Automated acoustic detection of Vanellus chilensis lampronotus

Ganchev, Todor; Jahn, Olaf; Marques, Marinêz Isaac; Figueiredo, Josiel Maimone de; Schuchmann, Karl‐Ludwig

doi:10.1016/j.eswa.2015.03.036

Cited by 35 publications

(26 citation statements)

References 23 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies use Frogloggers (construction manual given by Peterson & Dorcas 1994;e.g., Acevedo & Villanueva-Rivera 2006;Akmentins et al 2014) or the Songmeter recorders (Wildlife Acoustics Inc.; e.g., Lehmann et al 2014;Zwart et al 2014;Ganchev et al 2015;Jansen et al 2016b). For the automatic detection of particular animal sounds there is a variety of algorithms that can be used, and several programs on the market have already implemented species identification tools for several taxonomic groups (Ganchev et al 2015). Although it is not in the focus of this paper to evaluate this increasing body of software, algorithms or machine learning techniques for signal detection (Acevedo et al 2009;Huang et al 2009), we will give some commonly used examples -without evaluating their efficiency.…”

Section: Automated Recording and Signal Recognitionmentioning

confidence: 99%

The use of bioacoustics in anuran taxonomy: theory, terminology, methods and recommendations for best practice

Köhler

Jansen

Rodríguez³

et al. 2017

Zootaxa

421

396

View full text Add to dashboard Cite

Vocalizations of anuran amphibians have received much attention in studies of behavioral ecology and physiology, but also provide informative characters for identifying and delimiting species. We here review the terminology and variation of frog calls from a perspective of integrative taxonomy, and provide hands-on protocols for recording, analyzing, comparing, interpreting and describing these sounds. Our focus is on advertisement calls, which serve as premating isolation mechanisms and, therefore, convey important taxonomic information. We provide recommendations for terminology of frog vocalizations, with call, note and pulse being the fundamental subunits to be used in descriptions and comparisons. However, due to the complexity and diversity of these signals, an unequivocal application of the terms call and note can be challenging. We therefore provide two coherent concepts that either follow a note-centered approach (defining uninterrupted units of sound as notes, and their entirety as call) or a call-centered approach (defining uninterrupted units as call whenever they are separated by long silent intervals) in terminology. Based on surveys of literature, we show that numerous call traits can be highly variable within and between individuals of one species. Despite idiosyncrasies of species and higher taxa, the duration of calls or notes, pulse rate within notes, and number of pulses per note appear to be more static within individuals and somewhat less affected by temperature. Therefore, these variables might often be preferable as taxonomic characters over call rate or note rate, which are heavily influenced by various factors. Dominant frequency is also comparatively static and only weakly affected by temperature, but depends strongly on body size. As with other taxonomic characters, strong call divergence is typically indicative of species-level differences, whereas call similarities of two populations are no evidence for them being conspecific. Taxonomic conclusions can especially be drawn when the general advertisement call structure of two candidate species is radically different and qualitative call differences are thus observed. On the other hand, quantitative differences in call traits might substantially vary within and among conspecific populations, and require careful evaluation and analysis. We provide guidelines for the taxonomic interpretation of advertisement call differences in sympatric and allopatric situations, and emphasize the need for an integrative use of multiple datasets (bio-acoustics, morphology, genetics), particularly for allopatric scenarios. We show that small-sized frogs often emit calls with frequency components in the ultrasound spectrum, although it is unlikely that these high frequencies are of biological relevance for the majority of them, and we illustrate that detection of upper harmonics depends also on recording distance because higher frequencies are attenuated more strongly. Bioacoustics remains a prime approach in integrative taxonomy of anurans if uncertainty due to possible intraspecific variation and technical artifacts is adequately considered and acknowledged.

show abstract

Section: Automated Recording and Signal Recognitionmentioning

confidence: 99%

The use of bioacoustics in anuran taxonomy: theory, terminology, methods and recommendations for best practice

Köhler

Jansen

Rodríguez³

et al. 2017

Zootaxa

421

396

View full text Add to dashboard Cite

show abstract

“…Among the change feature learning methods, physically-meaningful features and learned change features both lead to a good performance and have been applied in various domains. As physically-meaningful features, vegetation indices, forest canopy variables and water indices are often extracted to identify changes in specific ground-object types [12,13]. For learned features and transformations, various features or transformed feature spaces are learned to highlight the change information to detect a changed region more easily than when using the original spectral information of multi-temporal images, such as in Principal Component Analysis (PCA) [14], Multivariate Alteration Detection (MAD) [15], subspace learning [16,17], sparse learning [18] and slow features [19].…”

Section: Introductionmentioning

confidence: 99%

Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

2016

View full text Add to dashboard Cite

When exploited in remote sensing analysis, a reliable change rule with transfer ability can detect changes accurately and be applied widely. However, in practice, the complexity of land cover changes makes it difficult to use only one change rule or change feature learned from a given multi-temporal dataset to detect any other new target images without applying other learning processes. In this study, we consider the design of an efficient change rule having transferability to detect both binary and multi-class changes. The proposed method relies on an improved Long Short-Term Memory (LSTM) model to acquire and record the change information of long-term sequence remote sensing data. In particular, a core memory cell is utilized to learn the change rule from the information concerning binary changes or multi-class changes. Three gates are utilized to control the input, output and update of the LSTM model for optimization. In addition, the learned rule can be applied to detect changes and transfer the change rule from one learned image to another new target multi-temporal image. In this study, binary experiments, transfer experiments and multi-class change experiments are exploited to demonstrate the superiority of our method. Three contributions of this work can be summarized as follows: (1) the proposed method can learn an effective change rule to provide reliable change information for multi-temporal images; (2) the learned change rule has good transferability for detecting changes in new target images without any extra learning process, and the new target images should have a multi-spectral distribution similar to that of the training images; and (3) to the authors' best knowledge, this is the first time that deep learning in recurrent neural networks is exploited for change detection. In addition, under the framework of the proposed method, changes can be detected under both binary detection and multi-class change detection.

show abstract

“…Between July 2012 and October 2014 we used Song Meter SM2+ recorders (Wildlife Acoustics 5 ) for soundscape collection in 24/7 mode, in total ca. 90 TB of audio recordings with a file duration of 14-30 min, 48-kHz sampling rate, and 16-bit resolution [34]. We completed one annual cycle of recordings each at Fazenda Pouso Alegre (À16.50303 S, À56.74533 W; 115-126 m a.s.l.…”

Section: Study Areamentioning

confidence: 99%

“…manually, and thus contain competing sounds from multiple species and certain interferences of abiotic origin. Each recording was time-stamped and tagged on the level of V. chilensis call series by a bird-sound expert [34]. In brief, the annotation procedure can be summarized as follows:…”

Section: Chilensis Validation Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Bird acoustic activity detection based on morphological filtering of the spectrogram

et al. 2015

Self Cite

View full text Add to dashboard Cite

Automated acoustic detection of Vanellus chilensis lampronotus

Cited by 35 publications

References 23 publications

The use of bioacoustics in anuran taxonomy: theory, terminology, methods and recommendations for best practice

The use of bioacoustics in anuran taxonomy: theory, terminology, methods and recommendations for best practice

Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection

Bird acoustic activity detection based on morphological filtering of the spectrogram

Contact Info

Product

Resources

About