Abstract: A system and method for optimizing industrial assembly process in an industrial environment is disclosed. A system operates on artificial intelligence (AI) based conversational/GUI platform, where it receives user commands related to industrial assembly process improvement queries. By analyzing received user commands, system identifies type of industrial assembly process mentioned by extracting relevant keywords or other attributes. Using trained AI-based classification table, system determines performance attributes associated with identified type of process. The system leverages various sources such as domain knowledge, organization-specific knowledge bases, data from tools/internet-based services, and statistical measurements from industrial environment.

Abstract: A system and method for learning human activities from video demonstrations using video augmentation is disclosed. The method includes receiving original videos from one or more data sources. The method includes processing the received original videos using one or more video augmentation techniques to generate a set of augmented videos. Further, the method includes generating a set of training videos by combining the received original videos with the generated set of augmented videos. Also, the method includes generating a deep learning model for the received original videos based on the generated set of training videos. Further, the method includes learning the one or more human activities performed in the received original videos by deploying the generated deep learning model. The method includes outputting the learnt one or more human activities performed in the original videos.

Abstract: A computer-implemented method executed by at least one processor for applying rolling shutter (RS)-aware spatially varying differential homography fields for simultaneous RS distortion removal and image stitching is presented. The method includes inputting two consecutive frames including RS distortions from a video stream, performing keypoint detection and matching to extract correspondences between the two consecutive frames, feeding the correspondences between the two consecutive frames into an RS-aware differential homography estimation component to filter out outlier correspondences, sending inlier correspondences to an RS-aware spatially varying differential homography field estimation component to compute an RS-aware spatially varying differential homography field, and using the RS-aware spatially varying differential homography field in an RS stitching and correction component to produce stitched images with removal of the RS distortions.

Abstract: A method for jointly removing rolling shutter (RS) distortions and blur artifacts in a single input RS and blurred image is presented. The method includes generating a plurality of RS blurred images from a camera, synthesizing RS blurred images from a set of GS sharp images, corresponding GS sharp depth maps, and synthesized RS camera motions by employing a structure-and-motion-aware RS distortion and blur rendering module to generate training data to train a single-view joint RS correction and deblurring convolutional neural network (CNN), and predicting an RS rectified and deblurred image from the single input RS and blurred image by employing the single-view joint RS correction and deblurring CNN.

Abstract: A system and method for determining sub-activities in videos and segmenting the videos is disclosed. The method includes extracting one or more batches from one or more videos and extracting one or more features from set of frames associated with the one or more batches. The method further includes generating a set of predicted codes and determining a cross-entropy loss, temporal coherence loss and a final loss. Further, the method includes categorizing the set of frames into one or more predefined clusters and generating one or more segmented videos based on the categorized set of frames, the determined final loss, and the set of predicted codes by using s activity determination-based ML model. The method includes outputting the generated one or more segmented videos on user interface screen of one or more electronic devices associated with one or more users.

Abstract: A system and method for learning human activities from video demonstrations using video augmentation is disclosed. The method includes receiving original videos from one or more data sources. The method includes processing the received original videos using one or more video augmentation techniques to generate a set of augmented videos. Further, the method includes generating a set of training videos by combining the received original videos with the generated set of augmented videos. Also, the method includes generating a deep learning model for the received original videos based on the generated set of training videos. Further, the method includes learning the one or more human activities performed in the received original videos by deploying the generated deep learning model. The method includes outputting the learnt one or more human activities performed in the original videos.

Abstract: A method for improving geometry-based monocular structure from motion (SfM) by exploiting depth maps predicted by convolutional neural networks (CNNs) is presented. The method includes capturing a sequence of RGB images from an unlabeled monocular video stream obtained by a monocular camera, feeding the RGB images into a depth estimation/refinement module, outputting depth maps, feeding the depth maps and the RGB images to a pose estimation/refinement module, the depths maps and the RGB images collectively defining pseudo RGB-D images, outputting camera poses and point clouds, and constructing a 3D map of a surrounding environment displayed on a visualization device.

Abstract: A method is provided in an Advanced Driver-Assistance System (ADAS). The method extracts, from an input video stream including a plurality of images using a multi-task Convolutional Neural Network (CNN), shared features across different perception tasks. The perception tasks include object detection and other perception tasks. The method concurrently solves, using the multi-task CNN, the different perception tasks in a single pass by concurrently processing corresponding ones of the shared features by respective different branches of the multi-task CNN to provide a plurality of different perception task outputs. Each respective different branch corresponds to a respective one of the different perception tasks. The method forms a parametric representation of a driving scene as at least one top-view map responsive to the plurality of different perception task outputs.

Abstract: A system and method for correlating video frames in a computing environment. The method includes receiving first video data and second video data from one or more data sources. The method further includes encoding the received first video data and the second video data using machine learning network. Further, the method includes generating first embedding video data and second embedding video data corresponding to the received first video data and the received second video data. Additionally, the method includes determining a contrastive IDM temporal regularization value for the first video data and the second video data. The method further includes determining temporal alignment loss between the first video data and the second video data. Also, the method includes determining correlated video frames between the first video data and the second video databased on the determined temporal alignment loss and the determined contrastive IDM temporal regularization value.

Abstract: A computer-implemented method for implementing a self-supervised visual odometry framework using long-term modeling includes, within a pose network of the self-supervised visual odometry framework including a plurality of pose encoders, a convolution long short-term memory (ConvLSTM) module having a first-layer ConvLSTM and a second-layer ConvLSTM, and a pose prediction layer, performing a first stage of training over a first image sequence using photometric loss, depth smoothness loss and pose cycle consistency loss, and performing a second stage of training to finetune the second-layer ConvLSTM over a second image sequence longer than the first image sequence.

