Erik E. Stone

Fall Detection in Homes of Older Adults Using the Microsoft Kinect

A method for detecting falls in the homes of older adults using the Microsoft Kinect and a two-stage fall detection system is presented. The first stage of the detection system characterizes a persons vertical state in individual depth image frames, and then segments on ground events from the vertical state time series obtained by tracking the person over time. The second stage uses an ensemble of decision trees to compute a confidence that a fall preceded on a ground event. Evaluation was conducted in the actual homes of older adults, using a combined nine years of continuous data collected in 13 apartments. The dataset includes 454 falls, 445 falls performed by trained stunt actors and nine naturally occurring resident falls. The extensive data collection allows for characterization of system performance under real-world conditions to a degree that has not been shown in other studies. Cross validation results are included for standing, sitting, and lying down positions, near (within 4 m) versus far fall locations, and occluded versus not occluded fallers. The method is compared against five state-of-the-art fall detection algorithms and significantly better results are achieved.

Evaluation of an inexpensive depth camera for in-home gait assessment

An investigation of a new, inexpensive depth camera device, the Microsoft Kinect, for passive gait assessment in home environments is presented. In order to allow older adults to safely continue living in independent settings as they age, the ability to assess their risk of falling, along with detecting the early onset of illness and functional decline, is essential. Daily measurements of temporal and spatial gait parameters would greatly facilitate such an assessment. Ideally, these measurements would be obtained passively, in normal daily activity, without the need for wearable devices or expensive equipment. In this work, the use of the inexpensive Microsoft Kinect for obtaining measurements of temporal and spatial gait parameters is evaluated against an existing web-camera based system, along with a Vicon marker-based motion capture system for ground truth. Techniques for extracting gait parameters from the Kinect data are described, as well as the potential advantages of the Kinect over the web-camera system for passive, in-home gait assessment.

Passive in-home measurement of stride-to-stride gait variability comparing vision and Kinect sensing

We present an analysis of measuring stride-to-stride gait variability passively, in a home setting using two vision based monitoring techniques: anonymized video data from a system of two web-cameras, and depth imagery from a single Microsoft Kinect. Millions of older adults fall every year. The ability to assess the fall risk of elderly individuals is essential to allowing them to continue living safely in independent settings as they age. Studies have shown that measures of stride-to-stride gait variability are predictive of falls in older adults. For this analysis, a set of participants were asked to perform a number of short walks while being monitored by the two vision based systems, along with a marker based Vicon motion capture system for ground truth. Measures of stride-to-stride gait variability were computed using each of the systems and compared against those obtained from the Vicon.

Unobtrusive, Continuous, In-Home Gait Measurement Using the Microsoft Kinect

A system for capturing habitual, in-home gait measurements using an environmentally mounted depth camera, the Microsoft Kinect, is presented. Previous work evaluating the use of the Kinect sensor for in-home gait measurement in a lab setting has shown the potential of this approach. In this paper, a single Kinect sensor and computer were deployed in the apartments of older adults in an independent living facility for the purpose of continuous, in-home gait measurement. In addition, a monthly fall risk assessment protocol was conducted for each resident by a clinician, which included traditional tools such as the timed up a go and habitual gait speed tests. A probabilistic methodology for generating automated gait estimates over time for the residents of the apartments from the Kinect data is described, along with results from the apartments as compared to two of the traditionally measured fall risk assessment tools. Potential applications and future work are discussed.

Toward a Passive Low-Cost In-Home Gait Assessment System for Older Adults

In this paper, we propose a webcam-based system for in-home gait assessment of older adults. A methodology has been developed to extract gait parameters including walking speed, step time, and step length from a 3-D voxel reconstruction, which is built from two calibrated webcam views. The gait parameters are validated with a GAITRite mat and a Vicon motion capture system in the laboratory with 13 participants and 44 tests, and again with GAITRite for 8 older adults in senior housing. Excellent agreement with intraclass correlation coefficients of 0.99 and repeatability coefficients between 0.7% and 6.6% was found for walking speed, step time, and step length given the limitation of frame rate and voxel resolution. The system was further tested with ten seniors in a scripted scenario representing everyday activities in an unstructured environment. The system results demonstrate the capability of being used as a daily gait assessment tool for fall risk assessment and other medical applications. Furthermore, we found that residents displayed different gait patterns during their clinical GAITRite tests compared to the realistic scenario, namely a mean increase of 21% in walking speed, a mean decrease of 12% in step time, and a mean increase of 6% in step length. These findings provide support for continuous gait assessment in the home for capturing habitual gait.

