MDPI Books
Go to cart
Reprint
Download Flyer

Application of Vision Technology and Artificial Intelligence in Smart Farming

Edited by
January 2024
270 pages
  • ISBN978-3-03928-597-6 (Hardback)
  • ISBN978-3-03928-598-3 (PDF)
https://doi.org/10.3390/books978-3-03928-598-3
Free download (PDF)

This book is a reprint of the Special Issue Application of Vision Technology and Artificial Intelligence in Smart Farming that was published in

Biology & Life Sciences
Engineering
Environmental & Earth Sciences
Summary

Artificial intelligence (AI) has been gaining traction in smart agriculture. Machine learning (ML) can be used for environmental and production performance data analysis and prediction, and computer vision (CV) can monitor abnormal phenotypes in plants and animals. They have massive potential to enhance the overall functioning of smart farming and reduce manual labor. This Special Issue focuses on the novel application of ML and CV in smart farming. The content of this Special Issue encompasses the use of various AI models for the in-depth analysis of quantitative data, RGB images, remote sensing images, and 3D point cloud data, thereby completing tasks such as environmental and growth state prediction, target recognition, and early disease diagnosis, improving crop growth performance and animal welfare.

Format
  • Hardback
License
© 2022 by the authors; CC BY-NC-ND license
Keywords
grain pest classification; visual attention mechanism; discrete wavelet transform; deep learning; computer vision; laying hens; feeding behavior; Faster R-CNN; model visualization; P. orientalis; recurrent neural network; inverse distance weighting; accumulated air temperature; dairy cow; individual identification; body pattern image; binarization; cascaded classification; Kinect; crop phenotypic; point cloud processing; three-dimensional reconstruction; singular value decomposition; mobile edge computing; convolutional neural network; deep reinforcement learning; wheat growth stages detection; dynamic migration algorithm; rice seed; variety classification; multimodal fusion; machine vision; point cloud; YOLOv5; deformable convolution; attention mechanism; visual detection system; Zanthoxylum-harvesting robot; soil moisture; prediction; XGBoost algorithm; SHAP; dual attention mechanism; multi-scale feature extraction; RFCA ResNet; classification; 3D reconstruction; the whole growth period; soybean; point cloud segmentation; dataset; bee mite; image processing; keypoint detection; image matching; cow udder classification; udder features; instance segmentation; CNN-LSTM; udder conformation; precision farming; smart farming; agricultural technology; Internet of Things (IoT); big data analytics; machine learning; artificial intelligence (AI); n/a