Smart agricultural technology最新文献

{"title":"Cover crop impacts on soil organic matter dynamics and its quantification using UAV and proximal sensing","authors":"Nikolaos-Christos Vavlas ,&nbsp;Rima Porre ,&nbsp;Liang Meng ,&nbsp;Ali Elhakeem ,&nbsp;Fenny van Egmond ,&nbsp;Lammert Kooistra ,&nbsp;Gerlinde B. De Deyn","doi":"10.1016/j.atech.2024.100621","DOIUrl":"10.1016/j.atech.2024.100621","url":null,"abstract":"<div><div>Soil health is a critical aspect of sustainable agriculture, with soil organic matter (SOM) serving as a key indicator. In arable fields, growing cover crops has been advocated as a prime practice to promote SOM accumulation. However, the effectiveness of cover crops to promote SOM accumulation can vary widely. Furthermore, accurate quantification of SOM at field scale is severely constrained by the labour intensity and destructive nature of traditional methods, which limits the ability to quantify and monitor cover crop impacts on SOM. We tested whether cover crop mixtures promote SOM accumulation more than cover crop monocultures in a 6-year field experiment with arable crop rotation on sandy soil. We found that the cover crops radish and oat-radish mixture significantly increased SOM levels compared to the fallow treatment. Next, on soil sampled in year 4, we explored the use of proximal (VIS-NIR, MIR) and remote sensing using Unmanned Aerial Vehicles (UAVs) to upscale SOM from wet lab-based point samples to the whole field and map its SOM status. Thereto, we used Random Forest (RF), Support Vector Regression (SVR), and Partial Least Squares (PLS) models and found that the best fitting model depended on the type of spectral sensor. With proximal sensing (MIR) the best SOM prediction was achieved using SVR (R²= 0.84, RMSE= 1.55 g/kg SOM). For UAV imagery with hyperspectral camera the best model was RF (R² = 0.69, RMSE= 2.19 g/kg SOM) and enabled digital mapping of SOM distribution across the field. The accuracy of MIR enabled identifying radish cover crop treatments as having on average higher SOM levels compared to the fallow. However, infield spatial SOM variation can override cover crop effects on SOM levels. Therefore, UAV time series are required to remotely quantify cover crop impacts on SOM changes. Overall, our results show potential for combining proximal and UAV-based sensing SOM as a tool for more efficient and accurate spatiotemporal monitoring of SOM at field scale, which can aid in promoting sustainable agricultural practices that enhance soil health.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100621"},"PeriodicalIF":6.3,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a low-cost smart irrigation system for sustainable water management in the Mediterranean region","authors":"Salvatore Filippo Di Gennaro ,&nbsp;Davide Cini ,&nbsp;Andrea Berton ,&nbsp;Alessandro Matese","doi":"10.1016/j.atech.2024.100629","DOIUrl":"10.1016/j.atech.2024.100629","url":null,"abstract":"<div><div>Agricultural water consumption, constituting 70–80 % of global water usage, faces critical challenges due to climate change, diminishing rainfall, and a burgeoning population. This research presents the development and implementation of a low-cost automatic smart irrigation system for tomato and melon crops in the Tuscany region, Italy. The initiative, embedded within the DATI project, aims to revolutionize water management in agriculture, particularly addressing challenges posed by climate change, drought, and an expanding population. The study spans three vegetative seasons (2021–2023) and focuses on optimizing irrigation efficiency through innovative technologies. The smart irrigation system evolved from a conventional setup to a comprehensive solution, integrating evapotranspiration models, wireless sensor networks, and advanced control algorithms. Different irrigation treatments were applied, representing varying levels of water reduction. Results demonstrate a significant reduction in water consumption, particularly in the 2023 season, where the smart system utilized 50 % less water compared to conventional practices in the area. The system's evolution involved addressing and troubleshooting various issues, including sensor calibration, hardware challenges, and soil moisture variations. Soil moisture sensor data revealed the system's impact, showcasing higher levels in treatments with more water. The study emphasizes the economic viability of the smart irrigation system, with total costs below €6000. The scalability of the system, capable of managing multiple irrigation lines remotely, underscores its potential for widespread adoption across different field sizes. In conclusion, the developed smart irrigation system, driven by evapotranspiration models and wireless sensor networks, emerges as a promising and sustainable solution. The system offers precise irrigation based on crop water needs, enhancing water use efficiency and overall yields. While challenges in sensor calibration and maintenance persist, the study highlights the potential of smart irrigation to address water scarcity and contribute to sustainable agriculture practices.