Enhanced Deep Learning Algorithm for Object Detection in the Agriculture Field

PDF (1180KB), PP.15-29

Views: 0 Downloads: 0


Priya Singh 1,* Rajalakshmi Krishnamurthi 1

1. Department of Computer Science, Jaypee Institute of Information Technology, Noida, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2024.03.02

Received: 30 Mar. 2023 / Revised: 26 Apr. 2023 / Accepted: 12 Jul. 2023 / Published: 8 Jun. 2024

Index Terms

Deep Learning (DL), You only look once, version 3 (YOLOv3), Microsoft Common Objects in Context (MS-COCO), Agricultural Security, and Object Detection


Agriculture is one of the most prominent industries which guarantee food requirements and employment throughout the globe due to huge land availability, and atmospheric conditions. But nowadays, security of the available resources are the major concerns due to damage caused by objects inside the agriculture field. There are many traditional algorithms for object detection, but they are not very effective in terms of real time environments. Hence, a deep learning-based object detection model is generated by enhancing YOLOv3. The process involved firstly, k-means clustering was used to identify clusters, followed by modifying the convolutional neural network layers. Additionally, the batch and subdivision values of the actual YOLOv3 model were optimized under the darknet53 framework. The architecture was also configured to detect eleven classes of objects, ensuring that the model could identify a broad range of objects. The experimental results demonstrate that the Delta model achieved a remarkable increase in accuracy from 75.19% to 95.86%. In addition, the model outperformed other models in terms of precision(97%), recall(96%), F1_Score(96%), IoU(80.81%), and mAP(95.86%). Based on these findings, it can be concluded that the delta model offers superior detection capabilities and lower computational complexity compared to conventional methods used in the agriculture field.

Cite This Paper

Priya Singh, Rajalakshmi Krishnamurthi, "Enhanced Deep Learning Algorithm for Object Detection in the Agriculture Field", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.16, No.3, pp. 15-29, 2024. DOI:10.5815/ijigsp.2024.03.02


