Babak Taati

Difference of Normals as a Multi-scale Operator in Unorganized Point Clouds

A novel multi-scale operator for unorganized 3D point clouds is introduced. The Difference of Normals (DoN) provides a computationally efficient, multi-scale approach to processing large unorganized 3D point clouds. The application of DoN in the multi-scale filtering of two different real-world outdoor urban LIDAR scene datasets is quantitatively and qualitatively demonstrated. In both datasets the DoN operator is shown to segment large 3D point clouds into scale-salient clusters, such as cars, people, and lamp posts towards applications in semi-automatic annotation, and as a pre-processing step in automatic object recognition. The application of the operator to segmentation is evaluated on a large public dataset of outdoor LIDAR scenes with ground truth annotations.

Local shape descriptor selection for object recognition in range data

Local shape descriptor selection for object recognition and localization in range data is formulated herein as an optimization problem. Local shape descriptors are used for establishing point correspondences between two surfaces by way of encapsulating local shape, such that their similarity indicates geometric similarity between respective neighbourhoods. We present a generalized platform for constructing local shape descriptors that subsumes a large class of existing methods, and that allows for tuning to the geometry of specific models. Experimental analysis confirms the superiority of optimized descriptors over generic ones in object recognition tasks using real LIDAR and stereo range images.

Towards a single sensor passive solution for automated fall detection

Falling in the home is one of the major challenges to independent living among older adults. The associated costs, coupled with a rapidly growing elderly population, are placing a burden on healthcare systems worldwide that will swiftly become unbearable. To facilitate expeditious emergency care, we have developed an artificially intelligent camera-based system that automatically detects if a person within the field-of-view has fallen. The system addresses concerns raised in earlier work and the requirements of a widely deployable in-home solution. The presented prototype utilizes a consumer-grade camera modified with a wide-angle lens. Machine learning techniques applied to carefully engineered features allow the system to classify falls at high accuracy while maintaining invariance to lighting, environment and the presence of multiple moving objects. This paper describes the system, outlines the algorithms used and presents empirical validation of its effectiveness.

Dynamic parameter identification and analysis of a PHANToM haptic device

In this paper, the dynamics of a SensAble Technologies PHANToM Premium 1.5 haptic device is experimentally identified and analyzed. Towards this purpose, the dynamic model derived in the work of M. C. Cavusoglu and D. Feygin (2001) is augmented with a friction model and is linearly parameterized. The identified model predicts joint torques with over 95% accuracy and produces an inertia matrix that is confirmed to be positive-definite within the device workspace. In addition, user hand force estimates with and without including the identified dynamics are compared with the measured values. The experiments are also conducted for other typical installation conditions of the device, such as with force sensor mounted at the end-effector, using gimbal and counterbalance weight, and upside-down installation of the device. The identified dynamic model can be used for hand force estimation, accurate gravity counterbalancing for different installation conditions, and model-based control systems design for haptic simulation and tele-operation applications

Variable Dimensional Local Shape Descriptors for Object Recognition in Range Data

We propose a new set of highly descriptive local shape descriptors (LSDs) for model-based object recognition and pose determination in input range data. Object recognition is performed in three phases: point matching, where point correspondences are established between range data and the complete model using local shape descriptors; pose recovery, where a computationally robust algorithm generates a rough alignment between the model and its instance in the scene, if such an instance is present; and pose refinement. While previously developed LSDs take a minimalist approach, in that they try to construct low dimensional and compact descriptors, we use high (up to 9) dimensional descriptors as the key to more accurate and robust point correspondence. Our strategy significantly simplifies the computational burden of the pose recovery phase by investing more time in the point matching phase. Experiments with Lidar and dense stereo range data illustrate the effectiveness of the approach by providing a higher percentage of correct matches in the candidate point matches list than a leading minimalist technique. Consequently, the number of RANSAC iterations required for recognition and pose determination is drastically smaller in our approach.

Use of Accelerometer-Based Feedback of Walking Activity for Appraising Progress With Walking-Related Goals in Inpatient Stroke Rehabilitation A Randomized Controlled Trial

