Abstract: An estimated camera pose may be determined for each of a plurality of single plane images of a designated three-dimensional scene. The sampling density of the single plane images may be below the Nyquist rate. However, the sampling density of the single plane images may be sufficiently high such that the single plane images is sufficiently high such that they may be promoted to multiplane images and used to generate novel viewpoints in a light field reconstruction framework. Scene depth information identifying for each of a respective plurality of pixels in the single plane image a respective depth value may be determined for each single plane image. A respective multiplane image including a respective plurality of depth planes may be determined for each single plane image. Each of the depth planes may include a respective plurality of pixels from the respective single plane image.

Abstract: A respective target viewpoint may be rendered for each of a plurality of multiplane images of a three-dimensional scene. Each of the multiplane images may be associated with a respective single plane image of the three-dimensional scene captured from a respective viewpoint. Each of the multiplane images may include a respective plurality of depth planes. Each of the depth planes may include a respective plurality of pixels from the respective single plane image. Each of the pixels in the depth plane may be positioned at approximately the same distance from the respective viewpoint. A weighted combination of the target viewpoint renderings may be determined, where the sampling density of the single plane images is sufficiently high that the weighted combination satisfies the inequality in Equation (7). The weighted combination of the target viewpoint renderings may be transmitted as a novel viewpoint image.

Abstract: A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

Abstract: Provided are mechanisms and processes for performing skeleton detection and tracking via client-server communication. In one example, a server transmits a skeleton detection message that includes position data for a skeleton representing the structure of an object depicted in a first video frame in a raw video stream at a client device. Based on the initial position data, a processor identifies intervening position data for the skeleton in one or more intervening video frames that are temporally located after the first video frame in the raw video stream. A filtered video stream is then presented by altering the raw video stream based at least in part on the first position data and the intervening position data.

Abstract: A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

Abstract: A system and a method for detecting fraudulent transactions at a transaction site by analyzing pattern of events associated with one or more transactions are provided. The present invention provides for forming a collection of most probable fraudulent patterns and true patterns associated with one or more transactions, selecting a pattern classification technique, generating a data input from an ongoing transaction that is interpretable by the selected pattern classification technique, and effectively and efficiently categorising ongoing transaction into fraudulent and genuine transactions using selected pattern classification technique. The present invention may be utilized in a variety of applications where discrete time-ordered visual events are associated with a transaction, for example: vehicles detected in relation to a transit point, badge or card swipes from an automated door lock etc., which indicate trespassing, theft and unauthorized access to restricted areas etc.

Abstract: Provided are mechanisms and processes for performing visual search using multi-view digital media representations, such as surround views. In one example, a process includes receiving a visual search query that includes a surround view of an object to be searched, where the surround view includes spatial information, scale information, and different viewpoint images of the object. The surround view is compared to stored surround views by comparing spatial information and scale information of the surround view to spatial information and scale information of the stored surround views. A correspondence measure is then generated indicating the degree of similarity between the surround view and a possible match. At least one search result is then transmitted with a corresponding image in response to the visual search query.

Abstract: A system and a method for detecting anomalous activities in a distributed and decentralised network is provided. Anonymous users transacting in the network are identified and one or more transactional attributes are retrieved to define characteristics of users and associated transactional behaviour with other users. Further, user-level statistics are evaluated based on transactional attributes. Datatype representative of transactional behavior of users with other users is generated using user-level statistics of identified users. Users with similar transactional behavior are classified based on generated transactional attributes. One or more anomaly detection techniques are implemented for identifying optimum classification of users into data clusters based on the change detected in the classification of users in data clusters. Anomalous users are identified from the optimum classification for efficiently and effectively detecting anomalous activities in the network.

Abstract: A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

Abstract: Various embodiments are described herein for methods and systems that can be used to track a position of a mobile receiver on a production line. In one example embodiment, the position of the mobile receiver is tracked by receiving at least one information signal from at least one location tag from among a plurality of location tags positioned at fixed locations along the length of a conveyor belt in a production line, by determining a signal strength of the at least one information signal, and by determining the position of the mobile receiver based on the signal strength of the at least one information signal.

Abstract: Machine learning algorithms are applied to OCT scan image data of a patient's retina to assess various eye diseases of the patient, such as ARMD, glaucoma, and diabetic retinopathy. The classification modules for each tested-for disease or condition preferably comprises an ensemble of machine learning algorithms, preferably including both deep learning and traditional machine learning (non-deep learning) algorithms. The results of the analysis can be transmitted back to the facility of the caregiver that used the OCT scanner to scan the patient's retina while the patient is still present at the caregiver's facility for an appointment.

