A fast accurate fine-grain object detection model based on YOLOv4 deep neural network
Open accessThe DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Abstract
Early identification and prevention of various plant diseases is a key feature of precision agriculture technology. This paper presents a high-performance real-time fine-grain object detection framework that addresses several obstacles in plant disease detection that hinders the performance of traditional methods, such as dense distribution, irregular morphology, multi-scale object classes, textural similarity. The proposed model is built on an improved version of the You Only Look Once (YOLOv4) algorithm. The modified network architecture maximizes both detection accuracy and speed by including the DenseNet in the backbone to optimize feature transfer and reuse; two new residual blocks in backbone and neck enhance feature extraction and reduce computing cost; the Spatial Pyramid Pooling (SPP) enhances receptive field, and a modified Path Aggregation Network (PANet) preserves fine-grain localized information and improves feature fusion. Additionally, use of the Hard-Swish function as the primary activation improved the model’s accuracy due to better nonlinear feature extraction. The proposed model is tested in detecting four different diseases in tomato plants under various challenging environments. The model outperforms the existing state-of-the-art detection models in detection accuracy and speed. At a detection rate of 70.19 FPS, the proposed model obtained a precision value of 90.33%, F1-score of 93.64%, and a mean average precision (mAP) value of 96.29%. Current work provides an effective and efficient method for detecting different plant diseases in complex scenarios that can be extended to different fruit and crop detection, generic disease detection, and various automated agricultural detection processes.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
YOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971
YOLOv4: Optimal Speed and Accuracy of Object Detection
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020) · arXiv · doi:10.48550/arxiv.2004.10934 · Cited by 10,307
Path Aggregation Network for Instance Segmentation
Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00913 · Cited by 10,011
Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708
Cascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00075 · Cited by 6,612
Object Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545 · cited 1×
“2) with existing state-of-the-art models for object detection [54].”
BackgroundCutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
Yun, S., Han, D., Chun, S., Oh, S. J., Yoo, Y., & Choe, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00612 · Cited by 5,400
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2019) · arXiv · doi:10.48550/arxiv.1911.08287 · Cited by 5,313 · cited 4×
“CIoU loss simultaneously considers three geometric metrics that are typically ignored: overlapping area, the distance between centers, and the aspect ratio in the bounding box regression in object detection [46].”
BackgroundMethodInfluentialSGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6999 · Cited by 5,288
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Wang, C.-Y., Mark Liao, H.-Y., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., & Yeh, I.-H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00203 · Cited by 5,265
Deep learning in agriculture: A survey
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2018.02.016 · Cited by 5,133
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335 · cited 2×
“However, using the Swish function [38] as a drop-in replacement for ReLU demonstrates significant improvement of the neural network performance [38,42,43].”
MethodA Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation
Goutte, C., & Gaussier, E. (2005) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-31865-1_25 · Cited by 2,285 · cited 1×
“Some traditional evaluation parameters, such as precision– recall (PR) curve, F-1 score, average precision (AP), or mean average precision (mAP), can be used [50] to measure the performance of an object detection model.”
MethodProceedings of IEEE International Conference on Computer Vision
(1995) · doi:10.1109/iccv.1995 · Cited by 2,280
MMDetection: Open MMLab Detection Toolbox and Benchmark
Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et al. (2019) · arXiv · doi:10.48550/arxiv.1906.07155 · Cited by 2,227
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
Elfwing, S., Uchibe, E., & Doya, K. (2018) · Neural Networks · doi:10.1016/j.neunet.2017.12.012 · Cited by 2,119
Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
Wu, Z., Shen, C., & van den Hengel, A. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.01.006 · Cited by 1,589
IEEE Transactions on Neural Networks and Learning Systems
(2013) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2013.2264575 · Cited by 1,573
Advanced methods of plant disease detection. A review
Martinelli, F., Scalenghe, R., Davino, S., Panno, S., Scuderi, G., Ruisi, P., Villa, P., Stroppiana, D., Boschetti, M., Goulart, L. R., et al. (2015) · Agronomy for Sustainable Development · doi:10.1007/s13593-014-0246-1 · Cited by 964
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey
Han, J., Zhang, D., Cheng, G., Liu, N., & Xu, D. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2749125 · Cited by 621
Deep fruit detection in orchards
Bargoti, S., & Underwood, J. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989417 · Cited by 607 · cited 1×
“These models are useful in crop and fruit detection, yield, growth evaluation, and automated agricultural management [17].”
How deep learning extracts and learns leaf features for plant classification
Lee, S. H., Chan, C. S., Mayo, S. J., & Remagnino, P. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.05.015 · Cited by 575
Mish: A Self Regularized Non-Monotonic Activation Function
Misra, D. (2019) · arXiv · doi:10.48550/arxiv.1908.08681 · Cited by 541
Solving Current Limitations of Deep Learning Based Approaches for Plant Disease Detection
Arsenovic, M., Karanovic, M., Sladojevic, S., Anderla, A., & Stefanovic, D. (2019) · Symmetry · doi:10.3390/sym11070939 · Cited by 519
Zheng, Y.-Y., Kong, J.-L., Jin, X.-B., Wang, X.-Y., Su, T.-L., & Zuo, M. (2019) · Sensors · doi:10.3390/s19051058 · Cited by 462
DropBlock: A regularization method for convolutional networks
Ghiasi, G., Lin, T.-Y., & Le, Q. V. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12890 · Cited by 459
A detection algorithm for cherry fruits based on the improved YOLO-v4 model
Gai, R., Chen, N., & Yuan, H. (2023) · Neural Computing and Applications · doi:10.1007/s00521-021-06029-z · Cited by 388 · cited 1×
“The more recent YOLOv4 has higher detection speed and performs with better precision and accuracy compared to YOLOv3 in different real-time object detection applications [25, 26] including its application in improving autonomous detection [27, 28].”
