Search results

Road accidents, an inadvertent mishap can be detected automatically and alerts sent instantly with the collaboration of image processing techniques and on-road video surveillance systems. However, to rely exclusively on visual information especially under adverse conditions like night times, dark areas and unfavourable weather conditions such as snowfall, rain, and fog which result in faint visibility lead to incertitude. The main goal of the proposed work is certainty of accident occurrence.

The authors of this work propose a method for detecting road accidents by analyzing audio signals to identify hazardous situations such as tire skidding and car crashes. The motive of this project is to build a simple and complete audio event detection system using signal feature extraction methods to improve its detection accuracy. The experimental analysis is carried out on a publicly available real time data-set consisting of audio samples like car crashes and tire skidding. The Temporal features of the recorded audio signal like Energy Volume Zero Crossing Rate 28ZCR2529 and the Spectral features like Spectral Centroid Spectral Spread Spectral Roll of factor Spectral Flux the Psychoacoustic features Energy Sub Bands ratio and Gammatonegram are computed. The extracted features are pre-processed and trained and tested using Support Vector Machine (SVM) and K-nearest neighborhood (KNN) classification algorithms for exact prediction of the accident occurrence for various SNR ranges. The combination of Gammatonegram with Temporal and Spectral features of the validates to be superior compared to the existing detection techniques.

Temporal, Spectral, Psychoacoustic features, gammetonegram of the recorded audio signal are extracted. A High level vector is generated based on centroid and the extracted features are classified with the help of machine learning algorithms like SVM, KNN and DT. The audio samples collected have varied SNR ranges and the accuracy of the classification algorithms is thoroughly tested.

Denoising of the audio samples for perfect feature extraction was a tedious chore.

The existing literature cites extraction of Temporal and Spectral features and then the application of classification algorithms. For perfect classification, the authors have chosen to construct a high level vector from all the four extracted Temporal, Spectral, Psycho acoustic and Gammetonegram features. The classification algorithms are employed on samples collected at varied SNR ranges.

The event‐driven paradigm is appropriate for context aware, distributed applications, yet basic events may be too low level to be meaningful to users. The authors aim to argue that this bottom‐up approach is insufficient to handle very low‐level sensor data or to express all the queries users might wish to make.

The authors propose an alternative model for querying and subscribing transparently to distributed state in a real‐time, ubiquitous, sensor‐driven environment such as is found in Sentient Computing.

The framework consists of four components: a state‐based, temporal first‐order logic (TFOL) model that represents the concrete state of the world, as perceived by sensors; an expressive TFOL‐based language, the Abstract Event Specification Language (AESL) for creating abstract event definitions, subscriptions and queries; a higherorder service (Abstract Event Detection Service) that accepts a subscription containing an abstract event definition as an argument and in return publishes an interface to a further service, an abstract event detector; and a satisfiability service that applies classical, logical satisfiability in order to check the satisfiability of the AESL definitions against the world model, in a manner similar to a constraint‐satisfaction problem.

The paper develops a model‐based approach, appropriate for distributed, heterogeneous environments.