Abstract: Systems and methods are disclosed for processing an electronic image corresponding to a specimen. One method for processing the electronic image includes: receiving a target electronic image of a slide corresponding to a target specimen, the target specimen including a tissue sample from a patient, applying a machine learning system to the target electronic image to determine deficiencies associated with the target specimen, the machine learning system having been generated by processing a plurality of training images to predict stain deficiencies and/or predict a needed recut, the training images including images of human tissue and/or images that are algorithmically generated; and based on the deficiencies associated with the target specimen, determining to automatically order an additional slide to be prepared.

Abstract: Provided herein are methods and systems for making patient-specific therapy recommendations of a combination of any two or more therapies selected from a lipid-lowering therapy, an anti-inflammatory therapy for patients with known or suspected cardiovascular disease, such as atherosclerosis.

Abstract: Risk prediction models are trained and deployed to analyze images, such as computed tomography scans, for predicting future risk of lung cancer for one or more subjects. Individual risk prediction models are separately trained on nodule-specific and non-nodule specific features such that each risk prediction model can predict future risk of lung cancer across different time periods (e.g., 1 year, 3 years, or 5 years). Such risk prediction models are useful for developing preventive therapies for lung cancer by enabling clinical trial enrichment.

Abstract: Systems and methods are provided for aiding the detection and diagnosis of critical heart defects during fetal ultrasound examinations, in which motion video clips are analyzed with machine learning algorithms to identify and select within the motion video clips image frames that correspond to standard views recommended by fetal ultrasound guidelines, and selected image frames are analyzed with machine learning algorithms to detecting and identify morphological abnormalities indicative of critical CHDs associated with the standard views. The results of the analyses are presented for review to the clinician with an overlay for the selected image frames that identifies the abnormalities with graphical or textual indicia. The overlay further may be annotated by the clinician and stored to create documentary record of the fetal ultrasound examination.

Abstract: Systems and methods are configured to extract images from provided source data files and to preprocess such images for content-based image analysis. An image analysis system applies one or more machine-learning based models for identifying specific features within analyzed images, and for determining one or more measurements based at least in part on the identified features. Such measurements may be embodied as absolute measurements for determining an absolute distance between features, or relative measurements for determining a relative relationship between features. The determined measurements are input into one or more machine-learning based models for determining a classification for the image.

Abstract: A method, a program, and a method determining hypermutated type cancer with higher accuracy than before is provided.

Abstract: A system for determining the viability of an embryo comprises an imaging device, an excitation device configured to direct an excitation energy at an embryo, a controller communicatively connected to the imaging device and the excitation device, configured to drive the excitation device and collect images from the imaging device at an imaging frequency, a processor performing steps comprising acquiring a set of images from the imaging device, performing a Fourier Transformation to generate a set of phasor coordinates, computing a D-trajectory, computing a set of values of additional parameters, comparing the set of values to a set of stored values related to embryos of known viability, and calculating a viability index factor of the embryo from the set of values and the set of stored values. Methods of calculating embryo viability and determining one or more properties of a tissue are also described.

Abstract: According to some embodiments, a system and method are provided comprising a vegetation module to receive image data from an image source; a memory for storing program instructions; a vegetation processor, coupled to the memory, and in communication with the vegetation module, and operative to execute program instructions to: receive image data; estimate a vegetation segmentation mask; generate at least one of a 3D point cloud and a 2.5D Digital Surface Model based on the received image data; estimate a relief surface using a digital terrain model; generate a vegetation masked digital surface model based on the digital terrain model, the vegetation segmentation mask and at least one of the 3D point cloud and the 2.

Abstract: A method includes: inputting an image of a target to each of a first model for estimating a region of an annular face of the target, a second model for estimating a region in an outer circumference of the annular face and a third model for estimating a region in an inner circumference of the annular face, and outputting a region image, as an estimated region of the annular face, the region image being obtained by synthesizing first, second, and third elements. The first element is a region outputted as a result of the first model for calculating a sum set in the synthesizing, the second element is a region outputted as a result of the second model for calculating a sum set in the synthesizing, and the third element is a region outputted as a result of the third model for calculating a difference set in the synthesizing.