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100629"},"PeriodicalIF":6.3,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and development of machine vision robotic arm for vegetable crops in hydroponics","authors":"Haider Ali Khan ,&nbsp;Umar Farooq ,&nbsp;Shoaib Rashid Saleem ,&nbsp;Ubaid-ur Rehman ,&nbsp;Muhammad Naveed Tahir ,&nbsp;Tahir Iqbal ,&nbsp;Muhammad Jehanzeb Masud Cheema ,&nbsp;Muhammad Abubakar Aslam ,&nbsp;Saddam Hussain","doi":"10.1016/j.atech.2024.100628","DOIUrl":"10.1016/j.atech.2024.100628","url":null,"abstract":"<div><div>Modern agricultural machinery such as harvesting robotic arms are necessary to optimize the semi-automated agricultural processes to meet the ever-growing food needs of the population of the world. Production of low cost and highly efficient robotic arms are needed to meet the needs of the small-scale growers of underdeveloped countries. In this regard, mechanical design, sensor placement, and object identification are essential to optimize the performance of agricultural robots. This research is conducted to design a fully automated robotic arm for fruit picking in hydroponics system and research farm using machine vision to help the smallholders. For this purpose, a robotic arm with 1.3 m in height is designed using aluminum (18-gauge) and mild steel (MS-16) as fabrication material for the mechanical structure. The prototype design is tested for stress estimation at various payloads using SolidWorks simulations. The proposed robotic arm is based on a four degrees of freedom (4-DoF) design with the gripper having an opening range of 5.5 to 12 cm depending upon the task to handle various objects. The robotic arm is installed on an expandable vertical mobile platform that enables an expanded operational workspace with lower energy consumption. The total weight of the robotic arm is 60 kgs housing a payload capacity ranging between 8 and 10 kgs in accordance with industry-standard load-bearing specifications. The inverse kinematic algorithm using DH-table is computed with an accuracy of up to 95 % and target height of gripper is cross checked by mounting the ultrasonic sensor at the base of robotic arm. The YOLOv8 algorithm is used for object detection using the depth sense camera having angle range of 0.3 m to 3 m with the precision of up to 96 %. The time needed for recognition of fruits and pitching was about 15 s, with a success rate of up to 90 %. This research produces a low-cost and efficient solution for stallholders by developing a fully automated robotic arm for fruit picking. It optimizes agricultural productivity through improved mechanical design, sensor accuracy, and object detection which reduces labor costs by increasing efficiency of semi-automated farming systems. Further research is required to optimize the overall weight of the system and automation of the movement of robotic arm system between the consecutive rows to build a fully autonomous fruit picking operation in hydroponics.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100628"},"PeriodicalIF":6.3,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Farmer's attitudes towards GHG emissions and adoption to low-cost sensor-driven smart farming for mitigation: The case of Ireland tillage and horticultural farmers","authors":"Fredrick Otieno ,&nbsp;Sudha-Rani N V Nalakurthi ,&nbsp;Mahdieh Raji ,&nbsp;Ananya Tiwari ,&nbsp;Iulia Anton ,&nbsp;Salem Gharbia","doi":"10.1016/j.atech.2024.100622","DOIUrl":"10.1016/j.atech.2024.100622","url":null,"abstract":"<div><div>The current agricultural practices make the sector the single largest contributor to overall GHG emissions thus contributing to the global climate crisis. Irish farmers are required to reduce total agricultural emissions by 25% by 2030 to mitigate the emissions. This study investigates the mitigation of on-farm GHG emissions for tillage and horticulture sector with regards to farmers’ experiences, practices, and challenges under the climate risks. It also analyses farmers’ willingness to engage in emission mitigation practices such as adoption of smart farming technologies (SFT) of low-cost sensors for environmental monitoring. In addition, identifying key farmer attitudes and variables influencing adoption of the SFT. Questionnaires were administered