Average in-home gait speed: investigation of a new metric for mobility and fall risk assessment of elders.

A study was conducted to assess how a new metric, average in-home gait speed (AIGS), measured using a low-cost, continuous, environmentally mounted monitoring system, compares to a set of traditional physical performance instruments used for mobility and fall risk assessment of elderly adults. Sixteen participants were recruited from a local independent living facility. In addition to having their gait monitored continuously in their home for an average of eleven months, the participants completed a monthly clinical assessment consisting of a set of traditional assessment instruments: Habitual Gait Speed, Timed-Up and Go, Short Physical Performance Battery, Berg Balance Scale--short form, and Multidirectional Reach Test. A methodology is developed to assess which of these instruments may work well with the largest subset of older adults, is best suited for detecting changes in an individual over time, and most reliably captures the true mobility level of an individual. Using the ability of an instrument to predict how an individual would score on all the instruments as a metric, AIGS performs best, having better predictive ability than the traditional instruments. AIGS also displays the best agreement between observed and smoothed values, indicating it has the lowest intra-individual test-retest variability of the instruments. AIGS, measured continuously, during normal everyday activity, represents a significant shift in assessment methodology compared to infrequently assessed, traditional physical performance instruments. Continuous, in-home data may provide a more accurate and precise picture of the physical function of older adults, leading to improved mobility and fall risk assessment.

Day or Night Activity Recognition From Video Using Fuzzy Clustering Techniques

We present an approach for activity state recognition implemented on data collected from various sensors-standard web cameras under normal illumination, web cameras using infrared lighting, and the inexpensive Microsoft Kinect camera system. Sensors such as the Kinect ensure that activity segmentation is possible during the daytime as well as night. This is especially useful for activity monitoring of older adults since falls are more prevalent at night than during the day. This paper is an application of fuzzy set techniques to a new domain. The approach described herein is capable of accurately detecting several different activity states related to fall detection and fall risk assessment including sitting, being upright, and being on the floor to ensure that elderly residents get the help they need quickly in case of emergencies and ultimately to help prevent such emergencies.

Capturing habitual, in-home gait parameter trends using an inexpensive depth camera

Results are presented for measuring the gait parameters of walking speed, stride time, and stride length of five older adults continuously, in their homes, over a four month period. The gait parameters were measured passively, using an inexpensive, environmentally mounted depth camera, the Microsoft Kinect. Research has indicated the importance of measuring a persons gait for a variety of purposes from fall risk assessment to early detection of health problems such as cognitive impairment. However, such assessments are often done infrequently and most current technologies are not suitable for continuous, long term use. For this work, a single Microsoft Kinect sensor was deployed in four apartments, containing a total of five residents. A methodology for generating trends in walking speed, stride time, and stride length based on data from identified walking sequences in the home is presented, along with trend estimates for the five participants who were monitored for this work.

Gait analysis and validation using voxel data

In this paper, we present a method for extracting gait parameters including walking speed, step time and step length from a three-dimensional voxel reconstruction, which is built from two calibrated camera views. These parameters are validated with a GAITRite Electronic mat and a Vicon motion capture system. Experiments were conducted in which subjects walked across the GAITRite mat at various speeds while the Vicon cameras recorded the motion of reflective markers attached to subjects’ shoes, and our two calibrated cameras captured the images. Excellent agreements were found for walking speed. Step time and step length were also found to have good agreement given the limitation of frame rate and voxel resolution.

Evaluation of the Microsoft Kinect for screening ACL injury

A study was conducted to evaluate the use of the skeletal model generated by the Microsoft Kinect SDK in capturing four biomechanical measures during the Drop Vertical Jump test. These measures, which include: knee valgus motion from initial contact to peak flexion, frontal plane knee angle at initial contact, frontal plane knee angle at peak flexion, and knee-to-ankle separation ratio at peak flexion, have proven to be useful in screening for future knee anterior cruciate ligament (ACL) injuries among female athletes. A marker-based Vicon motion capture system was used for ground truth. Results indicate that the Kinect skeletal model likely has acceptable accuracy for use as part of a screening tool to identify elevated risk for ACL injury.