[ LEAPMOTION] HowTo: Show The Number Of Fingers Ever The Leap
The algorithms SMG (mr_SMG), ML or ML_Adverb (mr_ML and mr_ML_Adverb), Hand Count (HC), Hand Feature (HF), Finger Count (FC), and Finger Feature (FF) are defined as shown in Figure 3. Supposing that the shooting motion has been defined within the FPS content, the first step was to apply the dynamic and static classification conditions to the shooting motion. Then, using the data on hand API, the classification conditions for the left and right hands were applied. Finally, using the data on finger API, the conditions on the number of fingers on the right hand, as well as the degrees of the fingers, were applied. When two fingers of the right hand were used, the API identifies whether the fingers are thumb and forefinger and distinguishes the x-z axis degree of the thumb. The shooting motion was recognized only when all of the aforementioned conditions were set. Given that the shooting motion has been defined only for the right hand, the direction and movement motions will be defined to the left hand, enabling the use of both hands for manipulation.
[ LEAPMOTION] HowTo: Show the number of fingers ever the Leap
Imagine the leap motion is positioned on a table and our fingers would appear as shadows on this table. In this case we would only be interested in the (x, z) coordinates and could show this directly on our 2D screen.
Mid-air interaction is an emerging spatial input mode which has been used in many areas of interaction, e.g., mid-air keyboard typing , interaction with large displays , virtual and augmented reality , and touchless interaction [2, 9, 10]. Recent progress in hand tracking using affordable controllers such as Leap Motion (www.leapmotion.com), Nimble VR (niblevr.com), and MS Kinect (www.microsoft.com) boosted research and development on precise hand tracking, especially in the area of computer games . Breakthroughs were also made in predicting self-occluded hand, e.g., , which, until recently, was a serious obstacle for using optical tracking devices. However, application of mid-air gestures for precise 3D object manipulation in virtual environments, such as virtual prototyping, assembling and various shape modeling operations, still remains a challenging research problem. Indeed, with 27 degrees of freedom for the hand, only one grasping gesture can be classified into 33 variants . With the motor skills acquired with age and experience, we take and manipulate objects of different size, shape and weight in a way that we feel is most natural and productive. For various simulations and training, professional motor skills in virtual environments, such natural gestures, should be recognized and implemented by the interactive modeling system.
For the unit we received, a paper manual was absent. However, owners just starting out will want to make certain their base is placed directly in front of them with the shiny side up and the green LED facing toward themselves. For set up instructions, users are instructed to visit leapmotion.com/setup, which is essentially a link to the latest controller software.
Recently, several studies [11,12,13] were conducted on PwPD to assess motor dysfunction using commercially available non-contact video and RGB-D based sensors. Result showed that the video-based system could detect bradykinesia and dyskinesia in the clinical environment. Recent studies also focused on another commercially available device, the Leap Motion controller (LMC), which incorporates a 3D camera that is connected to a computer and is claimed to measure positional data accurate to within 0.01 mm . LMC was primarily employed with video games, such as in the study of Lin , where it was used to track the hand movements to enhance the computer accessibility in rehabilitation. Similarly, in the study of Blazica , LMC was used with kinetic sensor to achieved the full kinematics of movement during game play. LMC has also been used for the assessment of movement disorder in PD. However, to the best of our knowledge, after a literature review, the number of studies focusing on the assessment of motor dysfunction in PD with LMC are limited. A study by Matthew  was performed using Leap Motion and a tremor-scope accelerometer-based device to assess the rest tremor and essential tremor in PwPD and healthy control, comparing K-mean clustering and SVM techniques. Results showed that out of eight, six characteristics of frequency and power showed no statistical difference between devices according to the Wilcoxon Signed Ranks Test and Sign Test.
In this study, highly reliable metrics provided by the Leap Motion SDK for skeletal tracking were exploited for MDS-UPDRSIII motor tasks to assess bradykinesia-related characteristics. This study, for the first time, focused on the MDS-UPDRSIII motor tasks. Other authors [42, 43] investigated the potential of the LMC for rehabilitation of the palm and fingers for patients with cerebral strokes, physical injury, or other developmental disabilities. Others [37, 44,45,46] focused on investigating the clinical association of the extracted information. Our approach required both PwPD and healthy subjects to perform MDS-UPDRSIII motor tasks from in a clinical environment. At the same time, one neurologist visualized the performance of each subject and assigned a subjective score based on the performance of the subject. The LMC-provided SDK was exploited to extract the related parameters for objective assessment of motor dysfunction in PwPD. Our finding showed that LMC has a limited angle of view to assess the motor dysfunction in PwPD. Certain gestures could not be recorded properly depending on the placement of the Leap Motion controller . The sensor was not able to recognise all of the fingers. Fingers touching each other, folded over the hand, or hidden from the camera viewpoint were not captured, and in many configurations, some visible fingers could be lost, specifically if the hand is perpendicular to the camera , eventually effecting the accuracy of the measured information. Experimental results showed that although the data recorded from Leap Motion was not completely reliable, a reasonable overall accuracy with the proposed set of features and classification algorithms was obtained. In general, we can conclude that LMC is not yet able to track motor dysfunction characteristics from all MDS-UPDRS proposed exercises. However, intra-rater variability in clinical scores could be one significant reason for the limited monotonic relationship between clinical scores and biomechanical parameters when classifying with machine learning algorithms. It would be interesting to investigate the other potential metrics to extract the related parameters. Following the same methodology with a large number of samples and more than one evaluator (neurologist) and employing only the tasks where consensus is found, such as hand opening/closing, could lead to an unbiased objective measuring system. This could lead to an improvement in the assessment and monitoring of movement disorders using LMC. This study, for the first time, revealed the functional limitation of LMC-provided SDK for postural tremor assessment in PwPD. One possible reason could be an inconsistent frame rate of the device with respect to time. Moreover, it is important to enhance the accuracy in SDK algorithms. Usability of the workspace should be improved to facilitate the use by nontechnical individuals. 350c69d7ab