Generalized cross-correlation based noise robust abnormal acoustic event localization utilizing non-negative matrix factorization

Moon, Sung-Kyu; Shon, Suwon; Kim, Wooil; Han, David K.

doi:10.1109/avss.2014.6918663

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acoustic features have been popular in various surveillance applications, such as object tracking [11,98] and event detection [110,76,115,33]. There are several benefits to use acoustic features.…”

Section: Features Beyond Visionmentioning

confidence: 99%

“…A more popular approach for acoustic event detection is based on a set of microphone array. This is because microphone array is not only able to be used to detect detect an abnormal acoustic event such as a gunshot, but also able to identify the location of that event [115,76], which we termed "acoustic localisation". The principal for acoustic event localisation is related to some physics knowledge.…”

Section: Features Beyond Visionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Event Detection for Signal-based Surveillance

Xu,

Fookes,

Sridharan

2016

Preprint

View full text Add to dashboard Cite

Signal-based Surveillance systems such as Closed Circuits Televisions (CCTV) have been widely installed in public places. Those systems are normally used to find the events with security interest, and play a significant role in public safety. Though such systems are still heavily reliant on human labour to monitor the captured information, there have been a number of automatic techniques proposed to analysing the data. This article provides an overview of automatic surveillance event detection techniques . Despite it's popularity in research, it is still too challenging a problem to be realised in a real world deployment. The challenges come from not only the detection techniques such as signal processing and machine learning, but also the experimental design with factors such as data collection, evaluation protocols, and ground-truth annotation. Finally, this article propose that multi-disciplinary research is the path towards a solution to this problem.

show abstract

Section: Features Beyond Visionmentioning

confidence: 99%

Section: Features Beyond Visionmentioning

confidence: 99%