to farmers (<em>n</em> = 53) across Ireland, augmented with agricultural experts’ interviews. The data obtained was subjected to exploratory data analysis to analyse patterns. This was followed by latent attitude analysis with Latent Class Analysis (LCA) model to reveal underlying attitudes influencing adoption of the SFT. Finally, a backward stepwise regression analysis was undertaken to determine significant (<em>p</em> &lt; 0.05) factors in the farmer’ experiences, practices and challenges that influence their latent attitudes. The farmers have multiple experiences and challenges with their farming practices including high acknowledgement of climate impact on production (76%) and limited awareness of GHG emission sources (10%). They also practice among others use of fertilizer (67%) and pesticides (67%). Nevertheless, they showed willingness to monitor local environmental conditions (67%) including on-farm carbon footprint (CF) measurements (62%). The farmers exhibited three types of attitudes, production orientation (21%), smart farming orientation (30%), and organic farming orientation (49%).</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100622"},"PeriodicalIF":6.3,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cybersecurity threats and mitigation measures in agriculture 4.0 and 5.0","authors":"Chrysanthos Maraveas ,&nbsp;Muttukrishnan Rajarajan ,&nbsp;Konstantinos G Arvanitis ,&nbsp;Anna Vatsanidou","doi":"10.1016/j.atech.2024.100616","DOIUrl":"10.1016/j.atech.2024.100616","url":null,"abstract":"<div><div>The primary aim of this study was to explore cybersecurity threats in agriculture 4.0 and 5.0, as well as possible mitigation strategies. A secondary method was employed involving narrative review in which many studies on cybersecurity were sampled and analyzed. The study showed that the main risks that increase cybersecurity threats to agricultural organizations include poor cybersecurity practices, lack of regulations and policies on cybersecurity, and outdated IT software. Moreover, the review indicated that the main cybersecurity threat in agriculture 4.0 and 5.0 involves denial of service attacks that target servers and disrupt the functioning of relevant smart technologies, including equipment for livestock tracking, climate monitoring, logistics and warehousing, and crop monitoring. The analysis also revealed that malware attacks occur when hackers change the code of a system application to access sensitive farm-related data and may alter the operations of the digitized systems. Some of the impacts of cybersecurity breaches were noted to include data loss, reduced efficiency of digitized systems, and reduced food security. A crucial mitigation strategy against cybersecurity threats includes using advanced technologies such as artificial intelligence (AI), blockchain, and quantum computing to improve malware detection in Internet of Things (IoT) digital equipment and ensure faster response to any threats. The other mitigation measures include training employees on best cybersecurity practices and creating guidelines and regulatory standards on best cybersecurity practices.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100616"},"PeriodicalIF":6.3,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging leaf spectroscopy to identify drought-tolerant soybean cultivars","authors":"Ramon Gonçalves de Paula ,&nbsp;Martha Freire da Silva ,&nbsp;Cibele Amaral ,&nbsp;Guilherme de Sousa Paula ,&nbsp;Laércio Junio da Silva ,&nbsp;Herika Paula Pessoa ,&nbsp;Felipe Lopes da Silva","doi":"10.1016/j.atech.2024.100626","DOIUrl":"10.1016/j.atech.2024.100626","url":null,"abstract":"<div><div>Understanding cultivars' physiological traits variations under abiotic stresses is critical to improve phenotyping and selections of resistant crop varieties. Traditional methods of accessing physiological traits in plants are costly and time consuming, which prevents their use in breeding programs. Spectroscopy data and statistical approaches such as partial least square regression could be applied to rapidly collect and predict several physiological parameters at leaf-level, allowing phenotyping several genotypes in a high-throughput manner. We collected spectroscopy data of twenty soybean cultivars planted under well-watered and drought conditions during the reproductive phase. At 20 days after drought was imposed, we measured leaf pigments content (chlorophyll a and b, and carotenoids), specific leaf area, electrons transfer rate, and photosynthetic active radiation. At 28 days after drought imposition, we measured leaf pigments content, specific leaf area, relative water content, and leaf temperature. Partial least square regression models accurately predicted leaf pigments content, specific leaf area, and leaf temperature (cross-validation R² ranging from 0.56 to 0.84). Discriminant analysis using 54 wavelengths was able to select the best-performance cultivars regarding all evaluated physiological traits. We showed the great potential of using spectroscopy as a feasible, non-destructive, and accurate method to estimate physiological traits and screening of superior genotypes.