Automatically recognizing four-legged animal behaviors to enhance welfare using spatial temporal graph convolutional networks

Zhao, Yaqin; Feng, Liqi; Tang, Jiaxi; Zhao, Wenxuan; Ding, Zhipeng; Li, Ao; Zheng, Zhaoxiang

doi:10.1016/j.applanim.2022.105594

Cited by 8 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Not only did we construct the first skeleton-based sub-dataset, but we also proposed a GCN (graph convolutional network)-based mammal behavior recognition method [60]. We randomly divided the animal behavior dataset into 10 subsets and selected nine subsets as the training set and the remaining one as the validation set.…”

Section: Experimental Results For Action Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

MammalClub: An Annotated Wild Mammal Dataset for Species Recognition, Individual Identification, and Behavior Recognition

Lu,

Zhao,

Wang

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

Mammals play an important role in conserving species diversity and maintaining ecological balance, so research on mammal species composition, individual identification, and behavioral analysis is of great significance for optimizing the ecological environment. Due to their great capabilities for feature extraction, deep learning networks have gradually been applied to wildlife monitoring. However, training a network requires a large number of animal image samples. Although a few wildlife datasets contain many mammals, most mammal images in these datasets are not annotated. In particular, selecting mammalian images from vast and comprehensive datasets is still a time-consuming task. Therefore, there is currently a lack of specialized datasets of images of wild mammals. To address these limitations, this article created a mammal image dataset (named MammalClub), which contains three sub-datasets (i.e., a species recognition sub-dataset, an individual identification sub-dataset, and a behavior recognition sub-dataset). This study labeled the bounding boxes of the images used for species recognition and the coordinates of the mammals’ skeletal joints for behavior recognition. This study also captured images of each individual from different points of view for individual mammal identification. This study explored novel intelligent animal recognition models and compared and analyzed them with the mainstream models in order to test the dataset.

show abstract

Section: Experimental Results For Action Recognitionmentioning

confidence: 99%

“…We proposed novel methods based on deep learning for species recognition, individual recognition, and action recognition, respectively [54,60,61]. We conducted experiments on our dataset with the proposed methods and other state-of-the-art methods for a comparison under the same experimental configuration.…”

Section: Methodsmentioning

confidence: 99%

MammalClub: An Annotated Wild Mammal Dataset for Species Recognition, Individual Identification, and Behavior Recognition

Lu,

Zhao,

Wang

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…AI(artificial intelligence) can make up for the shortcomings of human vision, such as incomplete capture and easy fatigue, automatically capture and analyze the objects in the field of vision, and monitor and evaluate the whole inspection process. As a kind of structured data, medical images are easy to be processed and learned by deep learning [4][5] . With the rapid development of deep learning, computer-aided screening and diagnosis using deep learning technology has been carried out in many medical research fields.…”

Section: Introductionmentioning

confidence: 99%

Construction of gastroscope image recognition model and diagnosis system based on artificial intelligence technology

Huang

Jiang

2023

Sixth International Conference on Intelligent Computing, Communication, and Devices (ICCD 2023)

View full text Add to dashboard Cite

In recent years, AI(artificial intelligence) technology has been applied to the diagnosis of diseases such as lung cancer, skin cancer and diabetic retinopathy, and has shown excellent diagnostic performance. AI technology with deep learning as the core can make full use of massive data, automatically learn the features in the data, and assist doctors in diagnosis accurately and quickly. Gastric cancer has a high degree of malignancy, hidden onset and no specific symptoms in the early stage. Its clinical manifestations are often similar to benign gastric diseases such as gastric ulcer and chronic gastritis, and it is easy to be ignored. In this paper, the gastroscope image recognition model and diagnosis system based on AI technology are developed. In this study, a gastroscope image recognition model based on GCN (Graph Convolutional Networks) is proposed. The GCN multi-label classification module is responsible for learning and representing the physiological and anatomical relationship of the upper digestive tract, and fusing the learning results with the output results of the detection module. Finally, a gastroscope image aided diagnosis system is designed and implemented. The results showed that the sensitivity and PPV of the model were 95.360% and 91.017%, respectively. It is suggested that the model is superior to the traditional method in the detection rate of early cancer lesions.

show abstract

“…Many researchers study ecosystem conservation using animals as observation objects [1], [2], [3], [4], [5]. The ecological quality of the natural environment can be assessed by counting the changes of animals populations [6], [7], [8], [9].…”

Section: Introductionmentioning

confidence: 99%

Wild Bird Species Identification Based on a Lightweight Model with Frequency Dynamic Convolution

et al. 2023

View full text Add to dashboard Cite

The sound recognition technology is used to count bird speciespopulation to provide accurate data for population ecology and conservation biology research. Bird species can be identified by spectrogram of bird's sounds. The existing Convolutional Neural Network(CNN) is not good at mining the relationship between features in time-frequency tasks, and the existing CNN has more parameters and complicated calculation, so existing models are not suitable for deployment in an actual field environment. In order to fill this gap, this paper proposes a lightweight model with frequency dynamic convolution for bird species identification. We use frequency dynamic convolution innovatively to better capture features of bird sounds at different frequencies. First of all, we replaced two-dimensional convolution with frequency-dynamic convolution in order to achieve not-shift invariance of the bird sound's spectrogram, so that we can effectively capture the feature differences of spectrogram in different frequency bands. Then, we replaced part of the Squeeze and Excitation(SE) attention mechanism with the Coordinate Attention(CA) attention mechanism in order to get more comprehensive global information. Finally, the feature fusion module was used to fuse the local and global features. In addition, we built a datasets containing 160 bird sounds, improving the generalization ability of the model. The experimental results show that our model has good generalization ability and is superior to the existing Lightweight CNN, and obtained better results in top1 accuracy and top5 accuracy.

show abstract

Automatically recognizing four-legged animal behaviors to enhance welfare using spatial temporal graph convolutional networks

Cited by 8 publications

References 17 publications

MammalClub: An Annotated Wild Mammal Dataset for Species Recognition, Individual Identification, and Behavior Recognition

MammalClub: An Annotated Wild Mammal Dataset for Species Recognition, Individual Identification, and Behavior Recognition

Construction of gastroscope image recognition model and diagnosis system based on artificial intelligence technology

Wild Bird Species Identification Based on a Lightweight Model with Frequency Dynamic Convolution

Contact Info

Product

Resources

About