Abstract: A method for correcting blur effects is presented. The method includes generating a plurality of images from a camera, synthesizing blurred images from sharp image counterparts to generate training data to train a structure-and-motion-aware convolutional neural network (CNN), and predicting a camera motion and a depth map from a single blurred image by employing the structure-and-motion-aware CNN to remove blurring from the single blurred image.

Abstract: A system and method for management and evaluation of one or more human activities is disclosed. The method includes receiving live videos from data sources. The live videos comprises activity performed by human. The activity comprises actions performed by the human. Further, the method includes detecting the actions performed by the human in the live videos using a neural network model. The method further includes generating a procedural instruction set for the activity performed by the human. Also, the method includes validating quality of the identified actions performed by the human using the generated procedural instruction set. Furthermore, the method includes detecting anomalies in the actions performed by the human based on results of validation. Additionally, the method includes generating rectifiable solutions for the detected anomalies. Moreover, the method includes outputting the rectifiable solutions on a user interface of a user device.

Abstract: A method for correcting rolling shutter (RS) effects is presented. The method includes generating a plurality of images from a camera, synthesizing RS images from global shutter (GS) counterparts to generate training data to train the structure-and-motion-aware convolutional neural network (CNN), and predicting an RS camera motion and an RS depth map from a single RS image by employing a structure-and-motion-aware CNN to remove RS distortions from the single RS image.

Abstract: A computer-implemented method executed by at least one processor for applying rolling shutter (RS)-aware spatially varying differential homography fields for simultaneous RS distortion removal and image stitching is presented. The method includes inputting two consecutive frames including RS distortions from a video stream, performing keypoint detection and matching to extract correspondences between the two consecutive frames, feeding the correspondences between the two consecutive frames into an RS-aware differential homography estimation component to filter out outlier correspondences, sending inlier correspondences to an RS-aware spatially varying differential homography field estimation component to compute an RS-aware spatially varying differential homography field, and using the RS-aware spatially varying differential homography field in an RS stitching and correction component to produce stitched images with removal of the RS distortions.

Abstract: A method for jointly removing rolling shutter (RS) distortions and blur artifacts in a single input RS and blurred image is presented. The method includes generating a plurality of RS blurred images from a camera, synthesizing RS blurred images from a set of GS sharp images, corresponding GS sharp depth maps, and synthesized RS camera motions by employing a structure-and-motion-aware RS distortion and blur rendering module to generate training data to train a single-view joint RS correction and deblurring convolutional neural network (CNN), and predicting an RS rectified and deblurred image from the single input RS and blurred image by employing the single-view joint RS correction and deblurring CNN.

Abstract: A system for building computational models of a goal-driven task from demonstration is disclosed. A task recording subsystem receives a recorded video file or recorded sensor data representative of an expert demonstration for a task. An instructor authoring tool generates one or more sub-activity proposals; enables an instructor to specify one or more sub-activity labels upon modification of the one or more sub-activity proposals into one or more sub-tasks. A task learning subsystem learns the one or more sub-tasks represented in the demonstration of the task; builds an activity model to predict and locate the task being performed in the recorded video file. A task evaluation subsystem evaluates a live video representative of the task; generates at least one performance description statistics; identifies a type of activity step executed by the one or more actors; provides an activity guidance feedback in real-time to the one or more actors.

Abstract: A method for improving geometry-based monocular structure from motion (SfM) by exploiting depth maps predicted by convolutional neural networks (CNNs) is presented. The method includes capturing a sequence of RGB images from an unlabeled monocular video stream obtained by a monocular camera, feeding the RGB images into a depth estimation/refinement module, outputting depth maps, feeding the depth maps and the RGB images to a pose estimation/refinement module, the depths maps and the RGB images collectively defining pseudo RGB-D images, outputting camera poses and point clouds, and constructing a 3D map of a surrounding environment displayed on a visualization device.

Abstract: A computer-implemented method for implementing a self-supervised visual odometry framework using long-term modeling includes, within a pose network of the self-supervised visual odometry framework including a plurality of pose encoders, a convolution long short-term memory (ConvLSTM) module having a first-layer ConvLSTM and a second-layer ConvLSTM, and a pose prediction layer, performing a first stage of training over a first image sequence using photometric loss, depth smoothness loss and pose cycle consistency loss, and performing a second stage of training to finetune the second-layer ConvLSTM over a second image sequence longer than the first image sequence.

Abstract: A computer-implemented method, system, and computer program product are provided for a stabilization system utilizing pose estimation in an aerial drone. The method includes receiving, by a pose estimation system, a plurality of images from one or more cameras. The method also includes predicting, by the pose estimation system, a pose from the score map and a combined feature map, the combined feature map correlated from a pair of the plurality of images. The method additionally includes moving, by a propulsion system, the aerial drone responsive to the pose.

Abstract: A computer-implemented method, system, and computer program product are provided for pose estimation. The method includes receiving, by a processor, a plurality of images from one or more cameras. The method also includes generating, by the processor with a feature extraction convolutional neural network (CNN), a feature map for each of the plurality of images. The method additionally includes estimating, by the processor with a feature weighting network, a score map from a pair of the feature maps. The method further includes predicting, by the processor with a pose estimation CNN, a pose from the score map and a combined feature map. The method also includes controlling an operation of a processor-based machine to change a state of the processor-based machine, responsive to the pose.