Skip to content
Research Article Open access CC BY 4.0

Development of Invasive Plant Recognition System Based on Deep Learning

Zhuolei Yang, Zheming Fan, Chenyu Niu, Peixin Li, Hongjie Zhong

Journal of Advances in Mathematics and Computer Science · pp. 39–53 · Published 29 Mar 2023

10.9734/jamcs/2023/v38i61767

Abstract

A major ecological issue that has seriously harmed both human society and the environment is the invasion of alien plants. To stop the invasion of alien plants, it is crucial to create an effective and precise monitoring and early warning system. In this situation, deep learning and computer vision have significant potential to enhance plant monitoring on a wide scale. This study suggests a deep learning-based approach for identifying invasive plants. The user interface is developed as a mobile application (APP). The identification result can be acquired in 1 to 2 seconds after downloading the plant image from the APP, uploading it to the server, and using the convolutional neural network (CNN). The system had an average accuracy of 90.39% on the test set thanks to data augmentation and enhanced networks. The deep learning-based invasive plant identification system created in this study has demonstrated through experiments that it may effectively support botanical research and ecological environment monitoring.

Alien plant deep learning mobile client CNN image recognition

References (24)

  1. 1 Deep Residual Learning for Image Recognition [DOI]
  2. 2 Going deeper with convolutions [DOI]
  3. 3 Densely Connected Convolutional Networks [DOI]
  4. 4 Microsoft COCO: Common Objects in Context [DOI]
  5. 5 Histograms of Oriented Gradients for Human Detection [DOI]
  6. 6 MobileNetV2: Inverted Residuals and Linear Bottlenecks [DOI]
  7. 7 Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [DOI]
  8. 8 BRST Cohomology of the Chapline-Manton Model [DOI]
  9. 9 Review on Convolutional Neural Networks (CNN) in vegetation remote sensing [DOI]
  10. 10 Weed detection in soybean crops using ConvNets [DOI]
  11. 11 Internet of things for smart agriculture: Technologies, practices and future direction [DOI]
  12. 12 Automation in Agriculture by Machine and Deep Learning Techniques: A Review of Recent Developments [DOI]
  13. 13 Deep learning techniques to classify agricultural crops through UAV imagery: a review [DOI]
  14. 14 Deep Learning with Unsupervised Data Labeling for Weed Detection in Line Crops in UAV Images [DOI]
  15. 15 Convolutional Neural Networks enable efficient, accurate and fine-grained segmentation of plant species and communities from high-resolution UAV imagery [DOI]
  16. 16 Computer vision based detection of external defects on tomatoes using deep learning [DOI]
  17. 17 Image-based orchard insect automated identification and classification method [DOI]
  18. 18 Local feature-based identification and classification for orchard insects [DOI]
  19. 19 Intelligent alerting for fruit-melon lesion image based on momentum deep learning [DOI]
  20. 20 A Review of Deep Learning-Based Visual Multi-Object Tracking Algorithms for Autonomous Driving [DOI]
  21. 21 Fruit recognition based on pulse coupled neural network and genetic Elman algorithm application in apple harvesting robot [DOI]
  22. 22 Fully-automatic natural plant recognition system using deep neural network for dynamic outdoor environments [DOI]
  23. 23 Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches [DOI]
  24. 24 Learning Graph Normalization for Graph Neural Networks [DOI]

Cited by 4

Context-Aware Invasive Plant Instance Synthesis for UAV-Based Crop Field Image Augmentation

Vasyl Faifura, Iryna Spivak, Svitlana Krepych · 2023 13th International Conference on Advanced Computer Information Technologies (ACIT) · 2023

IMPROVEMENT OF REMOTE SENSING METHODS OF THE SPREAD OF INVASIVE PLANT SPECIES IN THE CONTEXT OF ASSESSING POTENTIAL DAMAGE TO THE ENVIRONMENT AND AGRICULTURE

Vasyl Faifura, Iryna Spivak, Vasyl Faifura · INNOVATIVE ECONOMY · 2023

Showing 2 of 4 known citations — external sources report more than can currently be individually listed.

Related research

Article metrics

Real usage data collected on this platform.

50

Page views

0

PDF downloads

6

Outbound clicks

4

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.