second transceiver receiving a signal from the first transceiver, and a second controller configured to obtain video data through the camera based on the signal received through the second transceiver.

Abstract: A system and apparatus are disclosed herein for vehicle to everything (V2X) wireless communication. A V2X wireless transmit/receive unit (WTRU) may receive a vehicle to everything (V2X) message including configuration information and a road side unit (RSU) address. The WTRU may then transmit a message to the RSU according to the configuration information including multimedia broadcast multicast services (MBMS) data. The configuration information may include a MBMS service descriptor. One or more of the V2X messages may include priority information, WTRU type information, or both.

Abstract: A method for 2D semantic keypoint detection and tracking is described. The method includes learning embedded descriptors of salient object keypoints detected in previous images according to a descriptor embedding space model. The method also includes predicting, using a shared image encoder backbone, salient object keypoints within a current image of a video stream. The method further includes inferring an object represented by the predicted, salient object keypoints within the current image of the video stream. The method also includes tracking the inferred object by matching embedded descriptors of the predicted, salient object keypoints representing the inferred object within the previous images of the video stream based on the descriptor embedding space model.

Abstract: A system and method for a videostream is operating correctly. The system decompresses a compressed videostream which includes a compressed graphical timestamp, thereby resulting in a decompressed videostream with a decompressed graphical timestamp, the compressed timestamp and the decompressed graphical timestamp associated with an insert time. The system then renders the decompressed videostream, resulting in a rendered videostream with a rendered graphical timestamp. The system then extracts the rendered graphical timestamp from the rendered videostream at an extract time and determines whether a difference between the insert time of the rendered graphical timestamp and the extract time exceeds a predetermined threshold.

Abstract: An apparatus configured to: receive spatial audio data comprising audio captured from a space extending around a capture device and directional information; receive video imagery captured by a camera, wherein the extent of the space from which the spatial audio data is captured is greater than the field of view of the camera; associate each audio sources determined from the directional information, with, for audio sources within the field of view, a region of the video imagery that corresponds to the direction towards the audio source, and, for audio sources outside the field of view, a part of an out-of-view graphic, the out-of-view graphic indicative of the spatial extent of the space outside the field of view; display the video imagery and the out-of-view graphic; receive user input; and provide for control of at least one audio capture property of a selected one of said one or more audio sources.

Abstract: A method includes detecting a first object in a first area of a scene; determining, based on characteristics of the first object, a first probability value indicating a first probability that the detected first object; detecting a second object in a second area of the scene captured in a second stream of image frames by a second camera of the camera system different from the first camera, wherein the second area at least partly overlaps the first area; determining, based on characteristics of the second object, a second probability value indicating a second probability that the detected second object; and when the second probability value is below a second threshold value and the first probability value is above a first threshold value determining an updated second probability value by increasing the second probability value.

Abstract: A wearable electronic device includes a head-mounted display (HMD) and a retention band connected to the HMD. The retention band can include a display assembly positioned within the retention band for displaying visual information on an exterior of the retention band.

Abstract: A video stream processing method is provided. A first group of coded picture frames in a video stream is received. A storage time and a network request protection time corresponding to the first group are determined. The storage time is an amount of time an intra frame of the first group is stored for transmission to a network node. When a transmission conflict with at least one second terminal occurs in a process of transmitting the intra frame to the network node, a start time of at least a second group of coded picture frames in the video stream is determined according to the storage time and the network request protection time, the second group being after the first group. An intra frame of the second group is transmitted to the network node based on the start time of the second group.

Abstract: A computer-implemented method of obtaining an excursion report for an aircraft is disclosed. The aircraft includes one or more sensors and a vision system, and the method includes obtaining sensor data from the one or more sensors; storing and time-stamping the sensor data; operating the vision system to detect the aircraft leaving a runway or taxiway; recording a start time of an excursion period based on a time of detection of the aircraft leaving the runway or taxiway; operating the vision system to detect the aircraft returning to the runway or taxiway; recording an end time of the excursion period based on a time of detection of the aircraft returning to the runway or taxiway; and compiling an excursion report, the excursion report comprising: the start time of the excursion period, the end time of the excursion period and a subset of the sensor data which was time-stamped during the excursion period.

