Xiuhua Li
Guangxi University
10 Papers
4 Citations
Xiuhua Li is an academic researcher from Guangxi University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 1, co-authored 1 publications.
Chat about Author
Papers
Key technologies of machine vision for weeding robots: A review and benchmark
TL;DR: In this article , a review of machine-vision-based weeding robots is presented, which provides an understanding of innovative trends in the use of machine vision in weeding systems and references for future research.
80
Integrate MSRCR and Mask R-CNN to Recognize Underwater Creatures on Small Sample Datasets
TL;DR: This work proposes a new method for recognition of underwater creatures that combines the MSRCR (multi-scale Retinex with color restoration) image enhancement algorithm and the Mask R-CNN (region-based convolutional neural work) framework, and achieves a mAP value higher than 90% on a small sample dataset.
Sugarcane Nitrogen Concentration and Irrigation Level Prediction Based on UAV Multispectral Imagery
TL;DR: In this paper, the potential of UAV multispectral images in predicting canopy nitrogen concentration (CNC) and irrigation levels for sugarcane was investigated. And the results of this study demonstrated that high resolution multi-spectral images could provide effective information for CNC prediction and water irrigation level recognition.
Identification and Counting of Sugarcane Seedlings in the Field Using Improved Faster R-CNN
TL;DR: Wang et al. as discussed by the authors proposed a method based on improved Faster RCNN for automatically detecting and counting sugarcane seedlings using aerial photography, which can provide accurate seedling data, thus can support farmers making proper cultivation management decision.
WeedNet-R: a sugar beet field weed detection algorithm based on enhanced RetinaNet and context semantic fusion
TL;DR: The proposed WeedNet-R, a vision-based network for weed identification and localization in sugar beet fields, is proposed, which outperforms other sophisticated object detection algorithms in terms of detection accuracy while matching other single-stage detectors in Terms of detection speed.
15