Search

US cotton producers are motivated to optimize planter performance to ensure timely and uniform stand establishment early in the season, especially when planting in sub-optimal field conditions. Field studies were conducted in 2017, 2018 and 2019 to evaluate the effect of seeding depth and planter downforce on crop emergence and yield in cotton planted in different soil moisture conditions. Field conditions representative of dry, normal and wet soil moisture conditions were attained by applying 0, 1.27 and 2.54 cm of irrigation within the same field. Two cotton cultivars (representing a small-seeded and a large-seeded cultivar, 9259–10,582 and 11,244–14,330 seeds kg−1, respectively), were planted at seeding depths of 1.3, 2.5 and 3.8 cm with each seeding depth paired with three different planter downforces of 0, 445 and 890 N in each block. Cotton was planted in plots that measured 3.66 m (four-rows) wide by 10.67 m long. Results indicated that crop emergence was affected by the seeding depth across most field conditions and higher crop emergence was observed in the large-seeded cultivar at 1.3 and 3.8 cm seeding depths in dry and wet field conditions, respectively. Lint yield was also higher for the large-seeded cultivar at the 3.8 cm seeding depth across all field conditions in 2017, and in dry field conditions in 2018. Planter downforce effect on crop emergence varied among the cultivars where the large-seeded cultivar exhibited higher crop emergence than the small-seeded cultivar at 445 and 890 N downforce. Planter downforce of 445 N yielded greater than the 0 and 890 N treatment in dry field conditions in 2017. The study results suggest that matching planter depth and downforce settings for prevalent soil moisture conditions at planting along with appropriate cultivar selection can help in achieving optimal emergence and yield in cotton.

Automation continues to play a greater role in agricultural production with commercial systems now available for machine vision identification of weeds and other pests, autonomous weed control, and robotic harvesters for fruits and vegetables. The growing availability of autonomous machines in agriculture indicates that there are opportunities to increase automation in cotton production. This article considers how current and future advances in automation has, could, or will impact cotton production practices. The results are organized to follow the cotton production process from land preparation to planting to within season management through harvesting and ginning. For each step, current and potential opportunities to automate processes are discussed. Specific examples include advances in automated weed control and progress made in the use of robotic systems for cotton harvesting.

HighlightsAn ensemble method using color segmentation, deep learning, and image transformation was developed.Experiments were conducted to compare the method with other state-of-the-art tracking algorithms.The optimized ensemble method to track bolls achieved 94.4% accuracy using weakly trained tiny YOLOv2 models.The method achieved 7.6 frames per second and outperformed five other tracking methods.Abstract. In robotic applications, good perception can be computationally costly and create undesirable latency before a control decision is initiated. Most of the methods available for object detection deep learning are either fast with low accuracy or slow with high accuracy. Fast and accurate methods are necessary to track and localize objects such as cotton bolls that may be visible or occluded by each other or not well illuminated. In this study, an ensemble of a deep learning method and other image processing techniques was used to detect cotton bolls in-field on defoliated plants. In each image, a trained deep learning method, the YOLOv2 model, was used to detect open cotton bolls, and color segmentation was applied to confirm if the bolls detected by the YOLOv2 model were actually white to avoid false positives. Boll tracking was performed by following the spatial movement of good features on the edges of the bolls using the Lucas-Kanade algorithm. An image transformation algorithm was applied to the next image in case the previously detected boll was lost to retrieve the information of the missing boll. Each tracked and localized boll was stored and counted to give the total number of bolls detected. In this study, detection accuracy was sacrificed for image processing speed by using the YOLOv2 model. Detection accuracy was improved by using an ensemble method that combined image color segmentation, optical flow, and image transformation. This method was compared to eight other open-source methods implemented in OpenCV. The ensemble method detected and counted bolls at a speed of 7.6 fps with an accuracy of 94.4% using the Jetson TX2 embedded system to process 1K resolution images, outperforming the other OpenCV methods in various measurements. Keywords: Boll counting, Cotton, Cotton harvesting, DarkFlow, Darknet, Deep learning, Machine vision, YOLOv2.

Maintaining adequate planter downforce is critical for achieving timely and uniform crop emergence across the field. On-farm research studies were conducted in different regions across South Georgia, USA to investigate the effect of planter downforce in varying soil textures. Six fields were planted in cotton with four different growers from 2017 to 2019. Soil electrical conductivity (EC) was mapped in each field to characterize areas of varying soil textures into low, medium and high soil EC zones. For each field, the downforce treatments consisted of a grower-preferred downforce along with a relatively lower and higher downforce dependent on prevalent field conditions and the downforce system available on the grower’s planter. Results varied from field to field depending on soil texture variability or the type of downforce system. In three out of six fields, emergence was delayed and reduced in areas of high soil EC (heavy textured soils) whereas soil EC or downforce did not affect crop emergence in two fields. In one field, increasing planter downforce from the grower preferred value of 555 N to 1110 N improved crop emergence in heavy textured soils. In some cases, it was noted that even the highest downforce (1110 N) was not sufficient to place seeds at the desired seeding depth in the heavy textured soils. More on-farm studies are required to thoroughly understand planter downforce response in varying field conditions that exist during planting. Future studies should consider better quantification of in-field soil variability and changes in planter downforce during field operation.

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.

In this review, we examine opportunities and challenges for 21st-century robotic agricultural cotton harvesting research and commercial development. The paper reviews opportunities present in the agricultural robotics industry, and a detailed analysis is conducted for the cotton harvesting robot industry. The review is divided into four sections: (1) general agricultural robotic operations, where we check the current robotic technologies in agriculture; (2) opportunities and advances in related robotic harvesting fields, which is focused on investigating robotic harvesting technologies; (3) status and progress in cotton harvesting robot research, which concentrates on the current research and technology development in cotton harvesting robots; and (4) challenges in commercial deployment of agricultural robots, where challenges to commercializing and using these robots are reviewed. Conclusions are drawn about cotton harvesting robot research and the potential of multipurpose robotic operations in general. The development of multipurpose robots that can do multiple operations on different crops to increase the value of the robots is discussed. In each of the sections except the conclusion, the analysis is divided into four robotic system categories; mobility and steering, sensing and localization, path planning, and robotic manipulation.

Cotton (Gossypium hirsutum L.) growers are motivated to reduce seeding rates due to increased technology fees associated with improved transgenic cotton cultivars. Advances in planting machinery have improved precision of seed metering and seed placement in recent years. A two-year study was conducted to evaluate the effect of seeding rate, planter downforce, and cultivar on crop emergence and lint yield in cotton planted as singulated and hill-drop (two seed hill-1) configuration. Study treatments consisted of two seeding rates (71,660 and 107,490 seed ha-1), two to three planter downforces (0, 445 and 890 N in 2017; 0 and 890 N in 2018) and two cotton cultivars (representing a large-seeded and small-seeded cultivar, 9,259 - 10,582 and 11,244 - 14,330 seed kg-1, respectively) arranged in a strip-split plot design in both seeding configurations. Crop emergence and lint yield in the middle two rows (four-row plots) were measured to evaluate treatment effects among seeding configurations. Results showed that seeding rate and cultivar did not affect (p>0.05) crop emergence and lint yield in both singulated and hill-drop cotton. Crop emergence varied between the two years due to differences in field tillage conditions. Planter downforce affected crop emergence in singulated cotton but not in hill-drop cotton during both years. Field tillage conditions also influenced downforce effect on crop emergence. Selection of an optimal planter downforce had more significant effect (p

Weeds are a persistent problem on sod farms, and herbicides to control different weed species are one of the largest chemical inputs. Recent advances in unmanned aerial systems (UAS) and artificial intelligence provide opportunities for weed mapping on sod farms. This study investigates the weed type composition and area through both ground and UAS-based weed surveys and trains a convolutional neural network (CNN) for identifying and mapping weeds in sod fields using UAS-based imagery and a high-level application programming interface (API) implementation (Fastai) of the PyTorch deep learning library. The performance of the CNN was overall similar to, and in some classes (broadleaf and spurge) better than, human eyes indicated by the metric recall. In general, the CNN detected broadleaf, grass weeds, spurge, sedge, and no weeds at a precision between 0.68 and 0.87, 0.57 and 0.82, 0.68 and 0.83, 0.66 and 0.90, and 0.80 and 0.88, respectively, when using UAS images at 0.57 cm–1.28 cm pixel–1 resolution. Recall ranges for the five classes were 0.78–0.93, 0.65–0.87, 0.82–0.93, 0.52–0.79, and 0.94–0.99. Additionally, this study demonstrates that a CNN can achieve precision and recall above 0.9 at detecting different types of weeds during turf establishment when the weeds are mature. The CNN is limited by the image resolution, and more than one model may be needed in practice to improve the overall performance of weed mapping.

This paper discusses a technique for identifying stress in plants using 4D models to determine stressed areas based on height and growth rates. The developed algorithm segments the field into low, medium, and high stress regions to provide warnings to the grower that an issue might exist. This algorithm was tested on a field of peanut plants and showed that high stressed regions produced 20% lower yield than low stressed regions on average. This metric can provide the grower with an early warning that regions of relatively high stress exists within their field that will have an impact on yield.

