Object Classification from Acoustic Analysis of Impact

We address the problem of autonomously classifying objects from the sounds they make when struck, and present results from different attempts to classify various items. Previous work has shown that object classification is possible based on features derived from the frequency content of signals. We develop a moving-maximum algorithm to extract the two most significant spikes in the FFT of the sounds of impact, and use these extracted spikes as features. We describe the transformation of the training data’s extracted features into a compilation of representative cluster means. These cluster means are used as labeled inputs to the different classifiers discussed. We discuss two techniques to classify test vectors based on their extracted feature spikes, and show that accurate classification of objects is possible using these features. The first technique is the familiar minimumdistance classifier that calculates the distance between a given test vector and each cluster mean, and assigns the test vector to the cluster that yields the smallest error. The second technique is one we developed for the task: the decision-map clussijkr: a hybrid minimum-distance classifier and decision-tree classifier, that iteratively finds the closest cluster mean to each test vector and uses multiple features only if it cannot classify the test sample. Results from classifier trials show that using our moving-maximum feature extractor and decision-map classifier, object classification from the sound of impact can be done as accurately as using the minimum-distance classifier, but at significantly lower computational expense.

[1]  Clayton V. Stewart,et al.  Classification of atmospheric acoustic signals from fixed-wing aircraft , 1992, Defense, Security, and Sensing.

[2]  M.-C. Perron Feature extraction and learning decision rules from ultrasonic signals-applicability in non-destructive testing , 1988, IEEE 1988 Ultrasonics Symposium Proceedings..

[3]  L. Deuser,et al.  A hybrid neural network classifier of short duration acoustic signals , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[4]  D. Legitimus,et al.  Experimental comparison between neural networks and classical techniques of classification applied to natural underwater transients identification , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[5]  C. Stewart,et al.  Detection and classification of acoustic signals from fixed-wing aircraft , 1991, IEEE 1991 International Conference on Systems Engineering.

[6]  M. Fisher On hearing the shape of a drum , 1966 .