Birdsong classification based on ensemble multi-scale convolutional neural network

Abstract

With the intensification of ecosystem damage, birds have become the symbolic species of the ecosystem. Ornithology with interdisciplinary technical research plays a great significance for protecting birds and evaluating ecosystem quality. Deep learning shows great progress for birdsongs recognition. However, as the number of network layers increases in traditional CNN, semantic information gradually becomes richer and detailed information disappears. Secondly, the global information carried by the entire input may be lost in convolution, pooling, or other operations, and these problems will weaken the performance of classification. In order to solve such problems, based on the feature spectrogram from the wavelet transform for the birdsongs, this paper explored the multi-scale convolution neural network (MSCNN) and proposed an ensemble multi-scale convolution neural network (EMSCNN) classification framework. The experiments compared the MSCNN and EMSCNN models with other CNN models including LeNet, VGG16, ResNet101, MobileNetV2, EfficientNetB7, Darknet53 and SPP-net. The results showed that the MSCNN model achieved an accuracy of 89.61%, and EMSCNN achieved an accuracy of 91.49%. In the experiments on the recognition of 30 species of birds, our models effectively improved the classification effect with high stability and efficiency, indicating that the models have better generalization ability and are suitable for birdsongs species recognition. It provides methodological and technical scheme reference for bird classification research.

Acoustic indices as proxies for bird species richness in an urban green space in Metro Manila

“…As acoustic indices were created to measure different characteristics of soundscapes quickly, they are not species-specific and lack sound recognition capabilities. For this reason, machine learning via convolutional neural networks (CNN) is increasingly being used in bioacoustic studies for birdsong classification [53][54][55]. Neural networks trained on Xeno-canto and Macaulay Library recordings have successfully classified North American and European bird species [53].…”

Deep Convolutional Neural Network for Automated Bird Species Classification

“…(5) Consistent Terminology: In order to ensure consistency and clarity, we can deal with deep learning architectures such as Convolutional Neural Networks (CNNs) in the examination [24]. CNNs are a type of deep network designed specifically for photo identification requirements.…”

Ornithological Imaging: Transforming Bird Species Identification with Technology

“…By advancing the capabilities of image-based bird species identification, we pave the way for more efficient and accurate biodiversity assessments, ultimately supporting global conservation initiatives. [4] created a novel model leveraging image processing techniques to recognize birds in aquaculture ponds, facilitating a more flexible distribution of predatory birds. Three image processing algorithmsimage morphology, artificial neural networks (ANN), and template matching-were designed and tested.…”

“…Figure 3: Schematic representation of the architecture of Convolutional Neural Network Related Work • Nadimpalli et al[4] created a novel model leveraging image processing techniques to recognize birds in aquaculture ponds, facilitating a more flexible distribution of predatory birds. Three image processing algorithmsimage morphology, artificial neural networks (ANN), and template matching-were designed and tested.…”