Abstract: Provided are mechanisms and processes for performing visual search using multi-view digital media representations, such as surround views. In one example, a process includes receiving a visual search query that includes a surround view of an object to be searched, where the surround view includes spatial information, scale information, and different viewpoint images of the object. The surround view is compared to stored surround views by comparing spatial information and scale information of the surround view to spatial information and scale information of the stored surround views. A correspondence measure is then generated indicating the degree of similarity between the surround view and a possible match. At least one search result is then transmitted with a corresponding image in response to the visual search query.

Abstract: Various embodiments are described herein for methods and systems that can be used to track a position of a mobile receiver on a production line. In one example embodiment, the position of the mobile receiver is tracked by receiving at least information signal from at least one location tag from among a plurality of location tags positioned at fixed locations along the length of a conveyor belt in a production line, by determining a signal strength of the at least one information signal, and by determining the position of the mobile receiver based on the signal strength of the at least one information signal.

Abstract: Provided are mechanisms and processes for performing live search using multi-view digital media representations. In one example, a process includes receiving a visual search query from a device for an object to be searched, where the visual search query includes a first set of viewpoints of the object obtained during capture of a first surround view of the object during a live search session. Next, additional recommended viewpoints of the object are identified for the device to capture, where the additional recommended viewpoints are chosen to provide more information about the object. A first set of search results based on the first set of viewpoints and additional recommended viewpoints of the object are transmitted to the device. In response, a second set of viewpoints of the object captured using image capture capabilities of the device are received. A second set of search results with enhanced matches for the object based on the first and second sets of viewpoints are then transmitted to the device.

Abstract: Provided are mechanisms and processes for performing live filtering in a camera view via client-server communication. In one example, a first video frame in a raw video stream is transmitted from a client device to a server. The client device receives a filter processing message associated with the first video frame that includes filter data for applying a filter to the first video frame. A processor at the client device creates a filtered video stream by applying the filter to a second video frame that occurs in the video stream later than the first video frame.

Abstract: A system, computer-implemented method and computer program product for determining relevant products for display in an online marketplace is provided. The system comprises a stock categorization module to identify products from an inventory database and categorize each of the identified products. The system further comprises a matrix generator to receive a transaction history of the customers and generate a matrix comprising products purchased by the customers from each of the one or more categories. Furthermore, the system comprises a probability calculator configured to convert the generated matrix into a probability matrix and a clustering module to fetch attributes of each of the one or more products and cluster the customers. In addition, the system comprises a customer questions database to receive one or more preferences from the one or more customers for an instant shopping session and a category list generator to display relevant product assortment corresponding to each customer.

Abstract: A system and a method for detecting anomalous activities in a distributed and decentralised network is provided. Anonymous users transacting in the network are identified and one or more transactional attributes are retrieved to define characteristics of users and associated transactional behaviour with other users. Further, user-level statistics are evaluated based on transactional attributes. Datatype representative of transactional behavior of users with other users is generated using user-level statistics of identified users. Users with similar transactional behavior are classified based on generated transactional attributes. One or more anomaly detection techniques are implemented for identifying optimum classification of users into data clusters based on the change detected in the classification of users in data clusters. Anomalous users are identified from the optimum classification for efficiently and effectively detecting anomalous activities in the network.

Abstract: A system and a method for detecting fraudulent transactions at a transaction site by analyzing pattern of events associated with one or more transactions are provided. The present invention provides for forming a collection of most probable fraudulent patterns and true patterns associated with one or more transactions, selecting a pattern classification technique, generating a data input from an ongoing transaction that is interpretable by the selected pattern classification technique, and effectively and efficiently categorising ongoing transaction into fraudulent and genuine transactions using selected pattern classification technique. The present invention may be utilized in a variety of applications where discrete time-ordered visual events are associated with a transaction, for example: vehicles detected in relation to a transit point, badge or card swipes from an automated door lock etc., which indicate trespassing, theft and unauthorized access to restricted areas etc.

Abstract: Provided are mechanisms and processes for performing live filtering in a camera view via client-server communication. In one example, a first video frame in a raw video stream is transmitted from a client device to a server. The client device receives a filter processing message associated with the first video frame that includes filter data for applying a filter to the first video frame. A processor at the client device creates a filtered video stream by applying the filter to a second video frame that occurs in the video stream later than the first video frame.

Abstract: Provided are mechanisms and processes for performing skeleton detection and tracking via client-server communication. In one example, a server transmits a skeleton detection message that includes position data for a skeleton representing the structure of an object depicted in a first video frame in a raw video stream at a client device. Based on the initial position data, a processor identifies intervening position data for the skeleton in one or more intervening video frames that are temporally located after the first video frame in the raw video stream. A filtered video stream is then presented by altering the raw video stream based at least in part on the first position data and the intervening position data.