Weeds are undesired plants that compete against productive crops for space, light, water, and soil nutrients and propagate themselves either through seeding or rhizomes. Hence, weed management and removal practices have been adopted for several decades to control weed growth. Another serious problem that plagues crop farming is the growth of weeds which leads to significant crop wastage annually. However, agricultural growth through crop farming is always at risk due to several reoccurring problems, for example, climate change, greenhouse gas emissions, pollution and waste generation, malnutrition, and food wastage. Moreover, with almost 9% of the world population hungry in 2020, agriculture is a powerful source of food, revenue, and employment and is expected to minimize poverty, raise income levels, and boost prosperity for a projected 9.7 billion population by 2050. In 2018, it contributed 4% to the global GDP and accounts for more than 25% of the GDP for many developing countries. Finally, the study will serve as a starting point for researchers who wish to undertake further research in this area.Ĭrop farming is considered a significant agricultural pursuit for the global economy in the modern era, and over a longer time period, it has had a notable impact on countries’ GDP. 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. Crop images were frequently captured using robots, drones, and cell phones. It also discusses the modality where RGB was most frequently used. 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. 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. 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. 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. 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. In this paper, we present a systematic literature review (SLR) on current state-of-the-art DL techniques for weed detection. 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. 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. Weeds are responsible for higher production costs due to crop waste and have a significant impact on the global agricultural economy. We Are Stardust Inaugural Lecture Maastricht University: Maastricht, The Netherland, 2018.Weeds are one of the most harmful agricultural pests that have a significant impact on crops.
Change in male proportion among newborn infants. War, marriage markets, and the sex ratio at birth.
Available online: (accessed on 2 March 2023). Website of the Collaborative Adverse Outcome Pathway Wiki (AOP-Wiki).WikiPathways: Pathway editing for the people. Thesis, Maastricht University, Maastricht, The Netherland, 2021. Flavonoids Seen through the Energy Perspective. Thesis, Maastricht University, Maastricht, The Netherland, 2019. Statistics and pharmacology: The bloody obvious test. Available online: (accessed on 29 September 2022).
The author declares no conflict of interest.
0 kommentar(er)
