外文翻译利用手腕麦克风和三轴加速计来进行手势定位.docx

1、外文翻译利用手腕麦克风和三轴加速计来进行手势定位Gesture Spotting Using Wrist Worn Microphoneand 3-Axis Accelerometer（原文2）Abstract. We perform continuous activity recognition using only two wrist-worn sensors - a 3-axis accelerometer and a microphone. We build on the intuitive notion that two very dierent sensors are unlike

2、ly to agree in classication of a false activity. By comparing imperfect, sliding window classications from each of these sensors, we are able discern activities of interest from null or uninteresting activities. Where one sensor alone is unable to perform such partitioning, using comparison we are a

3、ble to report good overall system performance of up to 70% accuracy. In presenting these results, we attempt to give a more-in depth visualization of the errors than can be gathered from confusion matrices alone.1 IntroductionHand actions play a crucial role in most human activities.As a consequence

4、s detecting and recognising such activities is one of the most important aspects of context recognition. At the same it is one of the most dicult. This is particularly true for continuous recognition where a set of relevant hand motions (gestures) need to be spotted in a data stream. The diculties o

5、f such recognition stem from two things.First, dueto a large number of degrees of freedom, hand motions tend to be very diverse. The same activity might be performed in many dierent ways even by a single person. Second, in terms of motion, hands are the most active body parts. We move our hands cont

6、inuously, mostly in an unstructured way, even when not doing anything particular with them. In fact in most situations such unstructured motions by far outnumber gestures that are relevant for context recognition. This means that a continuous gesture spotting applications has to deal with an zero cl

7、ass that is dicult to model while taking up most of the signal.1.1 Paper ContributionsOur group has invested a considerable amount of work into hand gesture spotting. To date this work has focused on using several sensors distributed over the userfi body to maximise system performance. This included

8、 motion sensors (3 axis accelerometer, 3 axis gyroscopes and 3 axis magnetic sensors) on the upper and lower arm 3, microphone/accelerometer combination on the upper and lower arm 5 as well as, more recently, a combination of several motion sensors and ultrasonic location devices.This paper investig

9、ates the performance of a gesture spotting system based on a single, wrist mounted device. The idea behind the work is that wrist mounted accessories are broadly accepted and worn by most people on daily basis. In contrast,systems that require the user to put on several sensors at locations such as

10、the upper arm would have much more problems with user acceptance.The downside of this approach is the reduced amount of information available for the recognition. This for example means that the method of analysing sound intensity dierences between microphones on dierent parts of the bodythat was th

11、e corner stone of our previous signal partitioning work is not feasible. This problem is compounded by the fact that for the approach to make sense that wrist mounted device can neither contain too manysensors nor can it require computing and/or communication power that would imply large, bulky batt

12、eries.The main contribution of the paper is to show that, for a certain subset of activities, reasonable gesture spotting results can be achieved with a combination of a microphone and 3 axis accelerometer mounted on the wrist. Our method relies on simple jumping window sound processing algorithms t

13、hat we have shown 10 to require only minimal computationaland communication performance. For the acceleration we use inference on Hidden Markov Models (HMM), again on jumping windows across the data.To our knowledge this is the rst time that such a simple system and a straight forward jumping window

14、 method has been successfully used for hand gesture spotting in continuous data stream with a dominant, unstructured zero class.Previously such setups and algorithms have only been shown to be successfull either for segmented recognition or for scenarios where the zero class was either easy to model

15、 or not relevant (e.g. recognition of standing, sitting, walking, running 6, 9,12). Where these approaches use acceleration sensors, in the work of ?, ? sound was exploited for performing situation analysis in the wearable computing domain. Also ? used sound information to improve the performance of

16、 hearing aids. Complimentary information from sound and acceleration has been used before to detect defects in material surfaces, e.g. in 13, but no work that the authors are aware uses these for recognition of complex activities.In the paper we summarise the sound and acceleration algorithms and th

17、en focus on the performance of dierent fusion methods. It is shown that appropriate fusion is the key to achieving good performance despite simple sensors and algorithms. We verify our approach on data from a wood workshop assembly experiment that have we have introduced and used in previous work 5.

