Detecting bird sounds in a complex acoustic environment and application to bioacoustic monitoring
Introduction
In order to evaluate the impact of human activities on populations of wild animals and to decide on the most effective actions for nature conservation, we need fundamental information on the extent of changes in the living environment. Birds are a good indicator for changes in biodiversity because they are distributed over a wide range of landscapes, are easy to detect in comparison to other animal groups and we have a good knowledge on the biology of most of the species. It is a fortunate fact that, at least in most European countries, we have huge associations of skilled and experienced birdwatchers, who willingly give their knowledge to non-profit service and support monitoring programs. Due to the activity of birdwatchers, data regarding trends in population sizes for certain European bird species has been recorded and made available since 1980 (Gregory et al., 2005). Different standardised methods for bird census have been developed (Bibby et al., 1992). Most of them are based on the mapping of singing males, assuming that the number of territorial males is equal to the number of breeding pairs. The most widely used method for estimating the number of breeding birds is based on point counts where all individuals heard and seen from stationary places are estimated (Klvaňová and Voříšek, 2007).
Complementing traditional approaches, vocalisations of birds serving for territory maintenance and mate attraction can be used for an automated acoustic monitoring of bird populations (Brandes, 2008, Frommolt et al., 2008). The main advantage of such an automated bioacoustic approach, as compared to previous methods, lies in the long-term recording in the absence of an observer. It allows to estimate bird numbers in ecologically sensitive areas (like nature reserves) or in areas that are difficult to access (for example large reed habitats). Even nocturnal birds and birds with low vocal activity could thus be effectively counted. In addition to the need of an applicable autonomous recording device, the greatest challenge is the development of appropriate pattern recognition algorithms giving reliable results even in complex acoustic environments. In order to apply acoustic methods for the monitoring of bird species, we have to solve two problems. We need pattern recognition algorithms for the automatic detection and identification of bird species and we need appropriate techniques for the estimation of the number of individuals.
Acoustic pattern recognition algorithms have been successfully applied to the study of nocturnal migrations of birds (Evan and Mellinger, 1999, Farnsworth et al., 2004, Farnsworth, 2005, Farnsworth and Russel, 2007, Hüppop et al., 2006, Mills, 2000, Hill and Hüppop, 2008, Schrama et al., 2008, Marcarini et al., 2008). However, these works mostly deal with relatively simple signals without background noise. The number of detected calls was used as a criterion to assess the occurrence of migrating birds. For noisy environments, hidden Markov models were successfully applied to frequency modulated sounds (Brandes, 2008, Trifa et al., 2008).
In this work we report about an approach using pattern recognition techniques for continuous bird monitoring. Our techniques are based on event detection and repetition rate estimation of bird song elements. Additionally, the algorithms use noise estimation from frequency bands known not to contain the bird’s vocalisations and apply them to an effective noise reduction. They can be used in parallel with traditional monitoring methodology to yield methods with improved speed and reproducibility in those cases where reliable detectors for bird vocalisations are available. In contrast to other applications our algorithms have been designed specifically for certain endagered target species. This approach was chosen in order to improve recognition rates even under poor acoustic conditions and it leads to a larger range covered by a single sensor unit in comparison to human observers and algorithms requiring high signal-to-noise ratios. Moreover, we apply this methodology to a quantitative survey of a real bird population yielding automatic map generation of breeding territories for one of the considered bird species.
In Section 2 we summarise related work in the field of pattern recognition for animal sounds. Approaches for the detection of the vocalisations of two endangered bird species are developed in Section 3. These algorithms have been evaluated in a study described in Section 4, which also gives evaluation results. These results are sufficient for automatic map generation of breeding territories for one of the bird species investigated. Results of a corresponding study are presented in Section 5. Finally, conclusions are given in Section 6.
Section snippets
Pattern recognition for animal sounds
In comparison to other fields in pattern recognition, little work has been carried out regarding animal sound recognition. Nevertheless, a wide variety of methods and animal species have been examined. In previous studies, bird song recognition with hidden Markov models has been proven to be a useful tool in the recognition of bird song elements (Kogan et al., 1998). In this case, recordings were made under laboratory conditions with captive birds and microphones close to the cages.
The most
Bird song detectors
In this section, we describe algorithms designed for the purpose of detecting the presence of species specific vocalisations. The two target species, the Eurasian bittern (Botaurus stellaris) and the Savi’s warbler (Locustella luscinioides), were chosen for their value for nature conservation. They are indicator species for extended reed beds. The two types of special purpose algorithms described in this section are tailored for different types of signals. The first algorithm to be described
Results for a real-world monitoring scenario
In order to evaluate our pattern recognition algorithms, we applied it to recordings attained at Lake Parstein in the north-east of Germany (federal state Brandenburg) in 2006 and 2007. The northern part of the lake is surrounded by extended reed belts providing breeding habitats for the two target species. Recording was conducted in a project with the aim to examine the applicability of pattern recognition methods as a tool for monitoring bird vocalisations. A four-channel stationary
Application of bird song detectors to the monitoring of Savi’s warblers
In our work, we could already successfully apply the pattern recognition algorithm for the Savi’s warbler described above to the monitoring of the population of this species at our study site at Lake Parstein. For this purpose, we examined songposts of the warblers at two different reed areas three times each year during the breeding seasons in the period from April to June in 2007 and 2008. In order to cover a more extended area, we decided to use a slow-moving small boat equipped with an
Conclusion
The computational evaluation of monitoring recordings introduces potent technology complementary to the existing means for assessing animal populations. Using robust feature extraction methods, the detectors introduced in the preceding sections feature a high detection precision even when used with badly conditioned recordings.
For less specific animal population surveys, the introduced features may be combined and used for the detection of a wider range of animal species. Several approaches to
Acknowledgements
The study was supported by grants from the German Federal Agency for Nature Conservation (BfN, Grant 806 82 060 - K2) and the foundation NaturschutzFonds Brandenburg (Grant 557). During the accomplishment of the study, R. Bardeli and D. Wolff have been members of the Multimedia Signal Processing Group at the Computer Science Department of the University of Bonn headed by M. Clausen.
References (41)
- et al.
Radial basis function neural networks and temporal fusion for the classification of bio acoustic time series
Neurocomputing
(2003) - et al.
Bird Census Techniques
(1992) Automated sound recording and analysis techniques for bird survey and conservation
Bird Conserv. Internat.
(2008)Feature vector selection and use of hidden markov models to identify frequency-modulated bioacoustic signals admidst noise
IEEE Trans. Audio, Speech, Language Process.
(2008)- et al.
Using image processing to detect and classify narrow-band cricket and frog calls
J. Acoust. Soc. Amer.
(2006) - et al.
Automatic classification of killer whale vocalizations using dynamic time warping
J. Acoust. Soc. Amer.
(2007) - et al.
Quantifying complex patterns of bioacoustic variation: Use of a neural network to compare killer whale (orcinus orca) dialects
J. Acoust. Soc. Amer.
(1999) - Deller, J., Proakis, J., Hanson, J., 1993. Discrete-time Processing of Speech Signals. Prentice-Hall, New...
- et al.
Monitoring grassland birds in nocturnal migration
Stud. Avian Biol.
(1999) - Fagerlund, S., 2007. Bird species recognition using support vector machines. EURASIP J. Appl. Signal Process. (EURASIP...