Abstract: Embodiments of this disclosure include a method and an apparatus for processing image. The method may include obtaining a to-be-processed image and performing image semantic segmentation on the to-be-processed image to obtain a semantically-segmented image. The semantically-segmented image may include a target region and a non-target region obtained through the semantic segmentation. The method may further include performing pose recognition on the to-be-processed image, to obtain a pose-recognized image recognizing skeletal region. The method may further include fusing the target region and the non-target region of the semantically-segmented image with the skeletal region of the pose-recognized image, to obtain a trimap comprising foreground region, background region, and recognition region. The method may further include generating, according to the to-be-processed image and the trimap, a transparency mask image for separating image from the to-be-processed image.

Abstract: A target object controlling method, apparatus (2), electronic device, and storage medium. The method includes in response to a movement control operation triggered for a target object in a real scene image, determining a control direction corresponding to the movement control operation (101); obtaining a photographing direction of the real scene image (102); and controlling the target object to move in the real scene image according to the control direction and the photographing direction (103). The target object controlling method can effectively solve the problem in the prior art that when the photographing direction of the real scene image changes, a direction deviation occurs in controlling the target object to move in the real scene image, and can also effectively improve the operation performance of the target object in the real scene image, bringing a better manipulation experience for a user.

Abstract: In order to extract a foreground area more appropriately, an image processing apparatus for extracting a foreground area from an inputted image includes an image input unit that sets a first area and a second area different from the first area in the inputted image, a first extraction unit that extracts a foreground area from the first area, and a second extraction unit that extracts a foreground area from the second area by using an extraction method different from an extraction method used by the first extraction unit.

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: The present invention generally relates to a technology of detecting a stationary object in a static video, i.e., a video which is generated by a camera with a fixed view, such as a CCTV video. More specifically, the present invention relates to a technology of identifying a stationary object by use of inference information (Tensor, Activation Map) of Deep Learning object detector among objects which have been detected in a static video such as a CCTV video. According to the present invention, it is possible to lower the priority of stationary objects (e.g., parked vehicles) in processing a static video so that computing resource of the video analysis system can be effectively utilized in the process after object detection so as to enhance the performance of image analysis.

Abstract: An object tracking device includes a storage unit that stores in advance a reference for a movement amount of an object between frames for each position or area on a fisheye image, a determining unit that determines, based on a position of the object in a first frame image and the reference for a movement amount associated with the position of the object in the first frame image, a position of a search area in a second frame image subsequent to the first frame image, and a search unit that searches the search area in the second frame image for the object to specify a position of the object in the second frame image.

Abstract: A ML model arrangement configured for evaluating motion patterns in a sequence of image data structures is described. The ML model arrangement comprises a first ML model configured for predicting a set of key data elements for each image data structure of the sequence of image data structures, a key data element indicating a respective position of a landmark in the image data structure. The ML model arrangement further comprises at least one second ML model, each second ML model being a ML model configured for evaluating a corresponding specific motion pattern. Each second ML model is configured for determining, based on input data comprising at least one of the key data elements predicted for at least one image data structure or data derived therefrom, class labels for each image data structure, said class labels identifying at least one of: at least one motion phase of the specific motion pattern, at least one evaluation point of the specific motion pattern.

Abstract: Disclosed systems and methods can include capturing the sequence of images of a monitored region that includes a sub-region of interest, processing the sequence of images using heuristics and rules of an artificial intelligence model to identify the plurality of discrete parts that are associated with a type of a unified entity, and processing the sequence of images using the heuristics and the rules of the artificial intelligence model to virtually link together a group of the plurality of discrete parts that correspond to a specific embodiment of the unified entity that is present in the sub-region of interest, wherein the heuristics and the rules of the artificial intelligence model can be developed from a training process that includes the artificial intelligence model receiving sample images delineating exemplary discrete parts on exemplary embodiments of the unified entity.

Abstract: The present disclosure provides a method and system for processing multi-modality images. The method may include obtaining multi-modality images; registering the multi-modality images; fusing the multi-modality images; generating a reconstructed image based on a fusion result of the multi-modality images; and determining a removal range with respect to a focus based on the reconstructed image. The multi-modality images may include at least three modalities. The multi-modality images may include a focus.

