Effective and efficient multi-crop pest detection based on deep learning object detection models

被引:12
作者
Arun, R. Arumuga [1 ]
Umamaheswari, S. [2 ]
机构
[1] Anna Univ, Dept Comp Technol, MIT Campus, Chennai, Tamil Nadu, India
[2] Anna Univ, Dept Informat Technol, MIT Campus, Chennai, Tamil Nadu, India
关键词
Deep learning; Convolutional Neutral Network; object detection; pest detection; transfer learning; NEURAL-NETWORK; LOCALIZATION; RECOGNITION; VEHICLE;
D O I
10.3233/JIFS-220595
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditional machine learning-based pest classification methods are a tedious and time-consuming process. A method of multi-class pest detection based on deep learning and convolutional neural networks could be the solution. It automatically extracts the complex features of different pests from the crop pest images. In this paper, various significant deep learning-based object detection models like SSD, EfficientDet, Faster R-CNN, and CenterNet are implemented based on the Tensorflow Object Detection framework. Several significant networks like MobileNet V2, ResNet101 V1, Inception ResNet V2, EfficientNet, and HourGlass104 are employed as backbone networks for these models to extract the different features of the pests. Object detection models are capable of identifying and locating pests in crops. Initially, these models are pre-trained with the COCO dataset and later be fine-tuned to the target pest dataset of 20 different pest classes. After conducting experiments on these models using the pest dataset, we demonstrate that Faster R-CNN ResNet101 V1 outperformed every other model and achieved mAP of 74.77%. Additionally, it is developed as a lightweight model, whose size is similar to 9 MB, and can detect pest objects in 130 milliseconds per image, allowing it to be used on resources-constrained devices commonly used by farmers.
引用
收藏
页码:5185 / 5203
页数:19
相关论文
共 50 条
[41]   Deep Learning based Neck Models for Object Detection: A Review and a Benchmarking Study [J].
Bouraya, Sara ;
Belangour, Abdessamad .
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2021, 12 (11) :161-167
[42]   ENHANCING FAKE PRODUCT DETECTION USING DEEP LEARNING OBJECT DETECTION MODELS [J].
Daoud, Eduard ;
Vu, Dang ;
Nguyen, Hung ;
Gaedke, Martin .
IADIS-INTERNATIONAL JOURNAL ON COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2020, 15 (01) :13-24
[43]   Object detection method of multi-view SSD based on deep learning [J].
Tang C. ;
Ling Y. ;
Zheng K. ;
Yang X. ;
Zheng C. ;
Yang H. ;
Jin W. .
Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering, 2018, 47 (01)
[44]   Evaluation of Robustness of Deep Learning-Based Object Detection Models for Invertebrate Grazers Detection and Monitoring [J].
Bak, Suho ;
Kim, Heung-Min ;
Kim, Tak-Young ;
Lim, Jae-Young ;
Jang, Seon Woong .
KOREAN JOURNAL OF REMOTE SENSING, 2023, 39 (03) :297-309
[45]   Optimizing Deep Learning Models for Object Detection [J].
Barburescu, Calin-George ;
Iuhasz, Gabriel .
2020 22ND INTERNATIONAL SYMPOSIUM ON SYMBOLIC AND NUMERIC ALGORITHMS FOR SCIENTIFIC COMPUTING (SYNASC 2020), 2020, :270-277
[46]   PestLite: A Novel YOLO-Based Deep Learning Technique for Crop Pest Detection [J].
Dong, Qing ;
Sun, Lina ;
Han, Tianxin ;
Cai, Minqi ;
Gao, Ce .
AGRICULTURE-BASEL, 2024, 14 (02)
[47]   Survey on crop pest detection using deep learning and machine learning approaches [J].
M. Chithambarathanu ;
M. K. Jeyakumar .
Multimedia Tools and Applications, 2023, 82 :42277-42310
[48]   Astronomical Object Shape Detection Using Deep Learning Models [J].
Mohanasundaram, K. ;
Balasaranya, K. ;
Priya, J. Geetha ;
Ruchitha, B. ;
Priya, A. Vishnu ;
Harshini, Hima .
INTERNATIONAL JOURNAL OF EARLY CHILDHOOD SPECIAL EDUCATION, 2022, 14 (02) :7867-7874
[49]   A Comparison of Deep Learning Object Detection Models for Satellite Imagery [J].
Groener, Austen ;
Chern, Gary ;
Pritt, Mark .
2019 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2019,
[50]   Benchmarking Object Detection Deep Learning Models in Embedded Devices [J].
Cantero, David ;
Esnaola-Gonzalez, Iker ;
Miguel-Alonso, Jose ;
Jauregi, Ekaitz .
SENSORS, 2022, 22 (11)