Gesturelogic Inc.

Bluewrist Inc.

Seyed Ali Etemad

Leonard Maceachern

Mark Klibanov

Roshanak Houmanfar

Adrian Straka

Mohsen Zand

Yangzheng Wu

Kaveh Firouzi

Michael Greenspan

Nick Stupich

Niranjan Iyer

Systems and methods are disclosed that facilitate object pose determination via keypoint detection. A machine learning algorithm is employed to facilitate voting-based estimation of the locations of at least three keypoints. In some example embodiments, the machine learning algorithm is trained, based on reference intensity-depth images of an object, to determine a radial distance between a keypoint and a 3D scene location associated with each pixel. At inference, the algorithm is employed to process an intensity-depth image to determine radial distance estimates for each pixel, and these radial distances are employed to increment an accumulator space, such that a sphere is generated in the accumulator space for each pixel, centered on the 3D scene location, and a keypoint location is determined by a peak in the accumulator space, with multiple keypoints enabling pose determination. The methods are adapted to other imaging modalities, including non-depth images and point cloud datasets.

Systems and methods for pose estimation via radial voting based keypoint localization

Systems, methods and devices for recognizing user activity using data from accelerometer or other sensors. 'Feature-based' approach and 'model-based' approaches are described. In a feature-based approach, various values are extracted from input signals and projected onto a space that is selected to facilitate better segregation of data points. Classifiers identify the regions in this projected space in which the data points fall to distinguish between the different activity types. In a &#x201c;model-based&#x201d; approach, a generative model is trained for each activity type. Different activity types can be distinguished by identifying similarities between the input data with the generative models.

Systems, methods and devices for activity recognition

Systems, methods and devices that facilitate determination of enhanced exercise or physical activity metrics by considering multiple types of data. Metrics are computable by pre-processing, and in some cases segmenting, a variety of input signals, such as acceleration signals, electromyography signals or other signals from a wearable device.

Systems, methods and devices for exercise and activity metric computation

A system, method and device are described for biometric analysis using a wearable device. The device can be removeably securable to a user's skin surface and can include a plurality of electrodes positioned to acquire electrical signals from the skin surface. The device can also include an electromyography acquisition module and skin impedance acquisition module. A processing unit can use the electrodes to capture a plurality of electrical signals including at least one electromyography signal. The processing unit can generate calibration data based on a subset of the captured electrical signals and process the electromyography signals using the calibration data to determine a biometric for the user.

Systems, methods and devices for acquiring and processing physiological signals

A system, method and device are described for detecting a heart rate. A sensing unit can have a skin-facing surface that is removably securable to a user's skin surface and include at least one sensor positioned to acquire a bio-signal from the skin surface. A controller can be configured to capture a bio-signal stream using the at least one sensor and generate a preprocessed bio-signal stream by band-pass filtering the captured bio-signal stream with a predetermined passband. The controller can also be configured to determine, in a moving window, heartbeat signal portions when the preprocessed bio-signal stream has heartbeat impulse characteristics and determine the time between adjacent heartbeat signal portions to compute the heart rate.

Growing community of inventors

Ottawa, Canada

Seyed Ali Etemad