Abstract: Provided is a dental image registration device comprising: an outermost boundary detection unit for detecting, from first teeth image data, a first outermost boundary region which is the outermost boundary region of dentition, and detecting, from second teeth image data, a second outermost boundary region which is the outermost boundary region of the dentition; and an image registration unit which registers the first and second teeth image data on the basis of a first inscribed circle inscribed within the first outermost boundary region and a second inscribed circle inscribed within the outermost boundary region, or registers the first and second teeth image data on the basis of a first central point of the first outermost boundary region and a second central point of the second outermost boundary region.

Abstract: Image pair co-registration systems and methods include receiving a pair of multi-modal images, defining a parametric deformation model, defining a loss function that is minimized when the pair of images are aligned, and performing a multi-scale search to determine deformation parameters that minimize the loss function. The optimized deformation parameters define an alignment of the pair of images. The pair of images may include visible spectrum image and an infrared image. The method further includes resizing the visible spectrum image to match the infrared image, applying at least one lens distortion correction model, and normalizing a dynamic range of each of the pair of images. The multi-scale search may further include resizing the pair of images to a current processing scale, applying adaptive histogram equalization to the pair of images to generate equalized images, applying Gaussian Blur to the equalized images, and optimizing the deformation parameters.

Abstract: Systems and methods of the present disclosure can facilitate determining a three-dimensional surface representation of an object. In some embodiments, the system includes a computer, a calibration module, which is configured to determine a camera geometry of a set of cameras, and an imaging module, which is configured to capture spatial images using the cameras. The computer is configured to determine epipolar lines in the spatial images, transform the spatial images with a collineation transformation, determine second derivative spatial images with a second derivative filter, construct epipolar plane edge images based on zero crossings of second derivative epipolar planes image based on the epipolar lines, select edges and compute depth estimates, sequence the edges based on contours in a spatial edge image, filter the depth estimates, and create a three-dimensional surface representation based on the filtered depth estimates and the original spatial images.

Abstract: A system and method are described herein for controlling optical power provided to one or more laser projectors of an image capture device, such as a stereo camera, for improving depth image acquisition and quality while adhering to eye safety standards based on laser emissions. The system includes one or more laser projectors operable to emit a laser dot pattern onto a scene, and image capture devices operable to capture images from the scene including the laser dot pattern. The images are analyzed to acquire depth information for objects in the scene, and the depth information is used to modulate the optical power of the laser projectors based on the distance to the object relative to the image capture device.

Abstract: Methodology of unwrapping of phase from an optical image in the presence of both noise and unreliable phase fringes configured to tackle both problems simultaneously and, in the most efficient of multiple related implementations, including at least three prongs: i) SD-ROM based denoising procedure, ii) reliable estimation of the gradient of both the wrapped and unwrapped phase with the use of the forward and inverse Laplacian operators; and iii) fringe quality improvement with the use of Fuzzy Logic based Edge Detection. Transformation of optical images with the use of such methodology to provide an image representing visually-perceivable representation of the object's shape. Computer program product configured to implement the same.

Abstract: The present disclosure relates to methods, apparatuses, and computer programs for processing computed tomography images. Precise segmentation of the left atrium (LA) in computed tomography (CT) images constitutes a crucial preparatory step for catheter ablation in atrial fibrillation (AF). We aim to apply deep convolutional neural networks (DCNNs) to automate the LA detection/segmentation procedure and create a three-dimensional (3D) geometries. The deep learning provides an efficient and accurate way for automatic contouring and LA volume calculation based on the construction of the 3D LA geometry. Non-pulmonary vein (NPV) trigger has been reported as an important predictor of recurrence post atrial fibrillation (AF) ablation. Elimination of NPV triggers can reduce the post-ablation AF recurrence. The deep learning was applied in pre-ablation pulmonary vein computed tomography (PVCT) geometric slices to create a prediction model for NPV triggers in patients with paroxysmal atrial fibrillation (PAF).

