Search

Apple (Malus domestica) fruit size plays an integral role in orchard management decision-making, particularly during chemical thinning, fruit quality assessment, and yield prediction. A machine vision system was developed using stereo cameras synchronised to a custom-built LED strobe to perform on-tree sizing of fruit in images with high measurement accuracy. Two deep neural network models (Faster R–CNN and Mask R–CNN) were trained to detect fruit candidates for sizing followed by extrapolation of occluded fruit regions to improve size estimation. The segmented fruit shapes were converted to metric surface areas and diameters using spatial resolutions and depth information from the stereo cameras. Monthly field trials from June to October using the camera system were conducted, measuring fruit diameters ranging from 22 to 82 mm, and compared against ground truth diameters. Diameter estimates had a mean absolute error ranging from 1.1 to 4.2 mm for the five-month trial period, an average error of 4.8% compared to ground truth diameter measurements. Standard deviation errors ranged from 0.7 to 1.9 mm. Using neural network models for intelligent sampling of fruit in images followed by extrapolation of missing regions can be an alternative method of handling fruit occlusion in agricultural imaging and improving sizing accuracy. [Display omitted] • On-tree apples at various maturity stages were sized using a machine vision system. • Active lighting system enhanced fruit boundary definition to reduce sizing error. • Neural network models identified and extrapolated fruit occlusion. • Imaged estimated diameters and fruit weight had R2 = 0.67 with 4.80% error. • Fruit weight had higher correlation to apple shape in images than diameter. [ABSTRACT FROM AUTHOR]

Applications of convolutional neural network (CNN)-based object detectors in agriculture have been a popular research topic in recent years. However, complicated agricultural environments bring many difficulties for ground truth annotation as well as potential uncertainties for image data quality. Using YOLOv4 as a representation of state-of-the-art object detectors, this study quantified YOLOv4's sensitivity against artificial image distortions including white noise, motion blur, hue shift, saturation change, and intensity change, and examined the importance of various training dataset attributes based on model classification accuracies, including dataset size, label quality, negative sample presence, image sequence, and image distortion levels. The YOLOv4 model trained and validated on the original datasets failed at 31.91% white noise, 22.05-pixel motion blur, 77.38° hue clockwise shift, 64.81° hue counterclockwise shift, 89.98% saturation decrease, 895.35% saturation increase, 79.80% intensity decrease, and 162.71% intensity increase with 30% mean average precisions (mAPs) for four apple flower bud growth stages. The performance of YOLOv4 decreased with both declining training dataset size and training image label quality. Negative samples and training image sequence did not make a substantial difference in model performance. Incorporating distorted images during training improved the classification accuracies of YOLOv4 models on noisy test datasets by 13 to 390%. In the context of apple flower bud growth-stage classification, except for motion blur, YOLOv4 is sufficiently robust for potential image distortions by white noise, hue shift, saturation change, and intensity change in real life. Training image label quality and training instance number are more important factors than training dataset size. Exposing models to test-image-alike training images is crucial for optimal model classification accuracies. The study enhances understanding of implementing object detectors in agricultural research. [ABSTRACT FROM AUTHOR]

• A UAV-LiDAR system utilizing UAV's built-in navigation units was developed. • A colored ICP-based aerial LiDAR point cloud registration algorithm was proposed. • Estimated peach tree parameter accuracy was improved up to 67%. Unmanned aerial vehicle (UAV)-borne light detection and ranging (LiDAR) scanners have been adopted as a promising instrument for plant parameter estimation in agricultural studies recently. However, accurate LiDAR data registration typically requires expensive external navigation devices such as survey-grade global navigation satellite systems (GNSSs) and tactical-grade inertial measurement units (IMUs). Although algorithmic point cloud registration can be an alternative method, the lack of unique landmarks in agricultural fields might bring much difficulty to accurate aerial LiDAR data alignment. In this study, we developed a UAV-LiDAR system employing UAV's built-in navigation units, and proposed a novel approach for registering UAV-LiDAR data of level agricultural fields utilizing a colored iterative closest point (ICP) algorithm and GNSS location and IMU orientation information from the UAV. The proposed algorithm was tested in a peach tree parameter estimation experiment in comparison to GNSS and IMU-based georeferencing. Using manually measured crown widths in two perpendicular dimensions and heights of 11 trees as evaluation metrics, our proposed algorithm achieved a root mean square error (RMSE) range of 0.05 to 0.2 m depending on the tree parameter and flight altitude, and it was able to register tree point clouds up to 67% more accurately in terms of the extracted tree parameters than the georeferencing method. The results demonstrated the potential of the proposed algorithm being a low-cost solution to crop inspection using single-pass aerial LiDAR point clouds from straight-pathed flights, yet future work is still needed to improve the algorithm's adaptability to multi-pass LiDAR data of complex landscapes from flights with curved paths. [ABSTRACT FROM AUTHOR]

[Display omitted] • An LED flash system was developed for daytime agricultural imaging. • System provided colour and brightness consistency in images and reduced motion blur. • Standard deviation of HSV color space in acquired images was reduced by 85%. • Motion blur error in stereo vision application was reduced from 7 mm to 1 mm. • No change in performance was detected for continuous 5-hour usage imaging at 5 Hz. Machine vision systems are being utilized extensively in agriculture applications. Daytime imaging in outdoor field conditions presents challenges such as variable lighting and colour inconsistencies due to sunlight. Motion blur can occur due to vehicle movement and vibrations from ground terrain. A camera system with active lighting can be a solution to overcome these challenges. In this study, the usage of over-current driven LEDs to produce a powerful flash was investigated as a viable light source for daytime imaging. The current drawn by an LED was increased by a factor of six times its normal rating resulting in increased illuminance. A circuit was designed for storing and releasing energy to the LEDs for a strobe-like effect and a controller was used for synchronizing the strobe with a camera to acquire images. The system was deployed in an apple orchard on three days in summer of 2020. Images were taken throughout the day in both sunny and cloudy conditions of different canopy structures. There was substantial improvement in image brightness and colour consistency by using the LED flashes. Images captured by the prototype system during an 11-hour period showed an average decrease of 85% in standard deviation for the Hue-Saturation-Value (HSV) channels compared to that of the auto-exposure setting. Additionally, the prototype system was able to fix motion blur in images averaging 7 mm in error for a stereo vision application with the camera moving at 7 km/hr. These results show that the designed LED flash system can reduce the undesirable effects of lighting variability and motion blur in images stemming from outdoor field conditions. [ABSTRACT FROM AUTHOR]

Frost is a natural disaster that can cause catastrophic damages in agriculture, while traditional temperature monitoring in orchards has disadvantages such as being imprecise and laborious, which can lead to inadequate or wasteful frost protection treatments. In this article, we presented a heating requirement assessment methodology for frost protection in an apple orchard utilizing unmanned aerial vehicle (UAV)-based thermal and RGB cameras. A thermal image stitching algorithm using the BRISK feature was developed for creating georeferenced orchard temperature maps, which attained a sub-centimeter map resolution and a stitching speed of 100 thermal images within 30 s. YOLOv4 classifiers for six apple flower bud growth stages in various network sizes were trained based on 5040 RGB images, and the best model achieved a 71.57% mAP for a test dataset consisted of 360 images. A flower bud mapping algorithm was developed to map classifier detection results into dense growth stage maps utilizing RGB image geoinformation. Heating requirement maps were created using artificial flower bud critical temperatures to simulate orchard heating demands during frost events. The results demonstrated the feasibility of the proposed orchard heating requirement determination methodology, which has the potential to be a critical component of an autonomous, precise frost management system in future studies. [ABSTRACT FROM AUTHOR]

Novel 1‐phenoxy‐3‐(piperazin‐1‐yl)propan‐2‐ol derivatives were designed and synthesized as potential triple reuptake inhibitors, which simultaneously inhibit serotonin, norepinephrine, and dopamine transporters (SERT, NET, and DAT, respectively). Through neurotransmitter transporter uptake assays, inhibitory activities of 1‐phenoxy‐3‐(piperazin‐1‐yl)propan‐2‐ol derivatives were evaluated. We discovered compound 19 exhibited the most potent inhibitory activities against all three monoamine neurotransmitter transporters and the IC50 values of 19 against SERT, NET, and DAT were determined. In addition, binding modes of 19 with SERT, NET, and DAT were predicted by docking studies. [ABSTRACT FROM AUTHOR]