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100626"},"PeriodicalIF":6.3,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of citrus black spot fungi Phyllosticta citricarpa & Phyllosticta capitalensis on UV-C fluorescence images using YOLOv8","authors":"Pappu Kumar Yadav ,&nbsp;Thomas Burks ,&nbsp;Jianwei Qin ,&nbsp;Moon Kim ,&nbsp;Megan M. Dewdney ,&nbsp;Fartash Vasefi","doi":"10.1016/j.atech.2024.100615","DOIUrl":"10.1016/j.atech.2024.100615","url":null,"abstract":"<div><div>Citrus Black Spot (CBS), caused by the pathogenic fungus <em>Phyllosticta citricarpa</em>, is a quarantine citrus disease, that has the potential to spread on nursery tress especially in regions like Florida and beyond. The early detection of this disease assumes paramount importance, especially during the asymptomatic phase of tree infection. This critical stage offers a window of opportunity for grove managers to implement preemptive measures, thereby mitigating the potential dissemination of the infection within orchards. In the present study, we elucidate the robust capabilities of the Contamination Sanitization Inspection-Disinfection Plus (CSI-<em>D</em>+) system, which integrates state-of-the-art fluorescence imaging technology, in tandem with the YOLOv8 deep learning framework. Our investigation is centered on the direct detection of conidia of the CBS-causing fungus <em>P. citricarpa</em> (Gc12) and its non-pathogenic counterpart <em>P. capitalensis</em> (Gm33), both prevalent on surfaces of infected citrus leaves across varying concentration gradients. Impressively, the CSI-<em>D</em>+ system (which is a new, handheld fluorescence-based imaging device developed to detect microbial contamination and disinfect surfaces rapidly) exhibits remarkable discriminatory acumen, achieving a noteworthy mean classification accuracy of 96.97 % for Gc12 fungus classification. This precision is complemented by an impressive F1-score of 96.35 %, coupled with a commendable mAP@50 score of 97.82 %. Furthermore, our inquiry extends to encompass the Gm33 variant, wherein the system maintains a commendable average classification accuracy of 96.17 %, alongside an F1-score of 88.76 %, and a mAP@50 of 91.64 %. Such pioneering systems bear substantial promise, serving as a rapid, non-invasive instrument for the early identification of incipient CBS infestations within citrus arboreal landscapes. In equipping grove managers with timely insights, these advancements stand to empower effective and timely intervention strategies, fortifying orchard resilience against the progression of this pathogenic menace.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100615"},"PeriodicalIF":6.3,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a flexible electronic control unit for seamless integration of machine vision to CAN-enabled boom sprayers for spot application technology","authors":"Mozammel Bin Motalab,&nbsp;Ahmad Al-Mallahi","doi":"10.1016/j.atech.2024.100618","DOIUrl":"10.1016/j.atech.2024.100618","url":null,"abstract":"<div><div>This research work aimed to develop an Electronic Control Unit (ECU) to establish a flexible bridge between machine vision and boom sprayer to control nozzles individually for pesticide spot application based on the Controller Area Network (CAN). The ECU consisted of two electronic entities. The first used UART protocol to parse machine vision messages, detect pest areas, and convert them into binary arrays for nozzle activation. The second received these arrays and generated nozzle controller CAN frames which were broadcast to control the sprayer nozzles on the implement bus. The ECU was tested in four scenarios involving combinations of three machine vision systems and two nozzle systems. The lab tests confirmed, assuming accurate detections, the ECU successfully sent spray commands to all targets across various camera-nozzle ratios. However, at specific ratios (1:3 and 1:6), some nozzles opened in unintended patterns. In the fourth scenario conducted in the field at a 1:2 ratio, all targets were sprayed regardless of their dimensions and distribution in the field. In this scenario, the sprayer operated at speeds of 3.22 km/h, 6.44 km/h, and 9.66 km/h, demonstrating real-time spraying with 55° angled nozzles, where the ECU sent CAN messages every 10ms and issued 400 ms spray commands upon detection, achieving a minimum spray length of 345 mm per detection.