A Comprehensive Review on Recent Advances in Bird Species Identification using Computer Vision and Acoustics
Year: 2025
Type: article
Abstract: As part of ornithology, bird species classifications is vital to understanding biodiversity, the functions of ecosystems, species distribution, habitat requirements, environmental changes and to develop effective conservation strategies that affect bird populations. It is possible for ornithologists to assess the health of a certain habitat by tracking changes in bird species distributions. This work has studied (A) an efficient transfer learning technique for labelling and classifying multiple bird species from real-time audio recordings. For this purpose, Wav2vec is fine-tuned using the back propagation technique, which makes the feature extractor more effective in learning each bird's pitch and other sound characteristics. To perform the task, each audio recording has been clipped as chunks from the overlapping audio to determine multi-labels from it using feed forward technique. (B) The positional relationships extracted from various acoustic features as model inputs, and feature fusion was applied to obtain the final set of feature vectors. Feature fusion combines the deep features extracted by various networks, resulting in a more comprehensive feature set, thereby improving recognition accuracy. The multiple integrated acoustic features, such as Mel frequency cepstral coefficients (MFCC), chroma features (Chroma) and Tonnetz features, which were encoded by a transformer encoder. (C) A deep learning based algorithms using the concept of image processing that help in identifying bird species. It will recognize the input image by comparing the model with a trained model and then predict the bird species. All the details of the bird will be displayed as an output. Also, it will help us to create dataset if any image captured or uploaded by user is missing in dataset then user can add that image to dataset. (D) A new image classification method for bird species identification. The extraction of the features of a bird and trained a convolutional neural network on the biggest publicly available dataset with novel preprocessing and data augmentation methods.
Authors: Jadhao, Dr. A. P., Wath, Darshana M., Bhopale, Pranjali P., Adole, Snehal C., Giri, Prerana R.
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6893290564
FWCI:
Cites:
Cited by:
Related to: