Apnet: Lightweight network for apricot tree disease and pest detection in real-world complex backgrounds.

in Plant methods by Minglang Li, Zhiyong Tao, Wentao Yan, Sen Lin, Kaihao Feng, Zeyi Zhang, Yurong Jing

TLDR

  • A novel dataset and detection algorithm for apricot tree pest and disease detection are introduced, with the proposed algorithm achieving an accuracy rate of 87.1%.

Abstract

Apricot trees, serving as critical agricultural resources, hold a significant role within the agricultural domain. Conventional methods for detecting pests and diseases in these trees are notably labor-intensive. Many conditions affecting apricot trees manifest distinct visual symptoms that are ideally suited for precise identification and classification via deep learning techniques. Despite this, the academic realm currently lacks extensive, realistic datasets and deep learning strategies specifically crafted for apricot trees. This study introduces ATZD01, a publicly accessible dataset encompassing 11 categories of apricot tree pests and diseases, meticulously compiled under genuine field conditions. Furthermore, we introduce an innovative detection algorithm founded on convolutional neural networks, specifically devised for the management of apricot tree pests and diseases. To enhance the accuracy of detection, we have developed a novel object detection framework, APNet, alongside a dedicated module, the Adaptive Thresholding Algorithm (ATA), tailored for the detection of apricot tree afflictions. Experimental evaluations reveal that our proposed algorithm attains an accuracy rate of 87.1% on ATZD01, surpassing the performance of all other leading algorithms tested, thereby affirming the effectiveness of our dataset and model. The code and dataset will be made available at https://github.com/meanlang/ATZD01 .

Overview

  • The study introduces ATZD01, a publicly accessible dataset containing 11 categories of apricot tree pests and diseases, collectively compiled under genuine field conditions.
  • The study also presents an innovative detection algorithm founded on convolutional neural networks, specifically designed for the management of apricot tree pests and diseases.
  • The primary objective is to develop a precise and efficient method for detecting pests and diseases in apricot trees, utilizing deep learning techniques and developing a novel object detection framework.

Comparative Analysis & Findings

  • The proposed algorithm achieves an accuracy rate of 87.1% on ATZD01, surpassing the performance of all other leading algorithms tested.
  • The experimental evaluation suggests that the proposed algorithm is effective in detecting apricot tree pests and diseases.
  • The study highlights the significance of utilizing deep learning techniques and developing novel object detection frameworks for the management of apricot tree pests and diseases.

Implications and Future Directions

  • The availability of the ATZD01 dataset and the proposed algorithm will facilitate further research and development in the field of apricot tree disease detection.
  • Future studies can focus on extending the dataset to include more diverse and complex apricot tree pests and diseases.
  • The development of transfer learning strategies can enable the adaptation of the proposed algorithm for other crop-based disease detection tasks.
Read Full Article