Amphibian biodiversity is declining globally, with over 40% of species being considered threatened to become extinct. Crucial to the success of conservation initiatives are a comprehensive understanding of life history and reproductive ecology of target species. Here we provide an overview of the Pseudacris genus, including breeding behaviour, reproduction, development, survival and longevity. We present an updated distribution map of the 18 species found throughout North America. We also summarize the conservation status at the national and subnational (state, provincial, and territorial) levels, in Canada, USA, and Mexico, to evaluate the relationship between life history traits and extinction risk. Results show a high degree of consistency in the life history traits of Pseudacris species considering their relative diversity and wide distribution in North America. However, data are lacking for several species, particularly in the Fat Frog and West Coast clades, causing some uncertainties and discrepancies in the literature. We also found that the most threatened populations of chorus frog were located in the east coast of the USA, potentially as a result of increased levels of anthropogenic disturbance. We suggest that the similarities in life history traits among chorus frog species provides an opportunity for collaboration and united efforts for the conservation of the genus. [ABSTRACT FROM AUTHOR]

• A data acquisition system for measuring the mushroom picking dynamics was developed. • The bending method was found to be a simple and effective method to detach mushrooms. • A picking end-effector with functions of bending, lifting, and twisting was developed. • The developed mechanism achieved the highest success rate using the bending method. • Acting time and strength of force were studied on mushroom bruise level test. Button mushrooms (Agaricus bisporus) are picked by hand individually, which is time consuming and labor intensive. Robotic harvesting is an alternative method to address this issue. Picking force and motion are critical for developing an effective robotic mushroom picking end-effector. Mushrooms are typically growing in a cluster. Conventional manual mushroom picking comprises a combination motion of twisting, bending, and lifting. To find an effective and simple picking method for robotic harvesting, a series of tests were conducted to compare the picking force and motion among the conventional method and three simplified methods, i.e., bending, twisting, and lifting. A sensor system was developed to measure the picking force and motion with three force sensors and an inertial measurement unit (IMU). The results showed that the conventional picking method required the most orientation changes to detach a mushroom, which could generate complexity for designing a robotic end-effector with the equivalent dexterity. The bending method was simple and effective with the least force compared to the other three methods, with the operation time, detachment angle, and peak force of 0.9 ± 0.5 s,13.6 ± 6.7°, and 3.3 ± 2.4 N respectively. A vacuum picking end-effector was then designed and evaluated with the three simplified methods. The results of picking end-effector evaluation also indicated that the bending motion achieved the best performance, with the picking rate of 100% for these target mushrooms, especially for the clustered ones. The developed picking end-effector can be further improved for an automatic mushroom picking system in the future. [ABSTRACT FROM AUTHOR]

Early detection and counting of immature green citrus fruit using computer vision can help growers produce a predictive yield map which could be used to adjust management practices during the fruit maturing stages. However, such detecting and counting is difficult because of varying illumination, random occlusion and color similarity with leaves. An immature fruit detection algorithm was developed with the aim of identifying and counting fruit in a citrus grove under varying illumination environments and random occlusions using images acquired by a regular red-green-blue (RGB) color camera. Acquired citrus images included front-lighting and back-lighting illumination conditions. The Retinex image enhancement algorithm and the two-dimensional discrete wavelet transform were used for image illumination normalization. Color-based K-means clustering and circular hough transform (CHT) were applied in order to detect potential fruit regions. A Local Binary Patterns feature-based Adaptive Boosting (AdaBoost) classifier was built for removing false positives. A sub-window was used to scan the difference image between the illumination-normalized image and the resulting image from CHT detection in order to detect small areas and partially occluded fruit. An overall accuracy of 85.6% was achieved for the validation set which showed promising potential for the proposed method. [ABSTRACT FROM AUTHOR]