Abstract: An image processing method and apparatus, a computer device, and a computer-readable storage medium. The image processing method includes: displaying a first application page, the first application page including an original role object and a face fusion control; acquiring a user face image of a target user in a case that the face fusion control is triggered; and displaying a target role object on a second application page, the target role object being obtained by fusing the user face image and the original role object, a display angle of the target role object matching posture information of the target user, and the posture information of the target user being determined according to the user face image.

Abstract: A monitoring unit for security and automation in a premises are described. The monitoring unit uses remote configuration and control to enable monitoring of a premises. The monitoring unit provides multiple monitoring functions to respond to events within the space and alert a user at a remote device like a smartphone. An image sensor provides a wide field of view which can be segmented on the mobile device to enable specific areas to be viewed enabling the user to view the area and be alerted when an event occurs based upon a rules based configuration.

Abstract: An information processing apparatus according to an embodiment of the present technology includes a classification unit and a generation unit. The classification unit classifies an object detected in a space on a basis of a predetermined criterion. The generation unit sets a priority for the object on a basis of a classification result by the classification unit, and generates position-related information regarding a position in the space on a basis of the set priority. Use of the position-related information makes it possible to improve the accuracy of autonomous movement control. This makes it possible to improve the accuracy of autonomous movement control.

Abstract: Methods and apparatus for pet detection in security systems. In one example, a method includes detecting a motion event in a scene using a motion detector, based on detecting the motion event, activating an image capture device to acquire a plurality of images of the scene, applying a motion detection process to the plurality of images to detect motion in the scene, applying an object detection process to at least one of the plurality of images to detect an object in the scene, pairing the motion with the object to locate a moving object, identifying the moving object as a pet, and based at least in part on identifying the moving object as a pet, deactivating the image capture device.

Abstract: A method for sharing surveillance video and receiving payment therefor utilizing a video sharing operator/manager is provided including providing access to video segments created by virtual viewpoint video surveillance camera systems tagged with capture information, providing a connection from each of the camera systems to the video sharing operator/manager and registering sellers of video. The method continues with receiving uploaded capture information on a searchable database from the camera systems and registering buyers. The method continues with receiving a search request from a buyer based on a specific set of capture information and receiving an uploaded requested video segment in response to the search request. The seller receives payment for the video segment from the buyer and, the video segment is downloaded to the buyer.

Abstract: A camera system for a venue including a camera mounted above the venue; a server including artificial intelligence (AI) adapted to follow a subject having a position; the AI adapted to generate aiming instructions based on the position of the subject. The camera being in communication with the server to receive and implement the aiming instructions. The camera system may include a wide area LED light mounted to a light pole. The camera may be mounted to the light pole. The camera system may include wide area LED light is in communication with the server. The wide area LED light produces light at an intensity and the server is adapted to vary the intensity based on the position of the subject.

Abstract: Methods and systems for identifying device positions include measuring radio signal strength information between devices. Inertial information is measured for the devices. The radio signal strength information and the inertial information are fused to determine relative locations between the devices. The relative locations are oriented to a fixed anchor node. Elevation is estimated for the plurality of devices using pressure sensor information.

Abstract: A video encoding/decoding method and apparatus, a computer device, and a storage medium. The method comprises: for each non-key frame in a video frame sequence, dividing a current non-key frame into a plurality of sub-image blocks according to information of an object in the current non-key image, and determining an importance level of each sub-image block; according to a pre-stored first correlation between different importance levels and different resolutions, performing conversion to make each sub-image block in each non-key frame have a resolution corresponding to the importance level of the sub-image block, wherein in the first correlation, a higher importance level corresponds to a higher resolution, and the highest importance level corresponds to a target highest resolution; and performing video encoding on the video frame sequence to obtain encoded video data. By means of the method, memory and bandwidth occupied by a video can be reduced.

Abstract: Systems and methods are disclosed for a shuttle track system having a calibration shuttle for determining portions of the track having non-conforming geometry for optimum use of the shuttle track system. For example, the shuttle track system may include a track having an electromagnetic propulsion system (e.g., linear synchronous motor) embedded between two sides of the track. The calibration shuttle may move to various locations on the track and may use imaging systems for generating image data of a portion of the track. A trained model may process the image data to determine edges and surfaces of the components of the track and may determine distances between reference points on the track. The distances may be compared to threshold values to determine if they are in conformity with desired track geometry.