The integration of GPS and visual navigation for autonomous navigation of an Ackerman steering mobile robot in cotton fields.

Autonomous navigation in agricultural fields presents a unique challenge due to the unpredictable outdoor environment. Various approaches have been explored to tackle this task, each with its own set of challenges. These include GPS guidance, which faces availability issues and struggles to avoid obstacles, and vision guidance techniques, which are sensitive to changes in light, weeds, and crop growth. This study proposes a novel idea that combining GPS and visual navigation offers an optimal solution for autonomous navigation in agricultural fields. Three solutions for autonomous navigation in cotton fields were developed and evaluated. The first solution utilized a path tracking algorithm, Pure Pursuit, to follow GPS coordinates and guide a mobile robot. It achieved an average lateral deviation of 8.3 cm from the pre-recorded path. The second solution employed a deep learning model, specifically a fully convolutional neural network for semantic segmentation, to detect paths between cotton rows. The mobile rover then navigated using the Dynamic Window Approach (DWA) path planning algorithm, achieving an average lateral deviation of 4.8 cm from the desired path. Finally, the two solutions were integrated for a more practical approach. GPS served as a global planner to map the field, while the deep learning model and DWA acted as a local planner for navigation and real-time decision-making. This integrated solution enabled the robot to navigate between cotton rows with an average lateral distance error of 9.5 cm, offering a more practical method for autonomous navigation in cotton fields.

Development of a Low-Cost Distributed Computing Pipeline for High-Throughput Cotton Phenotyping.

In this paper, we present the development of a low-cost distributed computing pipeline for cotton plant phenotyping using Raspberry Pi, Hadoop, and deep learning. Specifically, we use a cluster of several Raspberry Pis in a primary-replica distributed architecture using the Apache Hadoop ecosystem and a pre-trained Tiny-YOLOv4 model for cotton bloom detection from our past work. We feed cotton image data collected from a research field in Tifton, GA, into our cluster's distributed file system for robust file access and distributed, parallel processing. We then submit job requests to our cluster from our client to process cotton image data in a distributed and parallel fashion, from pre-processing to bloom detection and spatio-temporal map creation. Additionally, we present a comparison of our four-node cluster performance with centralized, one-, two-, and three-node clusters. This work is the first to develop a distributed computing pipeline for high-throughput cotton phenotyping in field-based agriculture.

Evaluation of Inference Performance of Deep Learning Models for Real-Time Weed Detection in an Embedded Computer.

The knowledge that precision weed control in agricultural fields can reduce waste and increase productivity has led to research into autonomous machines capable of detecting and removing weeds in real time. One of the driving factors for weed detection is to develop alternatives to herbicides, which are becoming less effective as weed species develop resistance. Advances in deep learning technology have significantly improved the robustness of weed detection tasks. However, deep learning algorithms often require extensive computational resources, typically found in powerful computers that are not suitable for deployment in robotic platforms. Most ground rovers and UAVs utilize embedded computers that are portable but limited in performance. This necessitates research into deep learning models that are computationally lightweight enough to function in embedded computers for real-time applications while still maintaining a base level of detection accuracy. This paper evaluates the weed detection performance of three real-time-capable deep learning models, YOLOv4, EfficientDet, and CenterNet, when run on a deep-learning-enabled embedded computer, an Nvidia Jetson Xavier AGX. We tested the accuracy of the models in detecting 13 different species of weeds and assesses their real-time viability through their inference speeds on an embedded computer compared to a powerful deep learning PC. The results showed that YOLOv4 performed better than the other models, achieving an average inference speed of 80 ms per image and 14 frames per second on a video when run on an imbedded computer, while maintaining a mean average precision of 93.4% at a 50% IoU threshold. Furthermore, recognizing that some real-world applications may require even greater speed, and that the detection program would not be the only task running on the embedded computer, a lightweight version of the YOLOv4 model, YOLOv4-tiny, was tested for improved performance in an embedded computer. YOLOv4-tiny impressively achieved an average inference speed of 24.5 ms per image and 52 frames per second, albeit with a slightly reduced mean average precision of 89% at a 50% IoU threshold, making it an ideal choice for real-time weed detection.

A Review of Successes and Impeding Challenges of IoT-Based Insect Pest Detection Systems for Estimating Agroecosystem Health and Productivity of Cotton.

Using artificial intelligence (AI) and the IoT (Internet of Things) is a primary focus of applied engineering research to improve agricultural efficiency. This review paper summarizes the engagement of artificial intelligence models and IoT techniques in detecting, classifying, and counting cotton insect pests and corresponding beneficial insects. The effectiveness and limitations of AI and IoT techniques in various cotton agricultural settings were comprehensively reviewed. This review indicates that insects can be detected with an accuracy of between 70 and 98% using camera/microphone sensors and enhanced deep learning algorithms. However, despite the numerous pests and beneficial insects, only a few species were targeted for detection and classification by AI and IoT systems. Not surprisingly, due to the challenges of identifying immature and predatory insects, few studies have designed systems to detect and characterize them. The location of the insects, sufficient data size, concentrated insects on the image, and similarity in species appearance are major obstacles when implementing AI. Similarly, IoT is constrained by a lack of effective field distance between sensors when targeting insects according to their estimated population size. Based on this study, the number of pest species monitored by AI and IoT technologies should be increased while improving the system's detection accuracy.

The Effect of Tractor Speed and Canopy Position on Fungicide Spray Deposition and Peach Scab Incidence and Severity.

Peach scab, caused by Venturia carpophila, is a damaging disease of peach in the southeastern United States. Thus, fungicides are applied to reduce peach scab. Tractor speed was investigated as a variable affecting spray deposition and disease control in relation to volume applied. In experiments in 2015 and 2016, trees were sprayed with fungicide to control scab at petal fall to 1% shuck split and at shuck split to 10% shuck off. Speeds were 3.2, 4.8, and 6.4 kph resulting in 1,403, 935, and 701 liters/ha, respectively, with the dose of active ingredient (a.i.) per ha kept constant. Deposition declined for all speeds with later spray dates. There was a negative linear relationship between tractor speed and spray coverage on three of four dates the experiment was repeated. Tractor speed (different volumes, equal doses) affected peach scab. In 2015 and 2016, mean incidence at 3.2, 4.8, and 6.4 kph was 68.6, 59.2, and 38.3%, and 64.2, 53.0, and 40.4% of fruit scabbed, respectively. Effect of speed on lesion number per fruit depended on year: in 2015, lesions per fruit were reduced at 6.4 kph compared with 3.2 and 4.8 kph but were not different in 2016. Control trees had fewer lesions per fruit high in the canopy, but there was little effect of sample height in fungicide-treated trees. Concentration of a.i. in lower volumes applied at higher speed may provide some benefit in reducing incidence of peach scab, but there appeared to be less effect on severity.

Thrips counts and disease incidence in response to reflective particle films and conservation tillage in cotton and peanut cropping systems.

Feeding damage to seedling cotton and peanut inflicted by adult and immature thrips may result in stunted growth and delayed maturity. Furthermore, adult thrips can transmit Tomato spotted wilt virus (TSWV) to seedling peanut, which reduces plant growth and yield. The objective of this research was to assess the efficacy of inert particle films, calcium carbonate or kaolin, in combination with conservation tillage, to reduce adult and immature thrips counts in cotton and peanut crops. Planting cotton or peanut into strip tillage utilizing a rolled rye winter cover crop significantly reduced immature thrips counts. Furthermore, plant damage ratings in cotton as well as TSWV incidence in peanut significantly decreased under conservation tillage. Aboveground cotton biomass and plant stand in cotton and peanut were unaffected by calcium carbonate or kaolin particle film applications. Within each week, immature thrips counts were unaffected by particle films, regardless of application rate. In cotton plots treated with kaolin, total Frankliniella fusca (Hinds) (Thysanoptera: Thripidae) counts summed across weeks were significantly greater compared to the untreated control. For adult F. fusca counts at 3 weeks after planting, an interaction between tillage and particle film treatments was observed with fewer adult thrips in particle film and strip tillage treated peanut. Similarly, reduced TSWV incidence was observed in particle film-treated peanut grown using conservation tillage. Neither cotton nor peanut yields were affected by particle film treatments.

A customized metal oxide semiconductor-based gas sensor array for onion quality evaluation: system development and characterization.

A gas sensor array, consisting of seven Metal Oxide Semiconductor (MOS) sensors that are sensitive to a wide range of organic volatile compounds was developed to detect rotten onions during storage. These MOS sensors were enclosed in a specially designed Teflon chamber equipped with a gas delivery system to pump volatiles from the onion samples into the chamber. The electronic circuit mainly comprised a microcontroller, non-volatile memory chip, and trickle-charge real time clock chip, serial communication chip, and parallel LCD panel. User preferences are communicated with the on-board microcontroller through a graphical user interface developed using LabVIEW. The developed gas sensor array was characterized and the discrimination potential was tested by exposing it to three different concentrations of acetone (ketone), acetonitrile (nitrile), ethyl acetate (ester), and ethanol (alcohol). The gas sensor array could differentiate the four chemicals of same concentrations and different concentrations within the chemical with significant difference. Experiment results also showed that the system was able to discriminate two concentrations (196 and 1964 ppm) of methlypropyl sulfide and two concentrations (145 and 1452 ppm) of 2-nonanone, two key volatile compounds emitted by rotten onions. As a proof of concept, the gas sensor array was able to achieve 89% correct classification of sour skin infected onions. The customized low-cost gas sensor array could be a useful tool to detect onion postharvest diseases in storage.

