Shixuan Li
ABSTRACT
In order to detect the types and quantities of pests in rice fields quickly and accurately, a lightweight target pest detection method SSD_RA based on SSD algorithm is proposed. In order to deal with the problems of high missed detection rate, inaccurate positioning, slow detection speed, large number of model parameters and low accuracy of the detection model, the ResNet feature extraction network was introduced and optimized. The first prediction feature layer of SSD was connected to the Conv3_x module of the ResNet network, and all network layers after the Conv3_x module were dropped. The number of parameters of the model is reduced, so that the model is more lightweight, the detection speed is improved, and the redundant features are reduced to ensure the accuracy of the model. In addition, aiming at the characteristics of small target, the structure of prediction feature layer of SSD algorithm is improved, the number of prediction feature layers is adjusted, and the output of underlying feature Conv2_x is connected to the prediction feature layer. The candidate box of each cell in the new prediction feature layer is 6, which accurately divides the boundaries of large, medium and small target boxes. The experimental results show that the mAP of SSD_RA of the improved algorithm in this paper is 84.1%, which is 23.4 percentage points higher than that of the original SSD model. The reasoning time in CPU and GPU environment is 0.056s and 0.009s, which is 0.101s and 0.005s faster than that of the original SSD model, and the model size is 51.9MB. It is reduced to about 7/100 of the original SSD model. Compared with other models, the mAP of SSD_RA is 7.8 and 4.2 percentage points higher than that of EfficientDet and RFCN, respectively. The SSD_RA model is more effective and faster to detecting insect pests and reduces the missed detection rate.
- Wu Y, Li Y, Niu L, Nutrient status of integrated rice-crayfish system impacts the microbial nitrogen-transformation processes in paddy fields and rice yields[J]. Science of The Total Environment, 2022, 836: 155706. https://doi.org/10.1016/j.scitotenv.2022.155706Google Scholar
Cross Ref
- Courson E, Petit S, Poggi S, Weather and landscape drivers of the regional level of pest occurrence in arable agriculture: A multi-pest analysis at the French national scale[J]. Agriculture, Ecosystems & Environment, 2022, 338: 108105. https://doi.org/10.1016/j.agee.2022.108105Google ScholarCross Ref
- Manu N, Opit G P, Osekre E A, Moisture content, insect pest infestation and mycotoxin levels of maize in markets in the northern region of Ghana[J]. Journal of stored products research, 2019, 80: 10-20. https://doi.org/10.1016/j.jspr.2018.10.007Google ScholarCross Ref
- Sawicka B, Egbuna C. Pests of agricultural crops and control measures[M]//Natural Remedies for Pest, Disease and Weed Control. Academic Press, 2020: 1-16. https://doi.org/10.1016/B978-0-12-819304-4.00001-4Google ScholarCross Ref
- Stanisz M, Bachosz K, Siwińska-Ciesielczyk K, Tailoring Lignin-Based Spherical Particles as a Support for Lipase Immobilization[J]. Catalysts, 2022, 12(9): 1031. https://doi.org/10.1016/j.indcrop.2022.114533Google ScholarCross Ref
- Martínez-Escudero C M, Garrido I, Flores P, Remediation of triazole, anilinopyrimidine, strobilurin and neonicotinoid pesticides in polluted soil using ozonation and solarization[J]. Journal of Environmental Management, 2022, 310: 114781. https://doi.org/10.1016/j.jenvman.2022.114781Google ScholarCross Ref
- Martínez C M, Garrido I, Flores P, Ozonation for remediation of pesticide-contaminated soils at field scale[J]. Chemical Engineering Journal, 2022: 137182. https://doi.org/10.1016/j.cej.2022.137182Google ScholarCross Ref
- Anandhakrishnan T, Jaisakthi S M. Deep Convolutional Neural Networks for image based tomato leaf disease detection[J]. Sustainable Chemistry and Pharmacy, 2022, 30: 100793. https://doi.org/10.1016/j.scp.2022.100793Google ScholarCross Ref