The colonic response to stress is greater in female rats than in male rats. The aim of this study was to evaluate the effect of probiotics in the repeated water avoidance stress (rWAS)-induced colonic microinflammation model of Wistar rats in a sex-specific manner. The three groups (no-stress, WAS, and WAS with probiotics) were exposed to r-WAS for 1 h daily for 10 days, and Lactobacillus farciminis was administered by oral gavage for 10 days to animals in the probiotics group. The visceromotor response (VMR) to colorectal distension (CRD) was assessed using a barostat and noninvasive manometry before and after WAS exposure. Immunohistochemistry for mast cells and real-time polymerase chain reaction (RT-PCR) for detection of mucosal cytokines were performed using distal colon tissue after the animals were sacrificed. Significant reduction of VMR to CRD (visceral analgesia) was observed at 60 mmHg in the female WAS group (P = 0.045), but not in males. In addition, the female WAS with probiotics group showed a significantly lower colonic mucosal mast cell count in comparison to the female WAS group (P = 0.013), but this phenomenon was not observed in the male group. The colonic mucosal mRNA levels of interferon-γ (IFNR), tumor necrosis factor-α (TNFA), interleukin (IL) 6, and IL17 were higher in the female WAS group than in the male WAS group. The mRNA levels of IFNR, TNFA, and IL6 were significantly decreased in WAS females who received probiotics (all P < 0.050). In conclusion, rWAS is induced in a sex-specific manner. A 10-day-long treatment with L. farciminis is an effective therapy for rWAS-induced colonic microinflammation in female rates, but not in male rats. [ABSTRACT FROM AUTHOR]

The aging-associated cellular and molecular changes in esophagus have not been established, yet. Thus we evaluated histological structure, interstitial cells of Cajal (ICCs), neuronal nitric oxide synthase (nNOS)-positive cells, and contractility in the esophagus of Fischer 344 rat at different ages (6-, 31-, 74-weeks, and 2-years). The lamina propria thickness and endomysial area were calculated. The immunoreactivity of c-Kit, nNOS and protein gene product (PGP) 9.5 was counted after immunohistochemistry. Expression of c-Kit, stem cell factor (SCF), nNOS and PGP 9.5 mRNA was measured by real-time PCR, and expression of c-Kit and nNOS protein was detected by Western blot. Isovolumetric contractile force measurement and electrical field stimulation (EFS) were conducted. The lamina propria thickness increased (6 week vs 2 year, P = 0.005) and the endomysial area of longitudinal muscle decreased with aging (6 week vs 2 year, P<0.001), while endomysial area of circular muscle did not significantly decrease. The proportions of NOS-immunoreactive cells and c-Kit-immunoreactive areas declined with aging (6 week vs 2 year; P<0.001 and P = 0.004, respectively), but there was no significant change of PGP 9.5-immunopositiviy. The expressions of nNOS, c-Kit and SCF mRNA also reduced with aging (6 week vs 2 year; P = 0.006, P = 0.001 and P = 0.006, respectively), while the change of PGP 9.5 mRNA expression was not significant. Western blot showed the significant decreases of nNOS and c-Kit protein expression with aging (6 week vs 2 year; P = 0.008 and P = 0.012, respectively). The EFS-induced esophageal contractions significantly decreased in 2-yr-old rat compared with 6-wk-old rats, however, L-NG-Nitroarginine methylester did not significantly increase the spontaneous and EFS-induced contractions in the 6-wk- and 2-yr-old rat esophagus. In conclusion, an increase of lamina propria thickness, a decrease of endomysial area, c-Kit, SCF and NOS expression with preserved total enteric neurons, and contractility in aged rat esophagus may explain the aging-associated esophageal dysmotility. [ABSTRACT FROM AUTHOR]