Background. Regaining independent ambulation is important to those with stroke. Increased walking practice during “down time” in rehabilitation could improve walking function for individuals with stroke. Objective. To determine the effect of providing physiotherapists with accelerometer-based feedback on patient activity and walking-related goals during inpatient stroke rehabilitation. Methods. Participants with stroke wore accelerometers around both ankles every weekday during inpatient rehabilitation. Participants were randomly assigned to receive daily feedback about walking activity via their physiotherapists (n = 29) or to receive no feedback (n = 28). Changes in measures of daily walking (walking time, number of steps, average cadence, longest bout duration, and number of “long” walking bouts) and changes in gait control and function assessed in-laboratory were compared between groups. Results. There was no significant increase in walking time, number of steps, longest bout duration, or number of long walking bouts for the feedback group compared with the control group (P values > .20). However, individuals who received feedback significantly increased cadence of daily walking more than the control group (P = .013). From the in-laboratory gait assessment, individuals who received feedback had a greater increase in walking speed and decrease in step time variability than the control group (P values < .030). Conclusion. Feedback did not increase the amount of walking completed by individuals with stroke. However, there was a significant increase in cadence, indicating that intensity of daily walking was greater for those who received feedback than the control group. Additionally, more intense daily walking activity appeared to translate to greater improvements in walking speed.

3D Human Motion Analysis to Detect Abnormal Events on Stairs

Falls on the stairs are a common cause of accidental injury among the older adults. Understanding the mechanisms leading to such accidents may improve not only the prevention of falls, but also support independent living among elderly. Thus, a method to automatically detect falls and other abnormal events on stairs is presented and empirically validated. Automatic fall detection will also assist in data collection for environmental design improvements and fall prevention. Real-time 3D joint tracking information, provided by a Microsoft Kinect, is used to estimate the walking speed and to extract a set of features that encode human motion during stairway descent. Supervised learning algorithms, trained on manually labelled training data simulated in a home laboratory, obtained a high detection accuracy rate of ~92% in leave-one-subject-out cross validation. In contrast with previous research, which identified visual tracking of the feet as the best indicator of dangerous activity, 3D motion of the hips is experimentally shown to be the most informative component in detecting abnormal events in the 3D tracking data provided by the Kinect.

Concurrent validity of the Microsoft Kinect for Windows v2 for measuring spatiotemporal gait parameters

This paper presents a study to evaluate the concurrent validity of the Microsoft Kinect for Windows v2 for measuring the spatiotemporal parameters of gait. Twenty healthy adults performed several sequences of walks across a GAITRite mat under three different conditions: usual pace, fast pace, and dual task. Each walking sequence was simultaneously captured with two Kinect for Windows v2 and the GAITRite system. An automated algorithm was employed to extract various spatiotemporal features including stance time, step length, step time and gait velocity from the recorded Kinect v2 sequences. Accuracy in terms of reliability, concurrent validity and limits of agreement was examined for each gait feature under different walking conditions. The 95% Bland-Altman limits of agreement were narrow enough for the Kinect v2 to be a valid tool for measuring all reported spatiotemporal parameters of gait in all three conditions. An excellent intraclass correlation coefficient (ICC2, 1) ranging from 0.9 to 0.98 was observed for all gait measures across different walking conditions. The inter trial reliability of all gait parameters were shown to be strong for all walking types (ICC3, 1 > 0.73). The results of this study suggest that the Kinect for Windows v2 has the capacity to measure selected spatiotemporal gait parameters for healthy adults.

Experimental identification and analysis of the dynamics of a phantom premium 1.5a haptic device

The dynamics of a PHANToM Premium 1.5A haptic device from SensAble Technologies, Inc. is experimentally identified and analyzed for different installations of the device and its accessories, such as the typical upright, upside down, with gimbal and counterbalance weight, and with force sensor.1 An earlier formulation of the robot dynamic model is augmented with a friction model, linearly parameterized, and experimentally identified using least squares. The identified dynamics are experimentally evaluated with an inverse dynamics controller and verified by comparing user hand force estimates with the measured values. The contribution of different dynamic terms such as inertial, Coriolis and centrifugal, gravitational, and Coulomb and viscous friction are demonstrated and discussed. The identified model can be used for a variety of haptic applications, such as hand force estimation, accurate active gravity compensation and counterbalance weight determination for various installation conditions, and model-based control for haptic simulation and teleoperation.

Video analysis for identifying human operation difficulties and faucet usability assessment

As the world struggles to cope with a growing elderly population, concerns of how to preserve independence are becoming increasingly acute. A major hurdle to independent living is the inability to use everyday household objects. This work aims to automate the assessment of product usability for the elderly population using the tools of computer vision and machine learning. A novel video analysis technique is presented that performs temporal segmentation of video containing human-product interaction and automatically identifies time segments in which the human has difficulties in operating the product. The method has applications in the automatic assessment of the usability of various product designs via measuring the frequency of operation difficulties. The approach is applied to a case study of water faucet design for the older adult population with dementia. Experiments in the automatic analysis of a large database of real-world recorded videos confirm the effectiveness of the approach in providing valid temporal segmentation (accuracy 88.1%) and in the correct estimation of the relative advantage (or disadvantage) of one design over another in terms of operation difficulties in performing various actions.