Linye kexue (1979), 2023-01, Vol.59 (8), p.112
2023
Volltextzugriff (PDF)
Details
- Autor(en) / Beteiligte
- Titel
- Wildlife Image Recognition in Miyun District Based on BS-ResNeXt-50
- Ist Teil von
- Linye kexue (1979), 2023-01, Vol.59 (8), p.112
- Ort / Verlag
- Beijing: Chinese Society of Forestry
- Erscheinungsjahr
- 2023
- Quelle
- Alma/SFX Local Collection
- Beschreibungen/Notizen
- [Objective】In the wild environment, the background of wildlife images captured by camera traps is complex,which poses a challenge for identifying wild animals in images with a large number of images and a wide variety of wildlife species. Based on convolutional neural network, this research aims to improve the existing structure and so as to implement the automatic recognition for wildlife images.【Method】In this study, 2 712 wildlife images of 8 categories were taken from Wuling Mountain Beijing Nature Reserve, Miyun Districts, Beijing. The Auto Augment policy was randomly selected from 14augmentation policies to add noise to the images. SENet and BlurPool were used to construct an improved network based on ResNeXt-50: SE-ResNeXt-50 for enhancement feature extraction, BP-ResNeXt-50 for Shift-invariance maintenance, and BSResNeXt-50 for both. The influences of fixed learning rate, segmented learning rate, and cosine annealing learning rate on the accuracy of the BS ResNeXt-50 network were tested on the self-bu
- Sprache
- Chinesisch
- Identifikatoren
- ISSN: 1001-7488Titel-ID: cdi_proquest_journals_2879595681
- Format
- –
- Schlagworte
- Accuracy, Annealing, Artificial neural networks, Categories, Datasets, Feature extraction, Invariance, Learning, Maintenance, Nature reserves, Neural networks, Species, Training, Wild animals, Wildlife