Weed Detection Using Deep Learning: A Systematic Literature Review
Weeds are one of the most harmful agricultural pests that have a significant impact on crops. Weeds are responsible for higher production costs due to crop waste and have a significant impact on the global agricultural economy. The importance of this problem has promoted the research community in ex...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/7/3670 |
| _version_ | 1797606918062080000 |
|---|---|
| author | Nafeesa Yousuf Murad Tariq Mahmood Abdur Rahim Mohammad Forkan Ahsan Morshed Prem Prakash Jayaraman Muhammad Shoaib Siddiqui |
| author_facet | Nafeesa Yousuf Murad Tariq Mahmood Abdur Rahim Mohammad Forkan Ahsan Morshed Prem Prakash Jayaraman Muhammad Shoaib Siddiqui |
| author_sort | Nafeesa Yousuf Murad |
| collection | DOAJ |
| description | Weeds are one of the most harmful agricultural pests that have a significant impact on crops. Weeds are responsible for higher production costs due to crop waste and have a significant impact on the global agricultural economy. The importance of this problem has promoted the research community in exploring the use of technology to support farmers in the early detection of weeds. Artificial intelligence (AI) driven image analysis for weed detection and, in particular, machine learning (ML) and deep learning (DL) using images from crop fields have been widely used in the literature for detecting various types of weeds that grow alongside crops. In this paper, we present a systematic literature review (SLR) on current state-of-the-art DL techniques for weed detection. Our SLR identified a rapid growth in research related to weed detection using DL since 2015 and filtered 52 application papers and 8 survey papers for further analysis. The pooled results from these papers yielded 34 unique weed types detection, 16 image processing techniques, and 11 DL algorithms with 19 different variants of CNNs. Moreover, we include a literature survey on popular vanilla ML techniques (e.g., SVM, random forest) that have been widely used prior to the dominance of DL. Our study presents a detailed thematic analysis of ML/DL algorithms used for detecting the weed/crop and provides a unique contribution to the analysis and assessment of the performance of these ML/DL techniques. Our study also details the use of crops associated with weeds, such as sugar beet, which was one of the most commonly used crops in most papers for detecting various types of weeds. It also discusses the modality where RGB was most frequently used. Crop images were frequently captured using robots, drones, and cell phones. It also discusses algorithm accuracy, such as how SVM outperformed all machine learning algorithms in many cases, with the highest accuracy of 99 percent, and how CNN with its variants also performed well with the highest accuracy of 99 percent, with only VGGNet providing the lowest accuracy of 84 percent. Finally, the study will serve as a starting point for researchers who wish to undertake further research in this area. |
| first_indexed | 2024-03-11T05:24:36Z |
| format | Article |
| id | doaj.art-37b2c56e55f24e36adfb761d3c1c8ac9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:24:36Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-37b2c56e55f24e36adfb761d3c1c8ac92023-11-17T17:36:00ZengMDPI AGSensors1424-82202023-03-01237367010.3390/s23073670Weed Detection Using Deep Learning: A Systematic Literature ReviewNafeesa Yousuf Murad0Tariq Mahmood1Abdur Rahim Mohammad Forkan2Ahsan Morshed3Prem Prakash Jayaraman4Muhammad Shoaib Siddiqui5Big Data Analytics Laboratory, Department of Computer Science, School of Mathematics and Computer Science, Institute of Business Administration, Karachi 75270, PakistanBig Data Analytics Laboratory, Department of Computer Science, School of Mathematics and Computer Science, Institute of Business Administration, Karachi 75270, PakistanSchool of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne 3122, AustraliaSchool of Engineering and Technology, Central Queensland University, Melbourne 3000, AustraliaSchool of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne 3122, AustraliaFaculty of Computer and Information Systems, Islamic University of Madinah, Medina 42351, Saudi ArabiaWeeds are one of the most harmful agricultural pests that have a significant impact on crops. Weeds are responsible for higher production costs due to crop waste and have a significant impact on the global agricultural economy. The importance of this problem has promoted the research community in exploring the use of technology to support farmers in the early detection of weeds. Artificial intelligence (AI) driven image analysis for weed detection and, in particular, machine learning (ML) and deep learning (DL) using images from crop fields have been widely used in the literature for detecting various types of weeds that grow alongside crops. In this paper, we present a systematic literature review (SLR) on current state-of-the-art DL techniques for weed detection. Our SLR identified a rapid growth in research related to weed detection using DL since 2015 and filtered 52 application papers and 8 survey papers for further analysis. The pooled results from these papers yielded 34 unique weed types detection, 16 image processing techniques, and 11 DL algorithms with 19 different variants of CNNs. Moreover, we include a literature survey on popular vanilla ML techniques (e.g., SVM, random forest) that have been widely used prior to the dominance of DL. Our study presents a detailed thematic analysis of ML/DL algorithms used for detecting the weed/crop and provides a unique contribution to the analysis and assessment of the performance of these ML/DL techniques. Our study also details the use of crops associated with weeds, such as sugar beet, which was one of the most commonly used crops in most papers for detecting various types of weeds. It also discusses the modality where RGB was most frequently used. Crop images were frequently captured using robots, drones, and cell phones. It also discusses algorithm accuracy, such as how SVM outperformed all machine learning algorithms in many cases, with the highest accuracy of 99 percent, and how CNN with its variants also performed well with the highest accuracy of 99 percent, with only VGGNet providing the lowest accuracy of 84 percent. Finally, the study will serve as a starting point for researchers who wish to undertake further research in this area.https://www.mdpi.com/1424-8220/23/7/3670weed detectiondeep learningmachine learningsystematic literature review |
| spellingShingle | Nafeesa Yousuf Murad Tariq Mahmood Abdur Rahim Mohammad Forkan Ahsan Morshed Prem Prakash Jayaraman Muhammad Shoaib Siddiqui Weed Detection Using Deep Learning: A Systematic Literature Review Sensors weed detection deep learning machine learning systematic literature review |
| title | Weed Detection Using Deep Learning: A Systematic Literature Review |
| title_full | Weed Detection Using Deep Learning: A Systematic Literature Review |
| title_fullStr | Weed Detection Using Deep Learning: A Systematic Literature Review |
| title_full_unstemmed | Weed Detection Using Deep Learning: A Systematic Literature Review |
| title_short | Weed Detection Using Deep Learning: A Systematic Literature Review |
| title_sort | weed detection using deep learning a systematic literature review |
| topic | weed detection deep learning machine learning systematic literature review |
| url | https://www.mdpi.com/1424-8220/23/7/3670 |
| work_keys_str_mv | AT nafeesayousufmurad weeddetectionusingdeeplearningasystematicliteraturereview AT tariqmahmood weeddetectionusingdeeplearningasystematicliteraturereview AT abdurrahimmohammadforkan weeddetectionusingdeeplearningasystematicliteraturereview AT ahsanmorshed weeddetectionusingdeeplearningasystematicliteraturereview AT premprakashjayaraman weeddetectionusingdeeplearningasystematicliteraturereview AT muhammadshoaibsiddiqui weeddetectionusingdeeplearningasystematicliteraturereview |