![]() A related relevant issue is automatic classification, for example categorizing the vessels detected, for example, according to their size (small, medium, large). Nonetheless, improving detection accuracy in noisy conditions and reducing the rate of false positives remain as challenges. While some solutions have employed classification approaches derived from the analysis of acoustic features (Leal, Leal, & Sanchez, 2015), others have focused on the specific spectral signatures of the sounds emitted by the different types of vessels, for example training neural networks to detect a set of known signatures (Chung, Sutin, Sedunov, & Bruno, 2011 Hanson, Antoni, Brown, & Emslie, 2008 Pollara, Lignan, Boulange, Sutin, & Salloum, 2017 Slamnoiu et al., 2016). This has motivated many research efforts towards devising methods to automatically detect the presence of vessels in underwater acoustic recordings. However, manual inspection of collections of audio recordings obtained over extensive time periods is not feasible, in view of the time and human effort it demands. They may interfere with species communication (Wittekind & Schuster, 2016), echolocation mechanisms (Veirs, Veirs, & Wood, 2016) and threaten fish population growth (Jain-Schlaepfer et al., 2018).Įcological audio recorders and hydrophones offer a cost-effective method for ocean monitoring in order to identify undesirable or threatening scenarios. It thus provides a solution to automate the detection of vessels, with potential applications for monitoring marine preservation areas.Īudio signals emitted by boats, ships and water crafts in general can strongly impact marine life. Besides being effective, the algorithm requires limited user input and no parameter fine tuning to handle diverse situations.We evaluated the algorithm on a database of underwater recordings collected at two conservation areas in the State of São Paulo, Brazil, with very good results, and also compared it with an existing solution.In this paper, we introduce an algorithm for boat and ship detection which computes an acoustic signature that captures the variance in the frequency amplitudes observed over the duration of the signal.The task is particularly challenging because it requires distinguishing multiple overlapping acoustic events in typically noisy audio recordings. Automated solutions are particularly relevant for monitoring preservation areas where the presence of watercrafts is usually regulated. Automatic detection of boat signatures in underwater audio recordings is thus an important task. ![]() ![]() ![]() Sound emissions by ships and boats can strongly impact marine life, with potential to affect communications, breeding and prey and predator relationships. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |