00966640

Component

https://doi.org/10.3141/1840-21

http://scholar.google.com....+Yu&publication_year=2003

A system for automated traffic accident detection in intersections was designed. The input to the system is a 3-s segment of audio signal. The system can be operated in two modes: the two-class and multiclass modes. The output of the two-class mode is a label of "crash" or "noncrash." In the multiclass mode of operation, the system identifies crashes as well as several types of noncrash incidents, including normal traffic and construction sounds. The system is composed of three main signal processing stages: feature extraction, feature reduction, and classification. Five methods of feature extraction were investigated and compared; these are based on the discrete wavelet transform, fast Fourier transform, discrete cosine transform, real cepstral transform, and mel frequency cepstral transform. Statistical methods are used for feature optimization and classification. Three types of classifiers are investigated and compared; these are the nearest-mean, maximum-likelihood, and nearest-neighbor methods. The results of the study show that the optimum design uses wavelet-based features in combination with the maximum-likelihood classifier. The system is computationally inexpensive relative to the other methods investigated, and the system consistently results in accident detection accuracies of 95% to 100% when the audio signal has a signal-to-noise-ratio of at least 0 decibels.

This paper appears in Transportation Research Record No. 1840, Statistical Methods and Modeling and Safety Data, Analysis, and Evaluation.

English

p. 186-192

2003

Transportation Research Record

0309085810

Figures (4) ; References (25) ; Tables (2)

Accuracy; Automatic crash notification; Digital audio; Intersections; Signal processing; Signal to noise ratio; Traffic crashes

Highways; Safety and Human Factors; I80: Accident Studies

TRIS, TRB, ATRI

Dec 17 2003 12:00AM

• ACCIDENT COUNT MODEL BASED ON MULTIYEAR CROSS-SECTIONAL ROADWAY DATA WITH SERIAL CORRELATION
• ARE SUVS "SUPREMELY UNSAFE VEHICLES"? ANALYSIS OF ROLLOVERS AND INJURIES WITH SPORT UTILITY VEHICLES
• CONFIGURATION ANALYSIS OF TWO-VEHICLE REAR-END CRASHES
• DEVELOPMENT OF A PROCEDURE FOR ESTIMATING EXPECTED SAFETY EFFECTS OF A CONTEMPLATED TRAFFIC SIGNAL INSTALLATION
• DEVELOPMENT OF CRASH REDUCTION FACTORS: METHODS, PROBLEMS, AND RESEARCH NEEDS
• EMPIRICAL APPROACHES TO OUTLIER DETECTION IN INTELLIGENT TRANSPORTATION SYSTEMS DATA
• EMPIRICAL INVESTIGATION OF INTERACTIVE HIGHWAY SAFETY DESIGN MODEL ACCIDENT PREDICTION ALGORITHM: RURAL INTERSECTIONS
• HUMAN FATALITIES IN ANIMAL-RELATED HIGHWAY CRASHES
• IDENTIFICATION OF ACCIDENT CAUSAL FACTORS AND PREDICTION OF HAZARDOUSNESS OF INTERSECTION APPROACHES
• LEVEL OF SERVICE OF SAFETY: CONCEPTUAL BLUEPRINT AND ANALYTICAL FRAMEWORK
• MACROLEVEL ACCIDENT PREDICTION MODELS FOR EVALUATING SAFETY OF URBAN TRANSPORTATION SYSTEMS
• MODELING TRAFFIC CRASH-FLOW RELATIONSHIPS FOR INTERSECTIONS: DISPERSION PARAMETER, FUNCTIONAL FORM, AND BAYES VERSUS EMPIRICAL BAYES METHODS
• OPTIMIZING AGGREGATION LEVEL FOR INTELLIGENT TRANSPORTATION SYSTEM DATA BASED ON WAVELET DECOMPOSITION
• PROFILING OF HIGH-FREQUENCY ACCIDENT LOCATIONS BY USE OF ASSOCIATION RULES
• REAL-TIME CRASH PREDICTION MODEL FOR APPLICATION TO CRASH PREVENTION IN FREEWAY TRAFFIC
• SAFETY EFFECTIVENESS OF INTERSECTION LEFT- AND RIGHT-TURN LANES
• STATISTICAL PROCEDURE USING AN EXPERT PANEL FOR PROCUREMENT OF EMERGING TRANSPORTATION TECHNOLOGIES
• STUDY OF FARM VEHICLE CRASHES IN NORTH CAROLINA
• SURROGATE SAFETY MEASURES FROM TRAFFIC SIMULATION MODELS
• SYSTEMWIDE OPTIMIZATION OF SAFETY IMPROVEMENTS FOR RESURFACING, RESTORATION, OR REHABILITATION PROJECTS
• VALIDATION OF FHWA CRASH MODELS FOR RURAL INTERSECTIONS: LESSONS LEARNED