S
Shuo Zhuang
Researcher at Tianjin University
Publications - 12
Citations - 199
Shuo Zhuang is an academic researcher from Tianjin University. The author has contributed to research in topics: Convolutional neural network & Feature (computer vision). The author has an hindex of 5, co-authored 12 publications receiving 106 citations. Previous affiliations of Shuo Zhuang include Hefei University of Technology.
Papers
More filters
Journal ArticleDOI
Early detection of water stress in maize based on digital images.
TL;DR: A model to detect water stress of maize in the early stage based on a supervised learning algorithm, gradient boosting decision tree (GBDT), which had an effective detection performance between water suitability and water stress conditions in the maize fields.
Journal ArticleDOI
Human fall detection using slow feature analysis
Kaibo Fan,Ping Wang,Shuo Zhuang +2 more
TL;DR: A novel slow feature analysis based framework for fall detection in a house care environment that is comparable to other state-of-the-art methods on the multiple-camera fall dataset and the SDUFall dataset.
Journal ArticleDOI
A Single Shot Framework with Multi-Scale Feature Fusion for Geospatial Object Detection
TL;DR: A large-scale remote-sensing dataset for geospatial object detection (RSD-GOD) that consists of 5 different categories with 18,187 annotated images and 40,990 instances is constructed and a single shot detection framework with multi-scale feature fusion is designed.
Journal ArticleDOI
Detection of maize drought based on texture and morphological features
TL;DR: This work proposes a method for detecting drought in maize from three aspects: colour, texture and plant morphology via computer vision, which has good adaptability to light conditions in different periods of the day.
Journal ArticleDOI
Learned features of leaf phenotype to monitor maize water status in the fields
TL;DR: Inspired by deep learning, a convolutional neural network is applied for the first time to maize water stress recognition and Experimental results demonstrate that the learned features perform better than hand-crafted features to detect water stress and quantify stress severity.