ABSTRACT
The study of animal behavior can provide a basis for ecological researchers to help them formulate more reasonable and targeted ecological protection strategies. In this paper, the feature detection method based on cascade convolutional neural network is applied to the detection of animal features. By analyzing the general flow of convolutional neural networks, the researchers designed a cascade convolutional neural network with three hierarchical structures. Each hierarchical structure has multiple convolutional networks, which perform the same or different operations respectively. In order to make up for the defects of neural network in reasoning, this paper uses Bayesian network to infer and estimate in the analysis of features. Through experiments on the proposed method on a self-built data set, the results show that the overall accuracy of the animal behavior estimation method based on CCNN and BN proposed in this paper is more than 85%, and compared with general methods, this method has the advantages of fast learning speed, accurate feature location, and high accuracy of behavior estimation.
- Mackenzie Weygandt Mathis, Alexander Mathis (2020). Deep learning tools for the measurement of animal behavior in neuroscience, Current Opinion in Neurobiology, 60:1--11.Google ScholarCross Ref
- Yousif H, Yuan J, Kays R, He Z (2019). Animal Scanner: Software for classifying humans, animals, and empty frames in camera trap images. Ecology and evolution, 9(4):1578--1589.Google Scholar
- Michael A. Tabak, et al. (2019). Machine learning to classify animal species in camera trap images: Applications in ecology, Methods in Ecology and Evolution, 10(4):585--590.Google ScholarCross Ref
- Nguyen, Hung, et al. Animal Recognition and Identification with Deep Convolutional Neural Networks for Automated Wildlife Monitoring, 10.1109/DSAA.2017.31.Google Scholar
- Zhongqi Miao, Kaitlyn M. Gaynor, Jiayun Wang, et al. (2019). Insights and approaches using deep learning to classify wildlife, https://doi.org/10.1038/s41598-019-44565-wGoogle Scholar
- Yinan Gong, Mengyu Tan, Zhen Wang, et al. (2019). AI recognition of infrared camera image of wild animals based on deep learning: Northeast Tiger and Leopard National Park for example, Acta Theriologica Sinica, 39(4):458--465Google Scholar
- Junwei, Zhai, Detection Method of Hoh Xil Tibetan Antelope Based on Image Processing [Chinese Master's thesis], Xi'an: Xidian University: 2018, 83p.Google Scholar
- I. Cohen, F. G. Cozman, N. Sebe et al. (2003), Semi-supervised learning of classifiers: theory, algorithms for Bayesian network classifiers and application to human-computer interaction, IEEE Transactions on Pattern Analysis and Machine Intelligence, 26: 1553--1566.Google ScholarDigital Library
- E. N. Mortensen, and J. Jia. Real-time semi-automatic segmentation using a Bayesian network, IEEE Conference on Computer Vision and Pattern Recognition, 2006.Google ScholarDigital Library
- B. Banerjee, A. Bisjee, A. Biswas (2000). Using Bayesian Networks to Model Agent Relationships. Applied Artif. Intelligence Journal. 14(9):867--880.Google ScholarCross Ref
- Chongyi Li and Jichang Guo and Fatih Porikli, et al. (2018), A Cascaded Convolutional Neural Network for Single Image Dehazing, https://arxiv.org/abs/1803.07955Google Scholar
- Scott E. Fahlman and Christian Lebiere. 1990. The cascade-correlation learning architecture. Advances in neural information processing systems 2. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 524--532.Google ScholarDigital Library
- Yang, W., Zhou, L., Li, T. et al. (2019), A Face Detection Method Based on Cascade Convolutional Neural Network. Multimed Tools Appl 78, 24373--24390. https://doi.org/10.1007/s11042-018-6995-0Google ScholarDigital Library
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, et al. (2016), SSD: Single Shot MultiBox Detector, https://doi.org/10.1007/978-3-319-46448-0_2Google Scholar
- VOC2012, http://host.robots.ox.ac.uk/pascal/VOC/voc2012/Google Scholar
- Sara Beery, Dan Morris, Pietro Perona (2019). The iWildCam 2019 Challenge Dataset, https://arxiv.org/abs/1907.07617Google Scholar
Index Terms
- An Animal Behavior State Estimation Method Using CCNN and BN Based System
Recommendations
Camera Pose Estimation Method Based on Deep Neural Network
ICDLT '19: Proceedings of the 2019 3rd International Conference on Deep Learning TechnologiesThis paper proposes a camera pose estimation algorithm based on deep neural network, which returns the translation and rotation of the camera based on supervised deep learning. This paper uses the ORB algorithm to extract the feature points of the image,...
Classifying animal behavior from accelerometry data via recurrent neural networks
AbstractWe study the classification of animal behavior from accelerometry data using various recurrent neural network (RNN) models. RNNs have extensively been employed to classify time-series data in various applications. However, their ...
Highlights- We develop RNN-based models for animal behavior classification via IMU sensor data.
Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network
AbstractTime series prediction problems are a difficult type of predictive modeling problem. In this paper, we propose a time series prediction method based on a variant long short-term memory (LSTM) recurrent neural network. In the proposed method, we ...
Comments