• A Mask R-CNN based fire blight detection and segmentation system was introduced. • ResNet-50 and ResNet-101 backbone were used for feature extraction. • The transfer learning approach was used to reduce data requirement. • Vegetation indices were calculated to analyze the individual index sensitivity to apple fire blight. • Results suggest that the system can detect fire blight in complex orchard conditions. Advanced sensing technologies and deep learning models are needed for automatic recognition of pathogens to protect trees in orchards. This study developed a fire blight disease detection and infected area segmentation system using image processing and deep learning approaches to automate the detection process in a complex apple orchard environment for site-specific management. Two types of images were acquired: multispectral images from an unmanned aerial vehicle (UAV) using a multispectral camera and red–greenblue (RGB) images from the ground using two different cameras. Multispectral images were preprocessed and used for image feature analysis by calculating vegetation indices, including excessive blue (ExB), normalized difference vegetation index (NDVI), green normalized difference vegetation index (GNDVI), red-edge normalized difference vegetation index (RENDVI), modified ratio vegetation index (RVI), and triangular blueness index (TBI). Vegetation indices were calculated from a total of 60 multispectral images (30 heathy and 30 fire blight infected). Results showed that RVI was most sensitive to fire blight infection among the six indices. A support vector machine model was used to classify unhealthy tree canopies. A Mask Region-Convolutional Neural Network (Mask R-CNN) based deep learning model was developed from RGB infected images. A total of 880 images were used for training, and 220 images were used for validation. Another 110 images were used for testing the trained Mask R-CNN model. A precision of 92.8 % and recall of 91.2 % were obtained by detecting the infected canopies using a ResNet-101 backbone and intersection over union (IoU) threshold of 0.7. The high precision demonstrates the effectiveness of Mask R-CNN for the identification and segmentation of fire blight infection in images taken in complex orchard conditions. These results prove the potential of this non-invasive sensing method in detecting disease in commercial fruit production for site-specific infected canopies removing. [ABSTRACT FROM AUTHOR]

• A sensor fusion-based tree canopy point correction system was developed. • A mathematical model was developed to perform the simulation for the correction of canopy points. • The model could provide the corrected canopy point location for any change of roll, pitch, and yaw. • The developed system could be able to reduce up to 15.45% of off-target deposition. Precision spraying is one of the most promising techniques to produce healthy and sustainably profitable crops. However, accurate canopy density measurements for precision spraying decisions are still a challenging endeavor, especially in orchards with uneven terrain conditions. A sensor fusion-based canopy point correction system was developed with a 3D light detection and ranging (LiDAR) sensor and an inertial navigation system-global navigation satellite system (INS-GNSS) for accurate tree canopy density measurement. The LiDAR sensor was used to acquire the tree canopy architectures, while the INS-GNSS sensor was to evaluate the terrain slopes and the tree georeferenced locations. A mathematical model was developed to perform the simulation for correction of canopy points based on given changes in the roll, pitch, and yaw angles. A sensor fusion algorithm was developed to process the canopy point corrections for the tree fruit orchards with three different sloping conditions, including longitudinal, lateral, and combination of both slopes. Simulation results reported that the developed model established the correction of tree canopy points with varying roll, pitch, and yaw angles. Field evaluation results suggested that the developed system could be used for correcting canopy points at any sloping conditions in various terrains. The measured tree canopy density from the corrected canopy points reported a possible of off-target chemical reduction up to 13.87%, 5.19%, and 15.45% in orchard sites 1, 2 and 3, respectively. With the accurate tree canopy density measurement, it is anticipated that the developed system could be used to reduce the off-target deposition for precision spraying applications in uneven tree fruit orchards. [ABSTRACT FROM AUTHOR]

• Highlighted the status and challenges in developing a robotic pruner. • Recent technological advancements for robotic pruning were reviewed. • Different components of the robotic pruning system were reviewed in detail. • Discussed the future opportunities of developing robotic pruner for apple trees. Automation and robotics have been widely applied in many agricultural operations; however, the production operations of apple trees are usually performed manually. Pruning is one of the most labor-intensive operations, accounting for about 20% of the total labor costs. Robotic pruning is a potential long-term solution to deal with the issue of labor shortages and associated high costs. In recent years, researchers have advanced technologies that could lead to the development of a robotic pruning system. However, numerous challenges are involved for successful adoption of robotic pruning technologies. This review highlighted the technological progress in the core components of a robotic pruner including machine vision, manipulator, end-effector, path planning, and obstacle avoidance; the challenges associated with the existing technologies; and potential solutions to the development of an automated pruning system. The review covers both scientific/research and commercial technologies developed for robotic tree pruning. The available literature related to all technological components of a robotic pruning system was reviewed in detail, and useful information was synthesized for presenting in the paper. Finally, the paper scrutinizes the challenges and potential future opportunities for developing a robotic pruning system for a sustainable apple production system. [ABSTRACT FROM AUTHOR]