Abstract: A returned goods processing system may include a camera configured to acquire human pose image data of a given user while processing a returned item. The system may also include a returned goods processing server configured to store reference human pose image data of sample users while processing returned items. The stored human pose image data may be indicative of compliance with an acceptable return processing procedure. The returned good processing server may also be configured to compare the acquired human pose image data with the stored reference human pose image data to determine compliance with the acceptable return processing procedure, and generate a notification based upon the comparing. The returned goods processing server may also be configured to perform machine learning to update the stored reference human pose image data based upon the acquired human pose image data.

Abstract: A method for proposing a location of a display device, includes: scanning, by an augmented reality device, an indoor space; receiving, by the augmented reality device, viewing environment information including viewing space information, viewing time information and viewing content information to the augmented reality device; and proposing, by the augmented reality device, an optimal location/type of the display device.

Abstract: Neural stimulation is provided according to a closed loop algorithm to treat sleep disordered breathing (SOB), including obstructive sleep apnea (OSA). The closed loop algorithm is executed by a system comprising a processor (which can be within the neural stimulator). The closed loop algorithm includes monitoring physiological data (e.g., EMG data) recorded by a sensor implanted adjacent to an anterior lingual muscle; identifying a trigger within the physiological data, wherein the trigger is identified as a biomarker for a condition related to sleep (e.g., inspiration); and applying a rule-based classification (which can learn) to the trigger to determine whether one or more parameters of a stimulation should be altered based on the biomarker.

Abstract: A method of training a video object detection model by using a training dataset is provided, including steps of: a learning device (a) after acquiring a training image (i) inputting the training image and first prior information, set as having probabilities of objects existing in locations in the training image, into the video object detection model, to thereby detect the objects and thus output first object detection information, and (ii) generating second prior information, which includes location information of the objects on the training image; (b) inputting the training image and the second prior information into the video object detection model, to detect the objects on the training and thus output second object detection information; and (c) generating a loss by referring to the second object detection information and a ground truth corresponding to the training image, and train the video object detection model to minimize the loss.

Abstract: An electronic device including a display; a distance sensor; a camera; and at least one processor configured to: obtain a two-dimensional (2D) face image of a user via the camera and obtain distance sensing data via the distance sensor; identify a distance between the user and the electronic device, and a rotation angle of a face of the user with respect to the electronic device, using the obtained 2D face image and the obtained distance sensing data; modify at least a part of the 2D face image based on at least one of the identified distance and the identified rotation angle; and provide information about at least the part of the modified 2D face image via the display.

Abstract: A navigation system for one or more vehicles located within a control volume includes: a first camera configured to observe the one or more vehicles and first, second and third reference points disposed within the control volume and having first, second and third known spatial positions, respectively, the first camera being further configured to produce a first output signal from observation of the observed vehicles and reference points; a second camera configured to observe the one or more vehicles and the first, second and third reference points, the second camera being further configured to produce a second output signal from observation of the observed vehicles and reference points; and a processor operatively connected with the first and second cameras and configured to determine a respective spatial position for each of the one or more vehicles from the first and second output signals.

Abstract: A non-transitory computer readable storage medium storing computer readable instructions executable by a computer is provided. The computer readable instructions cause the computer to obtain first image data composing a first image and second image data composing a second image, specify first edge pixels in the first image using the first image and second edge pixels in the second image using the second image data, determine positional relation between the first image and the second image in a first degree of accuracy, based on positional relation between the first edge pixels and the second edge pixels, determine first usable pixels among the first edge pixels and the second usable pixels among the second edge pixels, and using the first usable pixels and the second usable pixels, determine positional relation between the first image and the second image in a second degree of accuracy being higher than the first degree.

Abstract: A computer-implemented medical method of determining the position of an anatomical region of interest of a patient's body is provided. The method includes acquiring finger model data, acquiring finger position data based on the finger model data and based on imaging the at least one finger, acquiring planning image data that describes a planning external surface of the anatomical region of interest, and determining anatomical region position data based on the finger position data and the planning image data, wherein the finger model data describes a user-specific model of the pose which is acquired by imaging the at least one finger when it attains the pose.

