Abstract: Described are systems, media, and methods for applying deep convolutional neural networks to medical images to generate a real-time or near real-time diagnosis.

Abstract: A method includes selecting at least two objects within a primary video stream, generating a first video stream from the primary video stream that includes a first of the selected objects, and generating a second video stream from the primary video stream that includes a second of the selected objects. The primary video stream has a primary field of view, and the first and second video streams have respective first and second fields of view that are more narrow than the primary field of view. The first field of view includes a portion of the primary field of view that is not within the second field of view, and the second field of view includes a portion of the primary field of view that is not within the first field of view.

Abstract: A method performed by an electronic device is described. The method includes interleaving multiple input image channels to produce an interleaved multi-channel input. The method also includes loading the interleaved multi-channel input to a single-instruction multiple data (SIMD) processor. The method further includes convolving the interleaved multi-channel input with a multi-channel filter.

Abstract: A method performed by an electronic device is described. The method includes generating a plurality of bounding regions based on an image. The method also includes determining a subset of the plurality of bounding regions based on at least one criterion and a selected area in the image. The method further includes processing the image based on the subset of the plurality of bounding regions.

Abstract: A method performed by an electronic device is described. The method includes interleaving multiple input image channels to produce an interleaved multi-channel input. The method also includes loading the interleaved multi-channel input to a single-instruction multiple data (SIMD) processor. The method further includes convolving the interleaved multi-channel input with a multi-channel filter.

Abstract: A method performed by an electronic device is described. The method includes generating a plurality of bounding regions based on an image. The method also includes determining a subset of the plurality of bounding regions based on at least one criterion and a selected area in the image. The method further includes processing the image based on the subset of the plurality of bounding regions.

Abstract: A method for object classification by an electronic device is described. The method includes obtaining an image frame that includes an object. The method also includes determining samples from the image frame. Each of the samples represents a multidimensional feature vector. The method further includes adding the samples to a training set for the image frame. The method additionally includes pruning one or more samples from the training set to produce a pruned training set. One or more non-support vector negative samples are pruned first. One or more non-support vector positive samples are pruned second if necessary to avoid exceeding a sample number threshold. One or more support vector samples are pruned third if necessary to avoid exceeding the sample number threshold. The method also includes updating classifier model weights based on the pruned training set.

Abstract: Systems, devices and methods for improved tracking with an electronic device are disclosed. The disclosures employ advanced exposure compensation and/or stabilization techniques. The tracking features may therefore be used in an electronic device to improve tracking performance under dramatically changing lighting conditions and/or when exposed to destabilizing influences, such as jitter. Historical data related to the lighting conditions and/or to the movement of a region of interest containing the tracked object are advantageously employed to improve the tracking system under such conditions.

Abstract: A method performed by an electronic device is described. The method includes determining a local motion pattern by determining a set of local motion vectors within a region of interest between a previous frame and a current frame. The method also includes determining a global motion pattern by determining a set of global motion vectors between the previous frame and the current frame. The method further includes calculating a separation metric based on the local motion pattern and the global motion pattern. The separation metric indicates a motion difference between the local motion pattern and the global motion pattern. The method additionally includes tracking an object based on the separation metric.

Abstract: A method of processing data includes receiving, at a computing device, data representative of an image captured by an image sensor. The method also includes determining a first scene clarity score. The method further includes determining whether the first scene clarity score satisfies a threshold, and if the first scene clarity score satisfies the threshold, determining a second scene clarity score based on second data extracted from the data.

Abstract: Systems provided herein include a learning environment and an agent. The learning environment includes an avatar and an object. A state signal corresponding to a state of the learning environment includes a location and orientation of the avatar and the object. The agent is adapted to receive the state signal, to issue an action capable of generating at least one change in the state of the learning environment, to produce a set of observations relevant to a task, to hypothesize a set of action models configured to explain the observations, and to vet the set of action models to identify a learned model for the task.

Abstract: A tracking and recognition system is provided. The system includes a computer vision-based identity recognition system configured to recognize one or more persons, without a priori knowledge of the respective persons, via an online discriminative learning of appearance signature models of the respective persons. The computer vision-based identity recognition system includes a memory physically encoding one or more routines, which when executed, cause the performance of constructing pairwise constraints between the unlabeled tracking samples. The computer vision-based identity recognition system also includes a processor configured to receive unlabeled tracking samples collected from one or more person trackers and to execute the routines stored in the memory via one or more algorithms to construct the pairwise constraints between the unlabeled tracking samples.

Abstract: A method for image scanning by an electronic device is described. The method includes obtaining an image pyramid including a plurality of scale levels and at least a first pyramid level for a frame. The method also includes providing a scanning window. The method further includes scanning at least two of the plurality of scale levels of the frame at a plurality of scanning window locations. A number of scanning window locations is equal for each scale level of the at least two scale levels of the first pyramid level.

Abstract: A method for object classification by an electronic device is described. The method includes obtaining an image frame that includes an object. The method also includes determining samples from the image frame. Each of the samples represents a multidimensional feature vector. The method further includes adding the samples to a training set for the image frame. The method additionally includes pruning one or more samples from the training set to produce a pruned training set. One or more non-support vector negative samples are pruned first. One or more non-support vector positive samples are pruned second if necessary to avoid exceeding a sample number threshold. One or more support vector samples are pruned third if necessary to avoid exceeding the sample number threshold. The method also includes updating classifier model weights based on the pruned training set.

Abstract: A method for detecting and tracking a target includes detecting the target using a plurality of feature cues, fusing the plurality of feature cues to form a set of target hypotheses, tracking the target based on the set of target hypotheses and a scene context analysis, and updating the tracking of the target based on a target motion model.

Abstract: A method performed by an electronic device is described. The method includes determining a haziness confidence level based on multiple modalities. The method also includes determining whether to perform an action based on the haziness confidence level. The method may include performing the action, including performing haziness reduction based on the haziness confidence level.

Abstract: A method for identifying assets is provided. The method includes illuminating an identification pattern associated with the asset with non-visible light. The identification pattern includes retroreflective material that represents identity information of the asset. The method further includes adjusting either a shutter speed of an image sensor, or a power of the non-visible light, or both, based on motion state of the asset. The image sensor is configured to receive response of the retroreflective material to the non-visible light. Furthermore, the method includes the step of identifying the asset based on decoded identity information. The decoded identity information is obtained by processing the response of the retroreflective material.

Abstract: A method includes selecting at least two objects within a primary video stream, generating a first video stream from the primary video stream that includes a first of the selected objects, and generating a second video stream from the primary video stream that includes a second of the selected objects. The primary video stream has a primary field of view, and the first and second video streams have respective first and second fields of view that are more narrow than the primary field of view. The first field of view includes a portion of the primary field of view that is not within the second field of view, and the second field of view includes a portion of the primary field of view that is not within the first field of view.

Abstract: A method includes receiving information that identifies a reference position in a location space. The method also includes receiving data that identifies one among a plurality of candidate geometrical arrangements. The method also includes producing a representation that depicts a plurality of objects which are arranged, relative to the reference position in the location space, according to the identified candidate geometrical arrangement.

Abstract: A method of generating metadata includes using at least one digital image to select a plurality of objects, wherein the at least one digital image depicts the plurality of objects in relation to a physical space. The method also includes, by at least one processor and based on information indicating positions of the selected objects in a location space, producing metadata that identifies one among a plurality of candidate geometrical arrangements of the selected objects.