This study proposes an algorithm that controls an autonomous, multi-purpose, center-articulated hydrostatic transmission rover to navigate along crop rows. This multi-purpose rover (MPR) is being developed to harvest undefoliated cotton to expand the harvest window to up to 50 days. The rover would harvest cotton in teams by performing several passes as the bolls become ready to harvest. We propose that a small robot could make cotton production more profitable for farmers and more accessible to owners of smaller plots of land who cannot afford large tractors and harvesting equipment. The rover was localized with a low-cost Real-Time Kinematic Global Navigation Satellite System (RTK-GNSS), encoders, and Inertial Measurement Unit (IMU)s for heading. Robot Operating System (ROS)-based software was developed to harness the sensor information, localize the rover, and execute path following controls. To test the localization and modified pure-pursuit path-following controls, first, GNSS waypoints were obtained by manually steering the rover over the rows followed by the rover autonomously driving over the rows. The results showed that the robot achieved a mean absolute error (MAE) of 0.04 m, 0.06 m, and 0.09 m for the first, second and third passes of the experiment, respectively. The robot achieved an MAE of 0.06 m. When turning at the end of the row, the MAE from the RTK-GNSS-generated path was 0.24 m. The turning errors were acceptable for the open field at the end of the row. Errors while driving down the row did damage the plants by moving close to the plants&rsquo, stems, and these errors likely would not impede operations designed for the MPR. Therefore, the designed rover and control algorithms are good and can be used for cotton harvesting operations.

Cotton harvesting is performed by using expensive combine harvesters which makes it difficult for small to medium-size cotton farmers to grow cotton economically. Advances in robotics have provided an opportunity to harvest cotton using small and robust autonomous rovers that can be deployed in the field as a &ldquo, swarm&rdquo, of harvesters, with each harvester responsible for a small hectarage. However, rovers need high-performance navigation to obtain the necessary precision for harvesting. Current precision harvesting systems depend heavily on Real-Time Kinematic Global Navigation Satellite System (RTK-GNSS) to navigate rows of crops. However, GNSS cannot be the only method used to navigate the farm because for robots to work as a coordinated multiagent unit on the same farm because they also require visual systems to navigate, avoid collisions, and to accommodate plant growth and canopy changes. Hence, the optical system remains to be a complementary method for increasing the efficiency of the GNSS. In this study, visual detection of cotton rows and bolls was developed, demonstrated, and evaluated. A pixel-based algorithm was used to calculate and determine the upper and lower part of the canopy of the cotton rows by assuming the normal distribution of the high and low depth pixels. The left and right rows were detected by using perspective transformation and pixel-based sliding window algorithms. Then, the system determined the Bayesian score of the detection and calculated the center of the rows for the smooth navigation of the rover. This visual system achieved an accuracy of 92.3% and an F1 score of 0.951 for the detection of cotton rows. Furthermore, the same stereo vision system was used to detect the location of the cotton bolls. A comparison of the cotton bolls&rsquo, distances above the ground to the manual measurements showed that the system achieved an average R2 value of 99% with a root mean square error (RMSE) of 9 mm when stationary and 95% with an RMSE of 34 mm when moving at approximately 0.64 km/h. The rover might have needed to stop several times to improve its detection accuracy or move more slowly. Therefore, the accuracy obtained in row detection and boll location estimation is favorable for use in a cotton harvesting robotic system. Future research should involve testing of the models in a large farm with undefoliated plants.

Multiple small rovers can repeatedly pick cotton as bolls begin to open until the end of the season. Several of these rovers can move between rows of cotton, and when bolls are detected, use a manipulator to pick the bolls. To develop such a multi-agent cotton-harvesting system, each cotton-harvesting rover would need to accomplish three motions: the rover must move forward/backward, turn left/right, and the robotic manipulator must move to harvest cotton bolls. Controlling these actions can involve several complex states and transitions. However, using the robot operating system (ROS)-independent finite state machine (SMACH), adaptive and optimal control can be achieved. SMACH provides task level capability for deploying multiple tasks to the rover and manipulator. In this study, a center-articulated hydrostatic cotton-harvesting rover, using a stereo camera to locate end-effector and pick cotton bolls, was developed. The robot harvested the bolls by using a 2D manipulator that moves linearly horizontally and vertically perpendicular to the direction of the rover&rsquo, s movement. We demonstrate preliminary results in an environment simulating direct sunlight, as well as in an actual cotton field. This study contributes to cotton engineering by presenting a robotic system that operates in the real field. The designed robot demonstrates that it is possible to use a Cartesian manipulator for the robotic harvesting of cotton, however, to reach commercial viability, the speed of harvest and successful removal of bolls (Action Success Ratio (ASR)) must be improved.

