Accession Number:

ADA409368

Title:

Ground Vehicle Classification Using Hidden Markov Models

Descriptive Note:

Corporate Author:

ATLANTIC COAST TECHNOLOGIES INC SILVER SPRING MD

Personal Author(s):

• Roberts, William J.
• Sabrin, Howard W.
• Ephraim, Yariv

Report Date:

2001-10-04

Pagination or Media Count:

11.0

Abstract:

Ground vehicle classification is performed using hidden Markov modelling of cepstral coefficients. The hidden Markov model HMM is used to represent audio signals. These signals are obtained as the vehicles travel past audio sensor arrays. Well known HMM training algorithms are applied to train models from training data. The trained models are used in two classification rules the MAP rule, and a list-based rule due to Forney. Under some general assumptions, these approaches can be regarded as optimal. Using recordings from the ACID database, over 96 recognition rate on single vehicle classification is achieved.

Descriptors:

• *CLASSIFICATION
• *GROUND VEHICLES
• *MARKOV PROCESSES
• DATA BASES
• MATHEMATICAL MODELS
• ALGORITHMS
• DETECTORS
• MODELS
• TRAINING
• ARRAYS
• SOUND
• ACOUSTIC SIGNALS

Subject Categories:

• Statistics and Probability
• Surface Transportation and Equipment

Distribution Statement:

APPROVED FOR PUBLIC RELEASE