MethodA Survey of Deep Learning Techniques: Application in Wind and Solar Energy Resources
Shamshirband, S., Rabczuk, T., & Chau, K.-W. (2019) · IEEE Access · doi:10.1109/access.2019.2951750 · Cited by 313
Deep Learning-Based Object Detection Improvement for Tomato Disease
Zhang, Y., Song, C., & Zhang, D. (2020) · IEEE Access · doi:10.1109/access.2020.2982456 · Cited by 298
Face Mask Wearing Detection Algorithm Based on Improved YOLO-v4
Yu, J., & Zhang, W. (2021) · Sensors · doi:10.3390/s21093263 · Cited by 280
Apple flower detection using deep convolutional networks
Dias, P. A., Tabb, A., & Medeiros, H. (2018) · Computers in Industry · doi:10.1016/j.compind.2018.03.010 · Cited by 265
Deep learning-based appearance features extraction for automated carp species identification
Banan, A., Nasiri, A., & Taheri-Garavand, A. (2020) · Aquacultural Engineering · doi:10.1016/j.aquaeng.2020.102053 · Cited by 262
On Plant Detection of Intact Tomato Fruits Using Image Analysis and Machine Learning Methods
Yamamoto, K., Guo, W., Yoshioka, Y., & Ninomiya, S. (2014) · Sensors · doi:10.3390/s140712191 · Cited by 248
A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision
Roy, A. M., & Bhaduri, J. (2021) · AI · doi:10.3390/ai2030026 · Cited by 189
Self-citationVougioukas, S. G. (2019) · Annual Review of Control, Robotics, and Autonomous Systems · doi:10.1146/annurev-control-053018-023617 · Cited by 180
Fan, Y., Xu, K., Wu, H., Zheng, Y., & Tao, B. (2020) · IEEE Access · doi:10.1109/access.2020.2970836 · Cited by 178
Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks
Eger, S., Youssef, P., & Gurevych, I. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1472 · Cited by 121
Cross-Iteration Batch Normalization
Yao, Z., Cao, Y., Zheng, S., Huang, G., & Lin, S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01215 · Cited by 112 · cited 2×
“Apart from the above mentioned modifications of the model architecture, dropout in the feature map [46], CIoU loss function [47], Cross mini Batch Normalization [48], cosine annealing scheduler [49], and dropblock regularization [50], are utilized to improve the performance of the proposed model.”
MethodSemantic Segmentation of Satellite Images using a Modified CNN with Hard-Swish Activation Function
Avenash, R., & Viswanath, P. (2019) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0007469604130420 · Cited by 40
Study on the Evaluation Method of Sound Phase Cloud Maps Based on an Improved YOLOv4 Algorithm
Zhu, Q., Zheng, H., Wang, Y., Cao, Y., & Guo, S. (2020) · Sensors · doi:10.3390/s20154314 · Cited by 33
Iris presentation attack detection based on best-k feature selection from YOLO inspired RoI
Choudhary, M., Tiwari, V., & Uduthalapally, V. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05342-3 · Cited by 27
A dynamic discarding technique to increase speed and preserve accuracy for YOLOv3
Martinez‐Alpiste, I., Golcarenarenji, G., Wang, Q., & Calero, J. M. A. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05764-7 · Cited by 25
Cited by
Upadhyay, A., Chandel, N. S., Singh, K. P., Chakraborty, S. K., Nandede, B. M., Kumar, M., Subeesh, A., Upendar, K., Salem, A., & Elbeltagi, A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-024-11100-x · Cited by 468
Roy, A. M., & Bhaduri, J. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.102007 · Cited by 269
Self-citationRoy, A. M., Bhaduri, J., Kumar, T., & Raj, K. (2023) · Ecological Informatics · doi:10.1016/j.ecoinf.2022.101919 · Cited by 257
Self-citationDeep learning-based cost-effective and responsive robot for autism treatment
Singh, A., Raj, K., Kumar, T., Verma, S., & Roy, A. (2023) · Drones · doi:10.3390/drones7020081 · Cited by 154
Self-citationHan, Z., Huang, H., Fan, Q., Li, Y., Li, Y., & Chen, X. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106888 · Cited by 45
Metadata
- Authors
- Roy, A. M., Bose, R., & Bhaduri, J.
- Venue
- Neural Computing and Applications
- Published
- 2022-01-07
- Volume
- 34
- Issue
- 5
- Pages
- 3895-3921
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W3210535920
- Cited by
- 332
- References
- 55
- FWCI
- 35.94
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.