Changing a dangerous rural cultural tradition: a randomized control study of youth as extra riders on tractors.

PURPOSE: This study used a randomized control design to evaluate the effectiveness of AgTeen, an in-home, family-based farm safety intervention, in decreasing extra riding on tractors by youth. Having children as extra riders on tractors has deep roots in farm culture, but it can result in serious injury or death. METHODS: The study randomized 151 families into 3 groups: parent-led intervention (fathers taught their families about farm safety), staff-led intervention (staff members who were peer farmers taught families), and a no-treatment control. Mothers, fathers, and all children aged 10-19 participated in the lessons. FINDINGS: At study entry, 93% of youth reported that they had been an extra rider on a tractor in the past year. Although they were aware of the injury risk, fathers frequently gave tractor rides to their children. After the intervention, fathers in both AgTeen groups were less likely than control fathers to give youth tractor rides. Intervention youth were less likely than control youth to be extra riders. The intervention positively affected the extra-riding attitudes and injury risk perceptions of mothers and fathers. The parent-led and staff-led groups did not significantly differ across study outcomes. CONCLUSIONS: Findings confirm the effectiveness of a family-based intervention in decreasing extra riding on tractors by youth.

Electroanalytical studies on green leaf volatiles for potential sensor development.

An electrochemical study for detecting green leaf plant volatiles from healthy and infected plants has been devised and tested. The electrocatalytic response of plant volatiles at a gold electrode was measured using cyclic voltammetry, amperometric current-time (i-t) analysis, differential pulse voltammetry (DPV) and hydrodynamic experiments. The sensitivity of the gold electrode in i-t analysis was 0.13 mA mM(-1) cm(-2) for cis-3-hexenol, 0.11 mA mM(-1) cm(-2) for cis-hexenyl acetate and 0.02 mA mM(-1) cm(-2) for hexyl acetate. The limits of detection of cis-3-hexenol, cis-hexenyl acetate and hexyl acetate by i-t analysis were 0.5, 0.3 and 0.6 µM, respectively, at a signal to noise ratio of 3. The hydrodynamic studies yielded the electro-kinetic parameters such as diffusivities of plant volatiles in solution and the rate constants for their electrochemical reactions. The DPV and interference studies reveal that the gold electrode possessed high sensitivity for plant volatiles determination in synthetic samples, which imitates both healthy and infected plants.

Using insect sniffing devices for detection.

Emerging information about the ability of insects to detect and associatively learn has revealed that they could be used within chemical detection systems. Such systems have been developed around free-moving insects, such as honey bees. Alternatively, behavioral changes of contained insects can be interpreted by sampling air pumped over their olfactory organs. These organisms are highly sensitive, flexible, portable and cheap to reproduce, and it is easy to condition them to detect target odorants. However, insect-sensing systems are not widely studied or accepted as proven biological sensors. Further studies are needed to examine additional insect species and to develop better methods of using their olfactory system for detecting odorants of interest.

Associative learning of odor with food- or blood-meal by Culex quinquefasciatus Say (Diptera: Culicidae).

The ability of many insects to learn has been documented. However, a limited number of studies examining associative learning in medically important arthropods has been published. Investigations into the associative learning capabilities of Culex quinquefasciatus Say were conducted by adapting methods commonly used in experiments involving Hymenoptera. Male and female mosquitoes were able to learn a conditioned stimulus that consisted of an odor not normally encountered in nature (synthetic strawberry or vanilla extracts) in association with an unconditioned stimulus consisting of either a sugar (males and females) or blood (females) meal. Such information could lead to a better understanding of the ability of mosquitoes to locate and select host and food resources in nature.

Behavioral monitoring of trained insects for chemical detection.

A portable, handheld volatile odor detector ("Wasp Hound") that utilizes a computer vision system and Microplitis croceipes (Cresson) (Hymenoptera: Braconidae), a parasitoid wasp, as the chemical sensor was created. Five wasps were placed in a test cartridge and placed inside the device. Wasps were either untrained or trained by associative learning to detect 3-octanone, a common fungal volatile chemical. The Wasp Hound sampled air from the headspace of corn samples prepared within the lab and, coupled with Visual Cortex, a software program developed using the LabView graphical programming language, monitored and analyzed wasp behavior. The Wasp Hound, with conditioned wasps, was able to detect 0.5 mg of 3-octanone within a 240 mL glass container filled with feed corn ( approximately 2.6 x 10(-5) mol/L). The Wasp Hound response to the control (corn alone) and a different chemical placed in the corn (0.5 mg of myrcene) was significantly different than the response to the 3-octanone. Wasp Hound results from untrained wasps were significantly different from trained wasps when comparing the responses to 3-octanone. The Wasp Hound may provide a unique method for monitoring grains, peanuts, and tree nuts for fungal growth associated with toxin production, as well as detecting chemicals associated with forensic investigations and plant/animal disease.