- Muppala C, Guruviah V. Detection of leaf folder and yellow stemborer moths in the paddy field using deep neural network with search and rescue optimization[J]. Information Processing in Agriculture, 2021, 8(2): 350-358. https://doi.org/10.1016/j.inpa.2020.09.002Google ScholarCross Ref
- Qing Y A O, Jin F, Jian T, Development of an automatic monitoring system for rice light-trap pests based on machine vision[J]. Journal of Integrative Agriculture, 2020, 19(10): 2500-2513. https://doi.org/10.1016/S2095-3119(20)63168-9Google ScholarCross Ref
- Wang F, Wang R, Xie C, Fusing multi-scale context-aware information representation for automatic in-field pest detection and recognition[J]. Computers and Electronics in Agriculture, 2020, 169: 105222. https://doi.org/10.1016/j.compag.2020.105222Google ScholarDigital Library
- Dong S, Wang R, Liu K, CRA-Net: A channel recalibration feature pyramid network for detecting small pests[J]. Computers and Electronics in Agriculture, 2021, 191: 106518. https://doi.org/10.1016/j.compag.2021.106518Google ScholarDigital Library
- Zhao N, Zhou L, Huang T, Development of an automatic pest monitoring system using a deep learning model of DPeNet[J]. Measurement, 2022: 111970. https://doi.org/10.1016/j.measurement.2022.111970Google ScholarCross Ref
- Qian S, Du J, Zhou J, An effective pest detection method with automatic data augmentation strategy in the agricultural field[J]. Signal, Image and Video Processing, 2022: 1-9. Qian S, Du J, Zhou J, An effective pest detection method with automatic data augmentation strategy in the agricultural field[J]. Signal, Image and Video Processing, 2022: 1-9.Google Scholar
- Liu W, Anguelov D, Erhan D, Ssd: Single shot multibox detector[C]//European conference on computer vision. Springer, Cham, 2016: 21-37. https://doi.org/10.1007/978-3-319-46448-0_2Google ScholarCross Ref
- Lin T Y, Goyal P, Girshick R, Focal loss for dense object detection[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2980-2988. https://doi.org/10.48550/arXiv.1708.02002Google ScholarCross Ref
- Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263-7271. https://doi.org/10.48550/arXiv.1612.08242Google ScholarCross Ref
- Dai J, Li Y, He K, R-fcn: Object detection via region-based fully convolutional networks[J]. Advances in neural information processing systems, 2016, 29.Google Scholar
- Tan M, Pang R, Le Q V. Efficientdet: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10781-10790 https://doi.org/10.48550/arXiv.1911.09070Google ScholarCross Ref
- Ren S, He K, Girshick R, Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28: 91-99.Google Scholar
- He K, Gkioxari G, Dollár P, Mask r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2961-2969. https://doi.org/10.48550/arXiv.1703.06870Google ScholarCross Ref
- Cai Z, Vasconcelos N. Cascade r-cnn: Delving into high quality object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6154-6162 https://doi.org/10.48550/arXiv.1712.00726.Google ScholarCross Ref
Index Terms
- Object pest detection method based on lightweight SSD_RA algorithm
Recommendations
Agricultural Pest Detection based on Improved Yolov5
CSAI '22: Proceedings of the 2022 6th International Conference on Computer Science and Artificial IntelligenceAgricultural pest detection is an important research direction in image detection. Due to the high similarity between many pests and the extremely similar color of pests and background, agricultural pest detection has always been a difficulty. In the ...
Rice Pest and Disease Detection Using Convolutional Neural Network
ICISS '18: Proceedings of the 1st International Conference on Information Science and SystemsDetection of rice pest and diseases, and proper management and control of pest infested rice fields may result to a higher rice crop production. According to the International Rice Research Institute, farmers lose an average of 37% of their rice crops ...
Vision-based pest detection based on SVM classification method
Detection of thrips in strawberry greenhouse.Detection based on SVM classification method.Pest detection using visible image processing.Real-time detection.Detection under the natural light. Automatic pest detection is a useful method for greenhouse ...
Comments