Improving plant photosynthesis provides the best possibility for increasing crop yield potential, which is considered a crucial effort for global food security. Chlorophyll fluorescence is an important indicator for the study of plant photosynthesis. Previous studies have intensively examined the use of spectrometer, airborne, and spaceborne spectral data to retrieve solar induced fluorescence (SIF) for estimating gross primary productivity and carbon fixation. None of the methods, however, had a spatial resolution and a scanning throughput suitable for applications at the canopy and sub-canopy levels, thereby limiting photosynthesis analysis for breeding programs and genetics/genomics studies. The goal of this study was to develop a hyperspectral imaging approach to characterize plant photosynthesis at the canopy level. An experimental field was planted with two cotton cultivars that received two different treatments (control and herbicide treated), with each cultivar-treatment combination having eight replicate 10 m plots. A ground mobile sensing system (GPhenoVision) was configured with a hyperspectral module consisting of a spectrometer and a hyperspectral camera that covered the spectral range from 400 to 1000 nm with a spectral sampling resolution of 2 nm. The system acquired downwelling irradiance spectra from the spectrometer and reflected radiance spectral images from the hyperspectral camera. On the day after 24 h of the DCMU (3-(3,4-dichlorophenyl)-1,1-dimethylurea) application, the system was used to conduct six data collection trials in the experiment field from 08:00 to 18:00 with an interval of two hours. A data processing pipeline was developed to measure SIF using the irradiance and radiance spectral data. Diurnal SIF measurements were used to estimate the effective quantum yield and electron transport rate, deriving rapid light curves (RLCs) to characterize photosynthetic efficiency at the group and plot levels. Experimental results showed that the effective quantum yields estimated by the developed method highly correlated with those measured by a pulse amplitude modulation (PAM) fluorometer. In addition, RLC characteristics calculated using the developed method showed similar statistical trends with those derived using the PAM data. Both the RLC and PAM data agreed with destructive growth analyses. This suggests that the developed method can be used as an effective tool for future breeding programs and genetics/genomics studies to characterize plant photosynthesis at the canopy level.

Small rovers are being developed to pick cotton as bolls open. The concept is to have several of these rovers move between rows of cotton, and when bolls are detected, use a manipulator to pick the bolls. To accomplish this goal, each cotton-picking robot needs to accomplish three movements; rover must move forward/backward, left/right and the manipulator must be able to move to harvest the detected cotton bolls. Control of these actions can have several states and transitions. Transitions from one state to another can be complex but using ROS-independent finite state machine (SMACH), adaptive and optimal control can be achieved. SMACH provides task level capability to deploy multiple tasks to the rover and manipulator. In this research, a cotton-picking robot using a stereo camera to locate end-effector and cotton bolls is developed. The robot harvests the bolls using a 2D manipulator that moves linearly horizontally and vertically. The boll 3-D position is determined by calculating stereo camera parameters, and the decision of the finite state machine guides the manipulator and the rover to the destination. PID control is deployed to control rover movement to the boll. We demonstrate preliminary results in a direct-sun simulated environment. The system achieved a picking performance of 17.3 seconds per boll. Also, it covered the task by navigating at a speed of 0.87 cm per second collecting 0.06 bolls per second. In each mission, the system was able to detect all the bolls but one.

Here, we present a novel presymptomatic disease detection method by utilizing electrical capacitance tomography (ECT) for plant root monitoring. This was achieved by enhancing the signal with iron oxide nanoparticles (IONPs). IONPs were added to healthy and underdeveloped tomato plants during the course of one and a half months while ECT measurements were collected. The readings for the IONP-exposed samples showed an enhancement over the unexposed samples. This enhancement was greater in the healthy plants when compared with the underdeveloped plants. We also verified earlier claims that ECT can be used for presymptomatic disease detection in bell pepper plants inoculated with Phytophthora capsici ( PCap ). The healthy plants all showed a continuous increase in capacitance over a 2-week period, while the inoculated plants showed a sudden spike in capacitance 12-24 hours before wilting and browning of the stem occurred. The results from these studies indicate that IONP-enhanced electrical capacitance tomography is a non-destructive, in-situ , and rapid method to monitor relative root health, and that ECT can detect disease presymptomatically.

