Video-based bird posture recognition using dual feature-rates deep fusion convolutional neural network

Lin, Chia-Hsien; Chen, Zhongsheng; Lin, Mengxiang

doi:10.1016/j.ecolind.2022.109141

Cited by 3 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5,6 The artificial intelligence (AI) techniques, like convolutional neural network [7][8][9] and artificial neural network, can help achieve these research goals. However, the geometric distortions caused by the birds' postures 10 and their rapid movements in the nature 6 along with the nature's lighting and structures generate problems and challenges to the AI techniques.…”

Section: Introductionmentioning

confidence: 99%

A frequency-driven deep learning technique for bird segmentation and detection from RGB video

Suthaharan

2023

Applications of Machine Learning 2023

View full text Add to dashboard Cite

The convolutional neuronal network (CNN) performs spatial learning on a two-dimensional data (e.g., images) using filters to learn features from the images. Hence it requires many images that have high discriminant spatial and longitudinal features, within and between classes for comprehensive learning. When this requirement is not met the CNN models suffer from the data paucity problem that leads to limited learning and poor classification performance. The segmentation and detection of birds from RGB videos to study the behavior of backyard birds is one of the applications that suffer from this data paucity problem. This paper first presents a new backyard birds' dataset that is extracted from RGB videos and consisted of the images of a cardinal and a sparrow to use it for developing an artificial neural network (ANN) model with a frequency-driven feature learning approach. It was observed that the images of these birds and their discriminant textures are geometrically distorted due to rapid movements and postures of these birds. These geometrical distortions bury the true representations of the main and the side lobs of the frequency spectrum of the images of the birds. To extract these latent features at different frequency bands and construct feature vectors for training an ANN model, Kaiser-Bessel window is used in the frequency domain along with the fast Fourier transform. Simulations show that by carefully selecting the model's parameters of the ANN model and the simulation parameters, we can achieve segmentation and detection of the cardinal and sparrow images with about 98% and 96% training and testing accuracy, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

A frequency-driven deep learning technique for bird segmentation and detection from RGB video

Suthaharan

2023

Applications of Machine Learning 2023

View full text Add to dashboard Cite

show abstract

Bird Action Recognition in Wetlands using Deep Learning

Rodriguez-Juan,

Berenguer-Agullo,

Benavent-Lledo

et al. 2024

Proceedings of the 2024 International Conference on Information Technology for Social Good

View full text Add to dashboard Cite

A Video Mosaicing-Based Sensing Method for Chicken Behavior Recognition on Edge Computing Devices

Teterja,

Garcia-Rodriguez,

Azorin-Lopez

et al. 2024

Sensors

View full text Add to dashboard Cite

Chicken behavior recognition is crucial for a number of reasons, including promoting animal welfare, ensuring the early detection of health issues, optimizing farm management practices, and contributing to more sustainable and ethical poultry farming. In this paper, we introduce a technique for recognizing chicken behavior on edge computing devices based on video sensing mosaicing. Our method combines video sensing mosaicing with deep learning to accurately identify specific chicken behaviors from videos. It attains remarkable accuracy, achieving 79.61% with MobileNetV2 for chickens demonstrating three types of behavior. These findings underscore the efficacy and promise of our approach in chicken behavior recognition on edge computing devices, making it adaptable for diverse applications. The ongoing exploration and identification of various behavioral patterns will contribute to a more comprehensive understanding of chicken behavior, enhancing the scope and accuracy of behavior analysis within diverse contexts.

show abstract

Video-based bird posture recognition using dual feature-rates deep fusion convolutional neural network

Cited by 3 publications

References 32 publications

A frequency-driven deep learning technique for bird segmentation and detection from RGB video

A frequency-driven deep learning technique for bird segmentation and detection from RGB video

Bird Action Recognition in Wetlands using Deep Learning

A Video Mosaicing-Based Sensing Method for Chicken Behavior Recognition on Edge Computing Devices

Contact Info

Product

Resources

About