18、 We present the results using both traditional confusion matrices, plus a novel visualisation method that provides a more in-depth understanding of the error types.2 Recognition MethodWe apply sliding windows of lenght w seconds across all the data in increments of w . At each step we apply an wjmp

19、LDA based classication on the sound data, and an HMM classication on the sound. The fisoft results of each classication - LDA distances for sound and HMM class likelihoods for acceleration - are converted into class rankings, and these are fused together using one of two methods: comparison of top r

20、ank (COMP), and a method using Logistic Regression(LR).2.1 Frame by Frame Sound ClassicationUsing LDA Frame-by-frame sound classication was carried out using pattern matching of features extracted in the frequency do-main. Each frame represents a window on 100ms of raw audio data. These windows are

21、then jumped over the entire dataset in 25ms increments, producing a 40Hz output.The audio stream was taken at a sample rate of 2kHz from the wrist worn microphone. From this a Fast Fourier Trans-form (FFT) was carried out on each 100ms window, generating a 100 bin output vector (12fsfftwnd = 122100

22、=100bins).Making use of the fact that our recognition problem requires a small nite number of classes, we applied Linear Discriminant Analysis (LDA)1 to reduce the dimensionality ofthese FFT vectors from 100 to #Classes1.Classication of each frame can then be carried out using a simple Euclidean min

23、imum distance calculation. Whenever we wish to make a decision, we simply calculate the incoming point in LDA space and nd its nearest class mean value from the training dataset. This saving in computation complexity by dimensionality reduction comes at the comparatively minor cost of requiring us t

24、o compute and store a set of LDA class mean values from which the LDA distances might be obtained.Equally, a nearest neighbour approach might be used. For the experiment described here however, Euclidean distance was found to be sucient.A larger window, wlen , was moved over the data in w jmp second

25、 increments. This relatively large window was chosen to reect the fact that all of the activities we are interested in occurat thetimescale of at least severalseconds. On each window we compute a sum of the constituent LDA distances for each class. From these total distances, we then rank each class

26、 according to minimum distance. Classication of the window is then simply a matter of choosing the top ranking class.2.2 HMM Acceleration ClassicationIn contrast to the approach used for sound recognition, we employed model based classication, specically the Hidden Markov Model (HMM), for classifyin

27、g accelerometer data8,11. (The implementation of the HMM learning and inference routines for this experiment was provided courtesy of KevinP. Murphyfi HMM Toolbox for matlab 7.)The features used to feed the HMM models were calculated fromsliding100ms windows on the x,y,andzaxisofthe100Hz sampled acc

28、eleration data. These windows were moved over the data in 25ms increments,producingthefollowing features,output at 40Hz: Mean of x-axisVariance of x-axis A count of the number of peaks (for x,y,z) Mean amplitude of the peaks (for x,y,z)Finally we globally standardised the features so as to avoid num

29、erical complications with the model learning algorithms in matlab.In previous work we employed single Gaussian observation models, but this was found to be inadequate for some classes unless a large number of states were used. Intuitively, the descriptive power of a mixture of Gaussian is much close

30、r to firealiy than only one, and so for these classes a mixture model was used. The specic number of mixtures and the number of hidden states used were individually tailored by hand for each class. The parameters themselves were trainedfrom the data.A window of wlen , in wjmp increments, was run ove

31、r the acceleration features, and the corresponding log likelihood for each HMM class model calculated.Classication is carried out for each window by choosing the class which produces the largest log likelihood given the stream of feature data from the test set.2.3 Fusion of classiersComparison of to

32、p choices (COMP) The top rankings from each of the sound and acceleration classiers for a given jumping window segment are taken, compared, and returned as valid if they agree. Those where both classiers disagree are thrown out - classied as null.Logistic regression (LR) The main problem with a direct comparison of top classier rankings is that it fails to take into account cases where one classier might be more reliable than another at recognising particular classes. If one classier reliably detects a class, but the other classier failsto, perhaps relegating the class to second or third ran