Robotic harvesting involves navigation and environmental perception as first operations before harvesting of the bolls can commence. Navigation is the distance required for a harvester‘s arm to reach the cotton boll while perception is the position of the boll relative to surrounding environment. These two operations give a 3D position of the cotton boll for picking and can only be achieved by detection and tracking of the cotton bolls in real-time. It means detection, tracking and counting of cotton bolls using a moving camera allows the robotic machine to harvest easily. GPU-accelerated deep neural networks were used to train the convolution networks for detection of cotton bolls. It was achieved by using pretrained tiny yolo weights and DarkFlow, a framework which translates YOLOv2 darknet neural networks to TensorFlow. A method to connect tracklets using vectors that are predicted using Lucas-Kanade algorithm and optimized using robust L-estimators and homography transformation is proposed. The system was tested in defoliated cotton plants during the spring of 2018. Using three video treatments, the counting performance accuracy was around 93% with standard deviation 6%. The system average processing speed was 21 fps in desktop computer and 3.9 fps in embedded system. Detection of the system achieved an accuracy and sensitivity of 93% while precision was 99.9% and F1 score was 1. The Tukey‘s test showed that the system accuracy and sensitivity was the same when the plants were rearranged. This performance is crucial for real-time robot decisions that also measure yield while harvesting.

Helicoverpa zea (Boddie) is a major insect pest of corn and other agricultural crops. An improved understanding of semiochemcials that control adult behavior is needed to develop alternative control measures. In this study, overnight SPME collection of volatiles from corn ears enclosed in Teflon bags in the field at two stages of development were made. C8–C10 aldehydes, a C8-alcohol, C6–C9 alcohol acetates, and numerous monoterpenes, sesquiterpenes, sequiterpene alcohols, and geosmin were identified after thermal desorption and GC/MS. Structural assignments of the alcohol acetates, Z-3-hexenyl acetate, 2-heptyl acetate, 2-nonyl acetate, and 4-nonyl acetate, the monoterpenes, α- and β-ocimene, and geosmin were made by analysis of standards that were purchased or prepared in the laboratory. All other assignments were based on published Kovat’s retention time indices (KI) and mass spectra. Pair-wise comparison of the relative amounts of each component between two groups of corn ears defined by silk weight did not identify significant differences, thus it is unknown whether or not silk weight impacted volatile emission composition and rate. To our knowledge three compounds detected in SPME collections, 2-heptyl acetate, 2-nonyl acetate, and 4-nonyl acetate have not been previously reported in corn ear or silk volatiles. Their impact on the flight response of gravid earworm females was evaluated in a flight chamber. No significant response to the individual compounds or a blend of all three was observed. Thus, their impact on moth behavior remains uncertain.

Damage to seedling cotton as a result of feeding by adult and immature thrips can result in stunted growth and reduced plant stand. Transmission of Tomato spotted wilt virus by thrips in peanut can result in reduced yield and plant stand. The objectives of this research were to examine the effects of planting cotton and peanut into conventionally (no soil residue) tilled plots or planting into reduced tillage plots including rolled rye and standing rye (cotton only) tillage in conjunction with thiamethoxam seed treatments on seedling thrips counts, thrips associated injury in cotton, Tomato spotted wilt virus incidence in peanut, and yield for both crops. Conservation tillage practices consistently reduced adult and immature thrips populations in cotton. Standing rye residues suppressed thrips similarly to rolled rye, but yielded less lint in one of the two years. Thiamethoxam seed treatment effects were inconsistent, although general numerical trends suggest that this practice can suppress immature thrips for up to three weeks in cotton. Thiamethoxam seed treatment either had no effect or significantly improved cotton lint yield depending on year. Conservation tillage was also effective at reducing immature thrips in peanut. Incidence of Tomato spotted wilt virus in peanut was decreased in conservation tilled plots in 2013, but was slightly greater in 2014. Similarly, effects of tillage on peanut yield were significant but inconsistent between years. Thiamethoxam seed treatments did not consistently reduce thrips in peanut nor did it improve yield in either year. These data demonstrate conservation tillage and thiamethoxam seed treatments are generally effective practices for reducing thrips densities; however, effects on yield and disease transmission were inconsistent.

The overall goal of this study was to test a customized gas sensor array in its ability to detect an important postharvest disease (sour skin) in onions. The sensor array consists of seven metal oxide semiconductor gas sensors and a microcontroller-based automatic data logging system. Three features were extracted from the sensor responses and three baseline correction methods were employed to correct the sensors’ responses. The gas sensor array was tested in two separate experiments with two treatments (control and sour skin). The multivariate data analysis revealed that the “relative response” feature combined with relative baseline correction method provided the best discrimination of infected onions among healthy ones. The best performance (85%) was achieved by using the support vector machine model when the data collected from an independent experiment were used for validation. The study demonstrated the potential of a gas sensor array to detect sour skin-infected onions placed among healthy onions in storage.