Abstract: An image processing apparatus 10 includes a learning model construction unit 11 that generates a divided space(s) obtained by dividing a target space into one or more spaces and constructs a learning model for recognizing an object(s) included in the divided space, a learning model management unit 12 that manages the learning model and a region forming the divided space including the object recognized by the learning model in association with each other, a space estimation unit 13 that estimates a region forming a camera recognition space captured by a camera provided in a UI device; and a detection unit 14 that selects, from among the managed learning models, a specific learning model associated with the region forming the divided space including the estimated region forming the camera recognition space, and to detect the object included in a space displayed on the UI device using the selected specific learning model.

Abstract: A system and/or method for imaging system calibration, including: determining a dense correspondence map matching features in a first image to features in a second image, and determining updated calibration parameters associated with the image acquisition system based on the matching features.

Abstract: An inspection support system for erroneous attachment includes an imaging device and an erroneous attachment detector. The imaging device is configured to capture an image that represents a state in which multiple components are attached to each other. The erroneous attachment detector is configured to convert a color space of the image into an HSV color space, create a comparative image on the basis of hue and saturation in the HSV color space, determine whether the multiple components are each a correct component and whether the multiple components are attached in a correct manner by comparing the comparative image with a correct image that is based on the hue and the saturation, and detect the erroneous attachment of at least one of the multiple components, in a case where the at least one of the multiple components is not the correct component and/or is not attached in the correct manner.

Abstract: A G-PCC coder is configured to receive the point cloud data, determine a final quantization parameter (QP) value for the point cloud data as a function of a node QP offset multiplied by a geometry QP multiplier, and code the point cloud data using the final QP value to create an coded point cloud.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.

Abstract: Provided are methods and apparatus for creating super-compressed map files. Using free and open-source software (FOSS), the tool create a super-compressed internally tiled Geo Tag Image File Format (TIFF) in a WGS84 datum (WGS84) similar in size to the original LizardTech's MrSID (SID) imagery from the National Geospatial-Intelligence Agency (NGA). Converting NGA data to WGS84 allows mapping systems like NASA Worldwind (WW) to eliminate the step of re-projecting on the fly from non-native projections, thus reducing processing time. The disclosed method includes removing all pure-black pixels by setting them to black+1, changing all near-black border pixels with values less than 15 to 0 (pure black), setting pure black values to “no-data,” compressing the image with a compression scheme, and translating the compressed image to JPEG and a YCbCr color space to achieve greater compression.

Abstract: An example method includes receiving (502) a plurality of points that represent a point cloud; representing a position of the point in each dimension of a three-dimensional space as a sequence of bits (504), where the position of the point is encoded according to a tree data structure; partitioning (506) at least one of the sequences of bits into a first portion of bits and a second portion of bits; quantizing (508) each of the second portions of bits according to a quantization step size, where the quantization step size is determined according to an exponential function having a quantization parameter value as an input and the quantization step size as an output; and generating (510) a data structure representing the point cloud and including the quantized second portions of bits.

Abstract: A method and a system for establishing a light source information prediction model are provided. A plurality of training images are captured for a target object. A white object is attached on the target object. True light source information of the training images is obtained according to a color of the white object in each of the training images. A neural network model is trained according to the training images and the true light source information, and a plurality of pieces of predicted light source information is generated according to the neural network model during the training. A learning rate for training the neural network model is adaptively adjusted based on the predicted light source information.

Abstract: An imaging device and an authentication controller are provided. The imaging device includes a modulator that includes a first pattern and that modulates light intensity with the first pattern, an image sensor that converts a light beam transmitted through the modulator into imaging data and outputs the imaging data, an image processing unit that performs, to the imaging data, a reconstruction process in which an image of the subject is reconstructed based on the cross-correlation operation between the imaging data and the pattern data having a second pattern and acquires an image, and a distance measurement unit that repeats the reconstruction process to the imaging data while changing a focus distance and acquires a focus distance having a highest contrast in a measurement region as a distance. The authentication controller performs image authentication and distance authentication using image data and distance data acquired by the imaging device.