[1]Elijah, Olakunle, Tharek Abdul Rahman, Igbafe Orikumhi, Chee Yen Leow, and MHD Nour Hindia. "An overview of Internet of Things (IoT) and data analytics in agriculture: Benefits and challenges." IEEE Internet of Things Journal 5, no. 5 (2018): 3758-3773.
[2]Astolfi, Angelica Christina Melo Nunes, Gilberto Astolfi, Maria Gabriela Alves Ferreira, Thaynara D’avalo Centurião, Leyzinara Zenteno Clemente, Bruno Leonardo Marques Castro de Oliveira, João Vitor de Andrade Porto et al. "Recognizing and counting Dendrocephalus brasiliensis (Crustacea: Anostraca) cysts using DL." Plos one 16, no. 3 (2021): e0248574.
[3]Nie, Xin, Meifang Yang, and Ryan Wen Liu. "Deep neural network-based robust ship detection under different weather conditions." In 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 47-52. IEEE, 2019.
[4]Ngo, Vuong M., Thuy-Van T. Duong, Tat-Bao-Thien Nguyen, Cach N. Dang, and Owen Conlan. "A big data smart agricultural system: recommending optimum fertilizers for crops." International Journal of Information Technology (2023): 1-17 
[5]Amici, Andrea, Fioravante Serrani, Carlo Maria Rossi, and Riccardo Primi. "Increase in crop damage caused by wild boar (Sus scrofa L.): the “refuge effect”." Agronomy for sustainable development 32, no. 3 (2012): 683-692. 
[6]Balakrishna, K., Fazil Mohammed, C. R. Ullas, C. M. Hema, and S. K. Sonakshi. "Application of IOT and machine learning in crop protection against animal intrusion." Global Transitions Proceedings 2, no. 2 (2021): 169-174
[7]Bapat, Varsha, Prasad Kale, Vijaykumar Shinde, Neha Deshpande, and Arvind Shaligram. "WSN application for crop protection to divert animal intrusions in the agricultural land." Computers and electronics in agriculture 133 (2017): 88-96.
[8]Navulur, Sridevi, and MN Giri Prasad. "Agricultural management through wireless sensors and internet of things." International Journal of Electrical and Computer Engineering 7, no. 6 (2017): 3492. 
[9]Gongal, A., Suraj Amatya, Manoj Karkee, Q. Zhang, and Karen Lewis. "Sensors and systems for fruit detection and localization: A review." Computers and Electronics in Agriculture 116 (2015): 8-19.
[10]Yadahalli, Srushti, Aditi Parmar, and Amol Deshpande. "Smart Intrusion Detection System for Crop Protection by using Arduino." In 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA), pp. 405-408. IEEE, 2020.
[11]Alqaralleh, Bassam AY, Sachi Nandan Mohanty, Deepak Gupta, Ashish Khanna, K. Shankar, and Thavavel Vaiyapuri. "Reliable Multi-Intruder Tracking Model Using DL and Energy Efficient Wireless Multimedia Sensor Networks." IEEE Access 8 (2020): 213426-213436.
[12]Baranwal, Tanmay, and Pushpendra Kumar Pateriya. "Development of IoT based smart security and monitoring devices for agriculture." In 2016 6th International Conference-Cloud System and Big Data Engineering (Confluence), pp. 597-602. IEEE, 2016.
[13]Kamilaris, Andreas, and Francesc X. Prenafeta-Boldú. "Deep learning in agriculture: A survey." Computers and electronics in agriculture 147 (2018): 70-90.
[14]Sa, Inkyu, Zongyuan Ge, Feras Dayoub, Ben Upcroft, Tristan Perez, and Chris McCool. "Deepfruits: A fruit detection system using deep neural networks." sensors 16, no. 8 (2016): 1222.
[15]Zheng, Yang-Yang, Jian-Lei Kong, Xue-Bo Jin, Xiao-Yi Wang, Ting-Li Su, and Min Zuo. "CropDeep: the crop vision dataset for deep-learning-based classification and detection in precision agriculture." Sensors 19, no. 5 (2019): 1058.
[16]Wei, Jinmeng, Yanhui Ding, Jie Liu, Muhammad Zakir Ullah, Xiang Yin, and Weikuan Jia. "Novel green-fruit detection algorithm based on D2D framework." International Journal of Agricultural and Biological Engineering 15, no. 1 (2022): 251-259.
[17]Wosner, Omer, Guy Farjon, and Aharon Bar-Hillel. "Object detection in agricultural contexts: A multiple resolution benchmark and comparison to human." Computers and Electronics in Agriculture 189 (2021): 106404.
[18]Santos, Thiago T., Leonardo L. de Souza, Andreza A. dos Santos, and Sandra Avila. "Grape detection, segmentation, and tracking using deep neural networks and three-dimensional association." Computers and Electronics in Agriculture 170 (2020): 105247.
[19]Khoroshevsky, Faina, Stanislav Khoroshevsky, and Aharon Bar-Hillel. "Parts-per-object count in agricultural images: Solving phenotyping problems via a single deep neural network." Remote Sensing 13, no. 13 (2021): 2496.
[20]Zhao, Liquan, and Shuaiyang Li. "Intrusion detection algorithm based on improved YOLOv3." Electronics 9, no. 3 (2020): 537.
[21]Misra, Rajesh, and Kumar S. Ray. "Intruder tracking based on quantum particle swarm optimization." In 2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR), pp. 1-6. IEEE, 2017
[22]Huang, Yi-Qi, Jia-Chun Zheng, Shi-Dan Sun, Cheng-Fu Yang, and Jing Liu. "Optimized YOLOv3 algorithm and its application in traffic flow detections." Applied Sciences 10, no. 9 (2020): 3079.
[23]Kumar, Saurav, Drishti Yadav, Himanshu Gupta, Om Prakash Verma, Irshad Ahmad Ansari, and Chang Wook Ahn. "A novel yolov3 algorithm-based DL approach for waste segregation: towards smart waste management." Electronics 10, no. 1 (2021): 14.
[24]Lu, Shengyu, Beizhan Wang, Hongji Wang, Lihao Chen, Ma Linjian, and Xiaoyan Zhang. "A real-time Intrusion detection algorithm for video." Computers & Electrical Engineering 77 (2019): 398-408.
[25]Adami, Davide, Mike O. Ojo, and Stefano Giordano. "Design, Development and Evaluation of an Intelligent Animal Repelling System for Crop Protection Based on Embedded Edge-AI." IEEE Access 9 (2021): 132125-132139.
[26]Xiao, Dong, Feng Shan, Ze Li, Ba Tuan Le, Xiwen Liu, and Xuerao Li. "A target detection model based on improved tiny-yolov3 under the environment of mining truck." IEEE Access 7 (2019): 123757-123764.
[27]Cao, Chang-Yu, Jia-Chun Zheng, Yi-Qi Huang, Jing Liu, and Cheng-Fu Yang. "Investigation of a promoted you only look once algorithm and its application in traffic flow monitoring." Applied Sciences 9, no. 17 (2019): 3619.
[28]Xuan, Guantao, Chong Gao, Yuanyuan Shao, Meng Zhang, Yongxian Wang, Jingrun Zhong, Qingguo Li, and Hongxing Peng. "Apple detection in natural environment using deep learning algorithms." IEEE Access 8 (2020): 216772-216780.
[29]Zhao, Baining, Haijuan Lan, Zhewen Niu, Huiling Zhu, Tong Qian, and Wenhu Tang. "Detection and Location of Safety Protective Wear in Power Substation Operation Using Wear-Enhanced YOLOv3 Algorithm." IEEE Access 9 (2021): 125540-125549.
[30]Mao, Qi-Chao, Hong-Mei Sun, Yan-Bo Liu, and Rui-Sheng Jia. "Mini-YOLOv3: real-time object detector for embedded applications." Ieee Access 7 (2019): 133529-133538.
[31]Taheri Tajar, Alireza, Abbas Ramazani, and Muharram Mansoorizadeh. "A lightweight Tiny-YOLOv3 vehicle detection approach." Journal of Real-Time Image Processing 18, no. 6 (2021): 2389-2401.