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.

A pure-pursuit navigational control algorithm in an autonomous articulated-steer vehicle was studied as a simple method for path-following. Paths were created using GPS coordinates and the articulated-steer vehicle programmed to follow those paths using a pure-pursuit (goal-seeking) path-following algorithm. A GUI was developed in LabVIEW to read RTK-GPS coordinates, hydraulic pressure and articulation angle, and control the articulated-steer vehicle. The vehicle was tested for its ability to follow five different paths with two speeds and three control pulse signals. Path following succeeded with lower vehicle speed and full pulse signal for the straight and sinusoidal paths. Averaged path-following errors ranged from 6 to 19 cm as the turn radius increased. For a 90 degree turn, the path-following error was almost 80 cm. Path-following improvements could be made with faster control signal updates and a variable look-ahead distance based on vehicle speed and required turning angle. It was concluded that the control architecture is a good basis for navigation of an articulated-steer autonomous vehicle.

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. Language: en

Screening cargo for illicit substances is in need of rapid high-throughput inspection systems that accurately identify suspicious cargo. Here we investigate the ability of a parasitic wasp, Microplitis croceipes to detect and respond to methyl benzoate, the volatile component of cocaine, by examining their response to training concentrations, their sensitivity at low concentrations, and their ability to detect methyl benzoate when two concealment substances (green tea and ground coffee) are added to the testing arena. Utilizing classical associative learning techniques with sucrose as reward, we found that M. croceipes learns individual concentrations of methyl benzoate, and they can generalize this learning to concentrations 100× lower than the training concentration. Their sensitivity to methyl benzoate is very low at an estimated 3 ppb. They are also able to detect methyl benzoate when covered completely by green tea, but were not able to detect methyl benzoate when covered completely by coffee grounds. Habituation to the tea and coffee odors prior to testing improves their responses, resulting in effective detection of methyl benzoate covered by the coffee grounds. With the aid of the portable device called ‘the wasp hound’, the wasps appear to have potential to be effective on-site biosensors for the detection of cocaine.

PURPOSE: Farm youth continue to experience high rates of injury and deaths as a result of agricultural activities. Farm machinery, especially tractors, is the most common cause of casualties to youth. A Roll-Over Protection Structure (ROPS) along with a fastened seatbelt can prevent almost all injuries and fatalities from tractor overturns. Despite this knowledge, the use of seatbelts by farmers on ROPS tractors remains low. This study treats farm safety as a family issue and builds on the central role of parents as teachers and role models of farm safety for youth. METHODS: This research study used a longitudinal, repeated-measures, randomized-control design in which youth 10-19 years of age were randomly assigned to either of two intervention groups (parent-led group and staff-led group) or the control group. RESULTS: Fathers in the parent-led group were less likely to operate ROPS tractors without a seatbelt compared with other groups. They were more likely to have communicated with youth about the importance of wearing seatbelts on ROPS tractors. Consequently, youth in the parent-led group were less likely to operate a ROPS tractor without a seatbelt than the control group at post-test. CONCLUSIONS: This randomized control trial supports the effectiveness of a home-based, father-led farm safety intervention as a promising strategy for reducing youth as well as father-unsafe behaviors (related to tractor seatbelts) on the farm. This intervention appealed to fathers' strong motivation to practice tractor safety for the sake of their youth. Involving fathers helped change both father as well as youth unsafe tractor-seatbelt behaviors. Language: en

Blueberry mechanical harvesters cause bruise damage to the fruit. The goal of this study was to test a custom-made sensor (berry impact recording device) to measure the quality and magnitude of mechanical impacts created by three major types of commercial blueberry mechanical harvesters (rotary, slapper, and sway). The sensor was mounted on blueberry bushes (cultivated) and harvested at standard operating conditions such that the sensor was detached and experienced the impact forces typically found during a mechanical harvesting process. The data collected by the sensor revealed that the slapper and sway harvesters generated not only larger number but also higher magnitude impacts than the rotary. Our analyses suggest that these disparities were mostly caused by different agitating mechanisms, contacting surface materials, and designs between the three harvesters. Results indicated that most impacts lasted 5-7ms in all three harvesters. The distribution of the impacts showed that 90% of impacts from the rotary were less than 190g and 90% of impacts from the slapper and sway were less than 250g. Corresponding measures were identified to reduce potential bruise damage in the harvesters. The information could be useful to select harvesters that create the least impacts and to improve current mechanical harvester designs.

