Car crashes detection by audio analysis in crowded roads

Pasquale Foggia; Alessia Saggese; Nicola Strisciuglio; Mario Vento; Nicolai Petkov

doi:10.1109/AVSS.2015.7301731

Car crashes detection by audio analysis in crowded roads

Pasquale Foggia, Alessia Saggese, Nicola Strisciuglio, Mario Vento, Nicolai Petkov

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

18 Citations (Scopus)

Abstract

In the last years, video surveillance has been employed for roads monitoring in order to detect abnormal events and improve the safety procedures in case of emergency. Certain events, such as car crashes or tire skidding, are difficult or impossible to detect when only the visual information is considered. In this paper we describe a preliminary system to detect events in roads by means of audio analysis. The system that we propose combines short- and long-time analysis of the audio signal in order to detect both impulsive and sustained events. We present the preliminary results achieved by the proposed system on a data set specifically made for roads surveillance, which we made publicly available. We also discuss the architectural deployment of such system in real environments with respect to a model of the noise of road traffic. The achieved results are promising and confirm the effectiveness of the system.

Original language	English
Title of host publication	2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015)
Place of Publication	Piscataway, NJ
Publisher	IEEE
ISBN (Electronic)	978-1-4673-7631-0
ISBN (Print)	978-1-4673-7632-7
DOIs	https://doi.org/10.1109/AVSS.2015.7301731
Publication status	Published - 19 Oct 2015
Externally published	Yes
Event	12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015 - Karlsruhe, Germany Duration: 25 Aug 2015 → 28 Aug 2015 Conference number: 12

Conference

Conference	12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015
Abbreviated title	AVSS 2015
Country/Territory	Germany
City	Karlsruhe
Period	25/08/15 → 28/08/15

Keywords

Roads
Signal to noise ratio
Support vector machines
Surveillance
Tires
Vehicle crash testing
Vehicles

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/AVSS.2015.7301731

Cite this

@inproceedings{a6b44f3fd8db4585a6c08ff4810d4525,

title = "Car crashes detection by audio analysis in crowded roads",

abstract = "In the last years, video surveillance has been employed for roads monitoring in order to detect abnormal events and improve the safety procedures in case of emergency. Certain events, such as car crashes or tire skidding, are difficult or impossible to detect when only the visual information is considered. In this paper we describe a preliminary system to detect events in roads by means of audio analysis. The system that we propose combines short- and long-time analysis of the audio signal in order to detect both impulsive and sustained events. We present the preliminary results achieved by the proposed system on a data set specifically made for roads surveillance, which we made publicly available. We also discuss the architectural deployment of such system in real environments with respect to a model of the noise of road traffic. The achieved results are promising and confirm the effectiveness of the system.",

keywords = "Roads, Signal to noise ratio, Support vector machines, Surveillance, Tires, Vehicle crash testing, Vehicles",

author = "Pasquale Foggia and Alessia Saggese and Nicola Strisciuglio and Mario Vento and Nicolai Petkov",

year = "2015",

month = oct,

day = "19",

doi = "10.1109/AVSS.2015.7301731",

language = "English",

isbn = "978-1-4673-7632-7",

booktitle = "2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015)",

publisher = "IEEE",

address = "United States",

note = "12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015, AVSS 2015 ; Conference date: 25-08-2015 Through 28-08-2015",

}

Foggia, P, Saggese, A, Strisciuglio, N, Vento, M & Petkov, N 2015, Car crashes detection by audio analysis in crowded roads. in 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015)., 7301731, IEEE, Piscataway, NJ, 12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015, Karlsruhe, Germany, 25/08/15. https://doi.org/10.1109/AVSS.2015.7301731

Car crashes detection by audio analysis in crowded roads. / Foggia, Pasquale; Saggese, Alessia; Strisciuglio, Nicola et al.
2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015). Piscataway, NJ: IEEE, 2015. 7301731.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Car crashes detection by audio analysis in crowded roads

AU - Foggia, Pasquale

AU - Saggese, Alessia

AU - Strisciuglio, Nicola

AU - Vento, Mario

AU - Petkov, Nicolai

N1 - Conference code: 12

PY - 2015/10/19

Y1 - 2015/10/19

N2 - In the last years, video surveillance has been employed for roads monitoring in order to detect abnormal events and improve the safety procedures in case of emergency. Certain events, such as car crashes or tire skidding, are difficult or impossible to detect when only the visual information is considered. In this paper we describe a preliminary system to detect events in roads by means of audio analysis. The system that we propose combines short- and long-time analysis of the audio signal in order to detect both impulsive and sustained events. We present the preliminary results achieved by the proposed system on a data set specifically made for roads surveillance, which we made publicly available. We also discuss the architectural deployment of such system in real environments with respect to a model of the noise of road traffic. The achieved results are promising and confirm the effectiveness of the system.

AB - In the last years, video surveillance has been employed for roads monitoring in order to detect abnormal events and improve the safety procedures in case of emergency. Certain events, such as car crashes or tire skidding, are difficult or impossible to detect when only the visual information is considered. In this paper we describe a preliminary system to detect events in roads by means of audio analysis. The system that we propose combines short- and long-time analysis of the audio signal in order to detect both impulsive and sustained events. We present the preliminary results achieved by the proposed system on a data set specifically made for roads surveillance, which we made publicly available. We also discuss the architectural deployment of such system in real environments with respect to a model of the noise of road traffic. The achieved results are promising and confirm the effectiveness of the system.

KW - Roads

KW - Signal to noise ratio

KW - Support vector machines

KW - Surveillance

KW - Tires

KW - Vehicle crash testing

KW - Vehicles

UR - http://www.scopus.com/inward/record.url?scp=84958632914&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2015.7301731

DO - 10.1109/AVSS.2015.7301731

M3 - Conference contribution

AN - SCOPUS:84958632914

SN - 978-1-4673-7632-7

BT - 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2015)

PB - IEEE

CY - Piscataway, NJ

T2 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015

Y2 - 25 August 2015 through 28 August 2015

ER -

Car crashes detection by audio analysis in crowded roads

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this