Wisconsin Alumni Research Foundation

Boston University

Kinevid, Llc.

Yu Hen Hu

Robert Radwin

Xuan Wang

Truong Q Nguyen

Nicholas Difranco

Chia-Hsiung Chen

Nigel Boston

Runyu L Greene

Seyfullah H Oguz

Thomas Y Yen

Seungjoon Yang

Damon L Tull

Trac D Tran

Wei-Yang Lin

A monitoring or tracking system may include an input port and a controller in communication with the input port. The input port may receive data from a data recorder. The data recorder is optionally part of the monitoring system and in some cases includes at least part of the controller. The controller may be configured to receive data via the input port and determine values for one or more dimensions of subject performing a task based on the data and determine a location of a hand of the subject performing the task based on the data. Further, the controller may be configured to determine one or both of trunk angle and trunk kinematics based on the received data. The controller may output via the output port assessment information.

Movement monitoring system

A monitoring system or tracking system may include an input port and a controller in communication with the input port. The input port may receive video from one or more image capturing devices. The image capturing device is optionally part of the monitoring system and in some cases includes at least part of the controller. The controller may be configured to receive video via the input port and identify a subject within frames of the video relative to a background within the frames. Further, the controller may be configured to identify dimensions, posture, hand location, feet location, twisting position/angle, and/or other parameters of the identified subject in frames of the video and determine when the subject is performing a task. Based on the dimensions and/or other parameters identified or extracted from the video during the predetermined task, the controller may output via the output port assessment information.

A monitoring system or tracking system may include an input port and a controller in communication with the input port. The input port may receive video from an image capturing device. The image capturing device is optionally part of the monitoring system and in some cases includes at least part of the controller. The controller may be configured to receive video via the input port and identify a subject within frames of the video relative to a background within the frames. Further, the controller may be configured to identify dimensions, posture, hand location, feet location, and/or other parameters of the identified subject in frames of the video and determine when the subject is performing a task. Based on the dimensions and/or other parameters identified or extracted from the video during the predetermined task, the controller may output via the output port assessment information.

A monitoring system may include an input port, an output port, and a controller in communication with the input port and the output port. The input port may receive video from an image capturing device. The image capturing device is optionally part of the monitoring system and in some cases includes at least part of the controller. The controller may be configured to receive video via the input port and identify a subject within frames of the video relative to a background within the frames. Further, the controller may be configured to identify dimensions and/or other parameters of the identified subject in frames of the video and determine when the subject is performing a predetermined task. Based on the dimensions and/or other parameters identified or extracted from the video during the predetermined task, the controller may output via the output port assessment information.

Provided herein are systems and methods that use a video content analysis algorithm to measure and quantify repetitive motion activity of a designated body part, including velocity, acceleration, frequency, and duty cycle, without applying sensors or other instrumentation to the body, for the purpose of preventing repetitive motion injuries. In some embodiments, the video-based direct exposure assessment system uses marker-less video and a video content analysis algorithm. The video content analysis algorithm is able to recognize and identify the pattern of repetitive motion, through a process known as cyclic motion analysis. Determination of the cycle pattern provides parameters for determining a body part's activity level, and thereby allows determination of the body part's activity level.

Apparatus, method and system for measuring repetitive motion activity

An image is analyzed to locate an object appearing in the image. A contour of that object is extracted from the image and normalized. Based on the normalized contour, one or more summation invariant values are determined and compared to templates comprising one or more summation invariants for each of one or more target objects. The determined summation invariants for the extracted object are compared to summation invariants for the target objects. When the summation invariants for the extracted object sufficiently match the summation invariants determined from an image of a target object, the extracted object is recognized as that target object. The summation invariants can be semi-local summation invariants determined for each point along the normalized contour, based on a number of points neighboring that point on the normalized contour. The semi-local summation invariants are determined as a function of the x and y coordinates of those points.

Systems and methods for recognizing objects in an image

An apparatus for post-processing of decompressed images having ringing artifacts identifies edges of the image such as may generate such artifacts and defines zones outside of those edges but conforming thereto in which ringing artifacts are to be expected. These zones may be modified according to a model of the human visual system and then filtered so as to reduce ringing artifacts. The filtered zones are spliced back into the image minimizing unnecessary modification of the image while reducing ringing artifacts.

Method and apparatus for the reduction of artifact in decompressed images using morphological post-filtering

A technique for post-processing decoded compressed images to reduce decoding-related artifacts employs a maximum likelihood estimation of an original image f. The decoded image is modeled as a montage of &ldquo;flat surfaces&rdquo; of different intensities, where the number of flat surfaces and their intensities are generally different in different regions of the decoded image. The intensity of each pixel is conditionally adjusted to that of a corresponding flat surface in a window region surrounding the pixel. In a general algorithm, the flat surface model is fitted to the observed image by estimating the model parameters using the &ldquo;k-means&rdquo; algorithm and a hierarchical clustering algorithm. A cluster similarity measure (CSM) is used to determine the number of intensity clusters, and hence flat surfaces, in the model of a window region surrounding a pixel of interest. The pixel intensity is adjusted to an estimated value which is the mean intensity of the cluster in which the pixel falls. A simplified version of the method employs a three-cluster model in which the cluster centers are initialized by a deterministic rule. This simplified method is non-iterative in nature, thus requiring fewer computational resources.

Image artifact reduction using maximum likelihood parameter estimation

An data compression technique combines the benefits of block-wise processing, such as allows reduced buffer memory usage and improved speed through parallel techniques, with tree-type compression normally associated with wavelet-type compression techniques. Block artifacts in the reconstructed data at the partitions between blocks are minimized by use of lapping transformations.

Growing community of inventors

Middleton, WI, United States of America

Yu Hen Hu