Navigation of a mobility aid robot having a camera and gripping part(s) disposed toward different directions is disclosed. The mobility aid robot is navigated to approach a user by identifying a posture of the user through the camera, determining a mode of the robot according to a type of the specified task to be performed on the user and the identified posture of the user, controlling the robot to move according to a planned trajectory corresponding to the determined mode of the robot, and turning the robot upon reaching the desired pose such that the gripping part faces the user, in response to the determined mode of the robot corresponding to the specified task of an assisting type and the user at one of a standing posture and a sitting posture.

A method and system to determine the position of a moveable platform relative to an object is disclosed. The method can include storing one or more synthetic models each trained by one of the one or more synthetic model datasets corresponding to one or more objects in a database; capturing an image of the object by one or more sensors associated with the moveable platform; identifying the object by comparing the captured image of the object to the one or more synthetic model datasets; generating a first model output using a first synthetic model of the one or more synthetic models, the first model output including a first relative coordinate position and a first spatial orientation of the moveable platform; and generating a platform coordinate output and a platform spatial orientation output of the moveable platform at the first position based on the first model output.

This application provides a method for evaluating a motion state of a vehicle performed by a computer device. The method includes: obtaining target image data captured by cameras on the vehicle, and combining every two neighboring image frames in the target image data into N image frame groups; obtaining matching feature points between two image frames included in each of the N image frame groups; constructing target mesh plane figures respectively corresponding to the N image frame groups according to the matching feature points in each image frame group; and determining the motion state of the vehicle according to the target mesh plane figures respectively corresponding to the N image frame groups. By adopting the embodiments of this application, the evaluation accuracy of the motion state of the vehicle may be improved.

A method of performing movement pattern anomaly detection with targeted alerts can include receiving input from each camera of a multi-camera system and for each input: performing video content analysis; generating a critical analysis matrix associated with the input from that camera; assigning a fusion value for each vector of the critical analysis matrix using a fusion map that indicates particular fusion values associated with possible elements of the critical analysis matrix; and triggering an alert according to whether the fusion value exceeds a threshold associated with that camera. The critical analysis matrix includes output from at least two different computer vision algorithms of the video content analysis applied to the input from a camera.

A 3D bounding box reconstruction method includes obtaining masks corresponding to a target object in images, obtaining a trajectory direction of the target object according to the masks, generating a target contour according to one of the masks, transforming the target contour into a transformed contour using a transformation matrix, obtaining a first bounding box according to the transformed contour and the trajectory direction, transforming the first bounding box into a second bounding box corresponding to the target contour using the transformation matrix, obtaining first reference points according to the target contour and the second bounding box, transforming the first reference points into second reference points using the transformation matrix, obtaining a third bounding box using the second reference points, transforming the third bounding box into a fourth bounding box using the transformation matrix, and obtaining a 3D bounding box using the second bounding box and the fourth bounding box.

The technology disclosed relates to relates to providing command input to a machine under control. It further relates to gesturally interacting with the machine. The technology disclosed also relates to providing monitoring information about a process under control. The technology disclosed further relates to providing biometric information about an individual. The technology disclosed yet further relates to providing abstract features information (pose, grab strength, pinch strength, confidence, and so forth) about an individual.

System and methods are provided for providing a dynamically-updated musculoskeletal representation of a hand. The system includes a plurality of neuromuscular sensors configured to continuously record a plurality of neuromuscular signals from a user, and at least one computer processor programmed to provide as input to a trained statistical model, the plurality of neuromuscular signals and temporally smooth in real-time an output of the trained statistical model. The system is also programmed to determine, based on the smoothed output of the trained statistical model, position information describing a spatial relationship between two or more connected segments of the musculoskeletal representation, force information describing a force exerted by at least one segment of the musculoskeletal representation, and update the musculoskeletal representation of the hand based, at least in part, on the position information and the force information.

A sensor simulation system may generate sensor data for use in simulations by rendering two-dimensional views of a three-dimensional simulated environment. In various examples, the sensor simulation system uses sensor dependency data to determine specific views to be re-rendered at different times during the simulation. The sensor simulation system also may generate unified views with multi-sensor data at each region (e.g., pixel) of the two-dimensional view for consumption by different sensor types. A hybrid technique may be used in some implementations in which rasterization is used to generate a view, after which ray tracing is used to align the view with a particular sensor. Spatial and temporal upsampling techniques also may be used, including depth-aware and velocity-aware analyses for simulated objects, to improve view resolution and reduce the frequency of re-rendering views.

In various embodiments, a map inference application automatically maps a user space. A camera is positioned within the user space. In operation, the map inference application determines a path of a first moving object within the user space based on a tracking dataset generated from images captured by the camera. Subsequently, the map inference application infers a walking space within the user space based on the path. The map inference application then generates a model of at least a portion of the user space based on the walking space. One or more movements of a second object within the user space are based on the model. Advantageously, unlike prior art solutions, the map inference application enables a model of a user space to be automatically and efficiently generated based on images from a single stationary camera.

Methods and systems are provided for tracking anatomical features across multiple images. One example method includes outputting, for display on a display device, an annotation indicative of a first location of an identified anatomical feature of a first ultrasound image, the annotation generated based on a first output of a model and outputting, for display on the display device, an adjusted annotation based on a second output of the model, the second output of the model generated based on a second ultrasound image and further based on the first output of the model, the adjusted annotation indicative of a second location of the identified anatomical feature in the second ultrasound image.