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100618"},"PeriodicalIF":6.3,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142554451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PcMNet: An efficient lightweight apple detection algorithm in natural orchards","authors":"Shiwei Wen,&nbsp;Jianguo Zhou,&nbsp;Guangrui Hu,&nbsp;Hao Zhang,&nbsp;Shan Tao,&nbsp;Zeyu Wang,&nbsp;Jun Chen","doi":"10.1016/j.atech.2024.100623","DOIUrl":"10.1016/j.atech.2024.100623","url":null,"abstract":"<div><div>Apple detection plays a critical role in enabling the functionality of harvesting robots within natural orchard environments. To address challenges related to low detection accuracy, slow inference speed, and high parameter count, we present PcMNet, a lightweight detection model based on an improved YOLOv8 network. Initially, we employed Partial Convolution (Pconv) to construct a PR module, forming the Pconv-block, which subsequently replaced the original C2f feature extraction module within the YOLOv8n backbone. This replacement led to improvements in both detection accuracy and speed, while simultaneously reducing computational complexity (FLOPs), parameter count, and model size. Furthermore, the Cross-Scale Feature Fusion (CCFF) module was refined into Faster-Cross-Scale Feature Fusion (Faster-CCFF) with the integration of Pconv-block, significantly enhancing the model's feature extraction and fusion capabilities. Additionally, we introduced Mixed Local Channel Attention (MLCA) to further strengthen the model's capacity to capture essential features while effectively suppressing background noise. Experimental results demonstrate that PcMNet achieved a detection accuracy of 92.8 % and an [email protected] of 95.5 %, representing improvements of 1.4 and 0.7 percentage points, respectively, over YOLOv8n. Moreover, PcMNet successfully reduced FLOPs, parameter count, and model size to 5.1 G, 1.4 M, and 3.2 MB, respectively. The per-image detection time was reduced to 2.3 ms, indicating reductions of 37.80 %, 53.33 %, 49.21 %, and 56.60 % in FLOPs, parameters, model size, and detection time compared to YOLOv8n. When deployed on edge computing devices with TensorRT acceleration, PcMNet achieved a detection rate of 92 FPS. Field validation experiments conducted in natural orchard environments confirmed PcMNet's superior ability to detect apples under challenging conditions, such as occlusions and varying lighting conditions. Its lightweight design and rapid detection capabilities provide a valuable reference for achieving real-time apple detection in automated and intelligent harvesting robots, thereby contributing to advancements in smart agriculture.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100623"},"PeriodicalIF":6.3,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic analysis of scan matching techniques for localization in dense orchards","authors":"Javier Guevara ,&nbsp;Jordi Gené-Mola ,&nbsp;Eduard Gregorio ,&nbsp;Fernando A. Auat Cheein","doi":"10.1016/j.atech.2024.100607","DOIUrl":"10.1016/j.atech.2024.100607","url":null,"abstract":"<div><div>In recent years, different methods have been studied to determine machinery position within a grove, as an alternative for complementing GNSS (global navigation satellite system) information in cases where GNSS signal is occluded. Such a situation can be observed when agricultural machinery travels under dense foliage or on the slopes of mountains. Scan matching techniques arise as a possible solution for localizing the machinery, complementing the absence of the GNSS signal when necessary. However, since key points are difficult to obtain in heterogeneous, unstructured and non-rigid environments (such as orchard plants), the performance of scan matching techniques often decreases in agricultural environments. This paper suggests dividing the point clouds into horizontal and vertical segments to improve the performance of scan-matching methods in orchards. It also examines the best way for registered frames to overlap. We validate the analysis with extensive experimentation in a Fuji apple orchard. The results show that the cumulative localization error in scan matching techniques can be notoriously decreased with selective parts of the orchard, by up to 60%. The experimentation performed herein suggests that the proposed methodology can complement the GNSS navigation in a middle-long path.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"9 ","pages":"Article 100607"},"PeriodicalIF":6.3,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}