Ten lectures on wavelets
Adapted wave form analysis, wavelet-packets and applications
ICIAM 91 Proceedings of the second international conference on Industrial and applied mathematics
Adapted wavelet analysis from theory to software
Adapted wavelet analysis from theory to software
Local discriminant bases and their applications
Journal of Mathematical Imaging and Vision - Special issue on mathematical imaging
Local discriminant time-frequency atoms for signal classification
Signal Processing
Analysis of Acoustic Signatures from Moving Vehicles UsingTime-Varying Autoregressive Models
Multidimensional Systems and Signal Processing
Fast adaptive wavelet packet image compression
IEEE Transactions on Image Processing
Wavelet-based acoustic detection of moving vehicles
Multidimensional Systems and Signal Processing
A diffusion framework for detection of moving vehicles
Digital Signal Processing
Distance based decision fusion in a distributed wireless sensor network
IPSN'03 Proceedings of the 2nd international conference on Information processing in sensor networks
Block Based Deconvolution Algorithm Using Spline Wavelet Packets
Journal of Mathematical Imaging and Vision
| Hi-index | 0.00 |
In this paper we propose a robustalgorithm that solves two related problems: 1) Classificationof acoustic signals emitted by different moving vehicles. Therecorded signals have to be assigned to pre-existing categoriesindependently from the recording surrounding conditions. 2) Detectionof the presence of a vehicle in a certain class via analysisof its acoustic signature against the existing database of recordedand processed acoustic signals. To achieve this detection withpractically no false alarms we construct the acoustic signatureof a certain vehicle using the distribution of the energies amongblocks which consist of wavelet packet coefficients. We allowno false alarms in the detection even under severe conditions;for example when the acoustic recording of target object is asuperposition of the acoustics emitted from other vehicles thatbelong to other classes. The proposed algorithm is robust evenunder severe noise and a range of rough surrounding conditions.This technology, which has many algorithmic variations, can beused to solve a wide range of classification and detection problemswhich are based on acoustic processing which are not relatedto vehicles. These have numerous applications.