Plant Disease Detection Based on YOLOv3 and YOLOv4

Shill, Apu; Rahman, Md. Asifur

doi:10.1109/acmi53878.2021.9528179

Cited by 23 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a previous work [7] by the same authors of this article, it was found that over the years, various CNN models have been considered in the literature for the tasks of plant identification and plant disease detection. Given the results reported in [15], [16] and [17], it was concluded that YOLOv3 or YOLOv4 would be the best option to consider when developing a mobile application to detect the development stages of wild flowers and plants. These models are fast, require relatively little processing capacity and allow results to be obtained in real time.…”

Section: Computer Vision Techniquesmentioning

confidence: 99%

“…This component is responsible for feature extraction, which is the process of transforming data into numerical values. In YOLOv4, the neck component uses Path Aggregation Network (PAN) [17] to extract feature maps, while YOLOv3 uses Feature Pyramid Extraction (FPN). Finally, the head component consists of applying anchor boxes to the feature map extracted by PAN.…”

Section: Yolov4 E Yolov4-tinymentioning

confidence: 99%

See 1 more Smart Citation

A Mobile Application for Detecting and Monitoring the Development Stages of Wild Flowers and Plants

Videira,

Gaspar,

Soares

et al. 2024

IJCAI

View full text Add to dashboard Cite

Wild flowers and plants appear spontaneously. They form the ecological basis on which life depends. They play a fundamental role in the regeneration of natural life and the balance of ecological systems. However, this irreplaceable natural heritage is at risk of being lost due to human activity and climate change. The work presented in this paper contributes to the conservation effort. It is based on a previous study by the same authors, which identified computer vision as a suitable technological platform for detecting and monitoring the development stages of wild flowers and plants. It describes the process of developing a mobile application that uses YOLOv4 and YOLOv4-tiny convolutional neural networks to detect the stages of development of wild flowers and plants. This application could be used by visitors in a nature park to provide information and raise awareness about the wild flowers and plants they find along the roads and trails. Povzetek: Raziskava uvaja mobilno aplikacijo z uporabo konvolucijskih nevronskih mrež YOLOv4 za prepoznavanje razvojnih stopenj divjih rastlin, prispevajoč k ohranjanju naravne dediščine.

show abstract

Section: Computer Vision Techniquesmentioning

confidence: 99%

Section: Yolov4 E Yolov4-tinymentioning

confidence: 99%

A Mobile Application for Detecting and Monitoring the Development Stages of Wild Flowers and Plants

Videira,

Gaspar,

Soares

et al. 2024

IJCAI

View full text Add to dashboard Cite

show abstract

“…One-stage detector-based plant disease detection algorithms mainly comprise YoLo [26], SSD [27], and RetinaNet [28]. A one-stage detector accomplishes the classification and localization of plant disease targets in a network and extracts features directly from the network for plant disease category and location prediction.…”

Section: One-stage Detectormentioning

confidence: 99%

One-Stage Disease Detection Method for Maize Leaf Based on Multi-Scale Feature Fusion

et al. 2022

View full text Add to dashboard Cite

Plant diseases such as drought stress and pest diseases significantly impact crops’ growth and yield levels. By detecting the surface characteristics of plant leaves, we can judge the growth state of plants and whether diseases occur. Traditional manual detection methods are limited by the professional knowledge and practical experience of operators. In recent years, a detection method based on deep learning has been applied to improve detection accuracy and reduce detection time. In this paper, we propose a disease detection method using a convolutional neural network (CNN) with multi-scale feature fusion for maize leaf disease detection. Based on the one-stage plant disease network YoLov5s, the coordinate attention (CA) attention module is added, along with a key feature weight to enhance the effective information of the feature map, and the spatial pyramid pooling (SSP) module is modified by data augmentation to reduce the loss of feature information. Three experiments are conducted under complex conditions such as overlapping occlusion, sparse distribution of detection targets, and similar textures and backgrounds of disease areas. The experimental results show that the average accuracy of the MFF-CNN is higher than that of currently used methods such as YoLov5s, Faster RCNN, CenterNet, and DETR, and the detection time is also reduced. The proposed method provides a feasible solution not only for the diagnosis of maize leaf diseases, but also for the detection of other plant diseases.

show abstract

“…The TL-SE-ResNeXt-101 model based on migration learning and residual networks proposed by Wang [46] has a mAP value of 47.37% when the input image size is 224 × 224. Shill and Rahman [47] proposed an accurate plant disease detection model based on YOLOv4, which is named as M_YOLOv4 in this table, and the mAP and F 1 -scores of the model are 55.45% and 56.00%, respectively. The F 1 -score of YOLOX-ASSANano proposed in this work is 56.11%, and the mAP of our model is 3.41% higher than that of M_YOLOv4, reaching 58.86% as the best disease detection result, which indicates the greater usefulness of our model in real agricultural settings.…”

Section: Comparison Experiments On Plantdocmentioning

confidence: 99%

An Improved Lightweight Network for Real-Time Detection of Apple Leaf Diseases in Natural Scenes

Qiao

et al. 2022

Agronomy

View full text Add to dashboard Cite

Achieving rapid and accurate detection of apple leaf diseases in the natural environment is essential for the growth of apple plants and the development of the apple industry. In recent years, deep learning has been widely studied and applied to apple leaf disease detection. However, existing networks have too many parameters to be easily deployed or lack research on leaf diseases in complex backgrounds to effectively use in real agricultural environments. This study proposes a novel deep learning network, YOLOX-ASSANano, which is an improved lightweight real-time model for apple leaf disease detection based on YOLOX-Nano. We improved the YOLOX-Nano backbone using a designed asymmetric ShuffleBlock, a CSP-SA module, and blueprint-separable convolution (BSConv), which significantly enhance feature-extraction capability and boost detection performance. In addition, we construct a multi-scene apple leaf disease dataset (MSALDD) for experiments. The experimental results show that the YOLOX-ASSANano model with only 0.83 MB parameters achieves 91.08% mAP on MSALDD and 58.85% mAP on the public dataset PlantDoc with a speed of 122 FPS. This study indicates that the YOLOX-ASSANano provides a feasible solution for the real-time diagnosis of apple leaf diseases in natural scenes, and could be helpful for the detection of other plant diseases.

show abstract

Plant Disease Detection Based on YOLOv3 and YOLOv4

Cited by 23 publications

References 11 publications

A Mobile Application for Detecting and Monitoring the Development Stages of Wild Flowers and Plants

A Mobile Application for Detecting and Monitoring the Development Stages of Wild Flowers and Plants

One-Stage Disease Detection Method for Maize Leaf Based on Multi-Scale Feature Fusion

An Improved Lightweight Network for Real-Time Detection of Apple Leaf Diseases in Natural Scenes

Contact Info

Product

Resources

About