Abstract: A computer readable recording medium storing at least one program, wherein an image pattern determining method for determining a stripe image can be performed when the program is executed. The image pattern determining method comprises: (a) classifying a single target image to a plurality of image blocks, wherein each of the image blocks comprises at least one pixel; (b) calculating pixel differences between pixel value sums of at least one of the image blocks and neighboring image blocks of the image block; (c) calculating image variation levels of each of the image blocks in a plurality of directions according to the pixel differences; and (d) determining whether the single target image comprises the strip image or not according to the image variation levels. An image pattern determining method for determining a check board image is also disclosed.

Abstract: Image recognition may include obtaining a first image, segmenting the first image into a plurality of first regions by using a target model, and searching for a target region among bounding boxes in the first image that use points in the first regions as centers. The target region is a bounding box in the first image in which a target object is located. The target model is a pre-trained neural network model configured to recognize from an image, a region in which the target object is located. The target model is obtained through training by using positive samples with a region in which the target object is located marked and negative samples with a region in which a noise is located marked. The target region is marked in the first image to improve accuracy of target object detection in an image.

Abstract: A method of generating an image recognition model for recognising an input image and a system thereof are provided. The method includes appending at least one feature extraction layer to the image recognition model, extracting a plurality of feature vectors from a set of predetermined images, grouping the plurality of feature vectors into a plurality of categories, clustering the plurality of feature vectors of each of the plurality of categories into at least one cluster, determining at least one centroid for each of the at least one cluster, such that each of the at least one cluster comprises at least one centroid, such that each of the at least one centroid is represented by a feature vector, generating a classification layer based on the feature vector of the at least one centroid of the plurality of categories, and appending the classification layer to the image recognition model. In addition, a method of classifying an input image and a system thereof are provided.

Abstract: A method of training a fingerprint image enhancing engine for use in a fingerprint capturing device, and a corresponding apparatus and computer readable medium, include producing a synthetic image dataset comprising plural pairs of synthetic images. Each pair of synthetic images include a clean synthetic image and a raw synthetic image corresponding to the clean synthetic image. Each raw synthetic image is produced according to a model of the fingerprint capturing device. The method also includes training a neural network using the synthetic image dataset.

Abstract: A computer-implemented method of forecasting the semantic output of at least one frame, the method comprising the steps of receiving the input frames from a camera up to a predetermined time, processing via a down-sampling module of a neural network the plurality of input frames to receive a plurality of feature tensors, determining spatio-temporal correlations between the plurality of feature tensors, processing the plurality of feature tensors and the spatio-temporal correlations to receive at least one forecasted feature tensor, and processing via an up-sampling module of the neural network the at least one forecasted feature to receive at least one forecasted semantic output for a time larger than the predetermined time.

Abstract: A method includes detecting a user input comprising an incomplete three-dimensional (3D) gesture performed by one or more hands of a first user by a virtual-reality (VR) headset, selecting candidate 3D gestures from pre-defined 3D gestures based on a personalized gesture-recognition model, wherein each of the candidate 3D gestures is associated with a confidence score representing a likelihood the first user intended to input the respective candidate 3D gesture, and presenting one or more suggested inputs corresponding to one or more of the candidate 3D gestures at the VR headset.

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: There is provided an imaging system. The imaging system comprising a multispectral camera configured to capture a multispectral image of an object, an RGB camera configured to capture a color image of the object, at least one storage device configured to store spectrum information for each of a plurality of labeled objects, and processing circuitry. The processing circuitry is configured to determine, based on the captured multispectral image, spectrum information associated with the object, associate, based at least in part, on the spectrum information associated with the object and the stored spectrum information for each of the plurality of objects, a label with the color image of the object, and store, on the at least one storage device, the color image and the associated label as training data.

Abstract: A method is provided for controlling a movable imaging assembly having a movable platform and an imaging device coupled to and movable relative to the movable platform. The method includes receiving user inputs that define an MIA position relative to a target and a frame position of the target within image frames captured by the imaging device. The user inputs include a horizontal distance, a circumferential position, and a horizontal distance that define the MIA position, and include a horizontal frame position and a vertical frame position that define the frame position. The method further includes predicting a future position of the target for a future time, and moving the MIA to be in the MIA position at the future time and moving the imaging device for the target to be in the frame position for an image frame captured at the future time.