The objective of this research was to test the applicability of using electrical capacitance tomography (ECT) as a rapid, in situ, and non-destructive method to monitor root health and detect disease before visual symptoms present. Two studies were performed. The first study compared capacitance measurements of healthy and stunted tomato plants. ECT measurements showed a slight increase (34%) in capacitance for the stunted group, while the healthy plants displayed a large increase (67%). The second study compared ECT measurements of healthy bell pepper plants and pepper plants exposed to Phytophthora capsici (PCap). The inoculated plants that died showed a sudden spike in capacitance (~52%) 12-24 hours before wilting and browning of the stem occurred. The healthy plants all showed a greater increase in capacitance compared with inoculated plants that survived for the same monitoring period. The results from the two studies indicate that ECT is a rapid and non-destructive method to monitor root health and detect disease pre-symptomatically.

Southern highbush blueberries (Vaccinium corymbosum interspecific hybrids) are predominantly for the fresh market and, with a few exceptions, are hand harvested. Though mechanical harvesting systems are available for processed blueberries, low harvest efficiency and high fruit damage have limited their use for picking blueberries for fresh market. To improve the current machine harvester design, it is apparent that the interaction between the machine harvester and fruit should be well understood. The goal of this study was, therefore, to provide such an understanding by using a custom-made miniature instrumented sphere. The miniature Berry Impact Recording Device (BIRD) was used to measure the mechanical impacts created by a rotary mechanical harvester during fruit harvesting. A closeup video recorded the harvesting to pinpoint critical control points where most impacts were created. The results showed that the catch plates on the rotary harvester accounted for over 30% of all mechanical impacts imposed on the BIRD, followed by the empty fruit collection box (lug) (>20%). Impacts created by the conveyer belt and shaking rods combined accounted for only 25% of mechanical impacts. Thus, the most significant reduction in bruising could be achieved through modifications in the catch plates and lugs. The impact of three contacting surfaces (the catch plates, conveyer belt, and steel tunnel) on the harvester and three commercial padding materials (Cellular Silicone, Slow Rebound, and No Bruze) were evaluated. Harvester surface evaluations revealed that the catch plate was the hardest surface. Among the three padding materials evaluated, the Cellular Silicone provided the best cushioning. This study proved the efficacy of using a customized miniature instrumented sphere in measuring mechanical impacts created by various machine parts during harvesting. It provided a better understanding of how the berries interact with different machine parts of a rotary harvester.

Developing data acquisition software is a major challenge in integrating a spectral imaging system. This paper presents the design and implementation of a data acquisition program using LabVIEW for a liquid crystal tunable filter based spectral imaging system (900-1700nm). The module-based program was designed in a three-tier structure. The image acquisition process, modelled by a finite state machine, was implemented in LabVIEW to control the spectral imaging system to collect hyperspectral or multispectral images. The collected spectral images were encoded in general format and could be further processed by other common spectral image analysis tools. In addition, the program could be used to observe band ratio images of the test object in real-time, collect spectral images after ensemble averaging, and select region of interest for spectral image acquisitions. This program is a useful data acquisition tool for the filter-based spectral imaging system. The design and implementation techniques described in this article could also be used to develop similar spectral image acquisition programs.

Sour skin (Burkholderia cepacia) is a major postharvest disease for onions and causes substantial production and economic losses in onion postharvest. In this study, a shortwave infrared hyperspectral imaging system was explored to detect sour skin. The hyperspectral reflectance images (950–1650 nm) of onions were obtained for the healthy and sour skin-infected onions. Principal component analysis conducted on the spectra of the healthy and sour skin-infected onions suggested that the neck area of the onion at two wavelengths (1070 and 1400 nm) was most indicative of the sour skin. Log-ratio images utilizing the two optimal wavelengths were used for two different image analysis approaches. The first method applied a global threshold (0.45) to segregate the sour skin-infected areas from log-ratio images. Using the pixel number of the segregated areas, Fisher’s discriminant analysis recognized 80% healthy and sour skin-infected onions. The second classification approach used three parameters (max, contrast, and homogeneity) of the log-ratio images as the input features of support vector machine (Gaussian kernel, γ = 1.5), which discriminated 87.14% healthy and sour skin-infected onions. The result of this study can be used to further develop a multispectral imaging system to detect sour skin-infected onions on packing lines.

Calibration is a critical step for developing spectral imaging systems. This paper presents a systematic calibration and characterization approach for a liquid crystal tunable filter (LCTF) based shortwave infrared (SWIR) spectral imaging system. A series of tests were conducted to validate the linearity of the system output, measure the field of view of the spectral imager, increase the system spectral sensitivity, test the spatial and spectral resolution of the system, evaluate the system stability and image distortion, and reduce the spectral noise of the system output. Results showed that the system had an angle of view of 6.98^o and a spatial resolution of 158@mm. The spectral sensitivity of the system was corrected by controlling the camera exposure time and gain, which increased the signal to noise ratio of the system by 16.5%. Test results also verified the system spectral accuracy and linearity (r>0.999). The system output was proven to be stable and image distortion was not perceivable. Results of calibration tests indicated that this system satisfied the design criteria in both spatial and spectral domains. The calibration methods presented here are applicable to the LCTF-based spectral imaging systems in other applications.

This paper presents the methodology to design and integrate a liquid crystal tunable filter (LCTF) based shortwave infrared (SWIR) spectral imaging system. The system consisted of an LCTF-based SWIR spectral imager, an illumination unit, a frame grabber, and a computer with the data acquisition software. The spectral imager included an InGaAs camera (320x256 pixels), an SWIR lens (50mm, F/1.4), and an LCTF (20mm aperture). Four multifaceted reflector halogen lamps (35W, 12 VDC) were used to build the illumination unit. The system was integrated by a LabVIEW program for data acquisition. It can capture hyperspectral or multispectral images of the test object in the spectral range of 900-1700nm. The system was validated by differentiating sugar from wheat flour, and water from 95% ethanol. The results showed that the system can distinguish these materials in both spectral and spatial domains. This SWIR spectral imaging system could be a potential useful tool for nondestructive inspection of food quality and safety.

This paper reports a complete impact data acquisition, processing, and analyzing software system that applies on the hardware platform of the Berry Impact Recording Device (BIRD). The software has three major sections that correspond to the hardware: The BIRD sensor program, the interface box program, and the computer software i-BIRD. The sensor program samples acceleration data from three axes and records them as single impacts with a maximum sampling rate of 3.0 kHz. Users can configure the sensor via the i-BIRD computer software, with different options of sampling frequencies (682–3050 Hz) and thresholds (0–205 g , where g is the gravitational acceleration). The data recorded can be downloaded, processed and graphically displayed on the computer. A real time clock was created using the interrupt service routine provided by the microcontroller. The accuracy of the sensor’s clock was calibrated with an error of 0.073%, which was adequate to record impact data in this application. The shape of impact curves recorded by the BIRD sensor at three sampling frequencies (682, 998, and 1480 Hz) matched well with the curves recorded by a high frequency (10 kHz) data logger with the maximum root mean squared error of 4.4 g. The velocity change had a relative error less than 5%. With confirmation of all those performances, the software system enabled the BIRD to be a useful tool to collect impact data during small fruit (such as blueberry) mechanical harvest.

Agricultural technology has increased farm production to unprecedented levels. However, return on investment is diminishing and environmental concerns conflict with current input intensive farm practices. Conventional technologies and their application such as crop breeding and management practices have focused on monocultural systems that are dependent on chemical inputs to produce optimum yields. Current profit margins are low or non-existent with these conventional non-sustainable practices and must be changed if the family farm is to survive. We propose an ecologically based approach to farm management that strives to reduce reliance on chemically intensive inputs through better use of multiple attributes inherent within agroecosystems. This approach requires a redirection in the development and application of current and emerging technologies. Examples of redirections in research and development programs for pest management practices, genetic engineering, and precision agriculture necessary to provide a more ecologically-based and sustainable farming approach are illustrated.

The off-flavor boar taint associated with the substances skatole, androstenone, and possibly indole represents a significant problem in the pig husbandry industry. Boar taint may occur in meat from uncastrated sexually mature male pigs; consumers commonly show a strong aversion to tainted meat. Consequently, there is a need for rapid methods to sort out and remove tainted carcasses at the slaughterline. We tested the ability of wasps, Microplitis croceipes to perceive and learn the 3 boar taint compounds both individually and in combination using classical conditioning paradigms. We also established the effectiveness and reliability of boar taint odor detection when wasps were used as biosensors in a contained system called the “wasp hound” using a cohort of trained wasps. We found that the wasps are able to successfully learn indole, skatole and to also detect them when presented a 1: 1: 1 mixture of all 3 compounds. This was shown for both a single hand-manipulated wasp bioassay and when using the “wasp hound” detector device. In contrast, the wasps showed a weak conditioned response to androstenone at the concentration tested. The estimated gas phase concentrations that the wasps perceived during training were in the range of 10 ± 0.4 pg/s for skatole and indole, and 2 ± 0.5 pg/s for androstenone. We conclude that use of these wasps as biosensors presents a promising method for boar taint detection and discuss future training paradigms that may improve their responses to compounds such as androstenone. Practical Application: The development of a perceptive, inexpensive, and reliable means of detecting boar taint before the product is presented to sensitive consumers.