• A 3D tree canopy characterization system was integrated for precision spraying. • Segmentation of tree trunk, trellis wires, and support poles was performed. • A correlation of 0.95 (R2 = 89.30%) between points and leaves was achieved with Fuji variety. • Canopy volume showed a strong correction of 0.98 (R2 = 95.90%) to leave number. • Canopy density map was generated to visualize leaves distribution. An unmanned ground-based canopy density measurement system to support precision spraying in apple orchards was developed to precisely apply pesticides to orchard canopies. The automated measurement system was comprised of a light detection and ranging (LiDAR) sensor, an interface box for data transmission, and a laptop computer. A data processing and analysis algorithm was developed to measure point cloud indices from the LiDAR sensor to describe the distribution of tree canopy density within four sections according to the position of the trellis wires. Experiments were conducted in two orchard sites, one with GoldRush (larger trees) and the other one with Fuji (smaller trees) apple trees. Tree leaves were counted manually from each section separated by trellis wires. Field evaluation results showed a strong correlation of 0.95 (R2 = 89.30%) between point cloud data and number of leaves for the Fuji block and a correlation of 0.82 (R2 = 67.16%) was obtained for the GoldRush block. A strong correlation of 0.98 (R2 = 95.90%) was achieved in the relationship between canopy volume and number of leaves. Finally, a canopy density map was generated to provide a graphical view of the tree canopy density in different sections. Since accurate canopy density information was computed, it is anticipated that the developed prototype system can guide the sprayer unit for reducing excessive pesticide use in orchards. [ABSTRACT FROM AUTHOR]

• A 3R DoF end-effector was integrated with a cartesian manipulator for tree pruning. • Reachable workspace, dexterity and manipulability of the end-effector were analyzed. • The end-effector was able to reach branches with an appropriate cutter orientation. • The shear cutter was able to cut ≤25 mm diameter branches of different orientations. Robotic pruning is a potential solution to address the issues of labor shortages and high associated costs, but it has challenges due to the unstructured working environment. For successful robotic pruning, target branches have to be reached with fewer spatial requirements for the end-effector cutter and the manipulator. A three-rotational (3R) degrees of freedom (DoF) end-effector was designed considering maneuvering, spatial, mechanical, and horticultural requirements. Simulations were conducted with the end-effector to investigate the reachable workspace, the cutter frame orientation, and the manipulability index. The simulation results suggested that the proposed design has a spherical reachable workspace with a void due to the presence of a physical constraint of the linear arm. The manipulability index was determined to be independent of the rotation of the first and last joint of the end-effector. The prototype of the proposed end-effector was integrated with a cartesian manipulator. An Arduino-based control system was developed along utilizing a Matlab graphical user interface (GUI). A series of field tests were conducted on 'Fuji'/Bud. 9 apple trees with trellis-trained architecture. The field tests validated the simulation results, and the end-effector successfully cut branches up to ~25 mm diameter at wide range of orientations. This study provides the foundation for future investigations of branch accessibility for pruning with an integrated 3R end-effector and a cartesian manipulator system following a collision free trajectory. [ABSTRACT FROM AUTHOR]

Anti-neutrophil cytoplasmic antibody (ANCA)-associated vasculitis is an autoimmune disorder which affects small- and, to a lesser degree, medium-sized vessels. ANCA-associated vasculitis encompasses three disease phenotypes: granulomatosis with polyangiitis (GPA), microscopic polyangiitis (MPA), and eosinophilic granulomatosis with polyangiitis (EGPA). This classification is largely based on clinical presentations and has several limitations. Recent research provided evidence that genetic background, risk of relapse, prognosis, and co-morbidities are more closely related to the ANCA serotype, proteinase 3 (PR3)-ANCA and myeloperoxidase (MPO)-ANCA, compared to the disease phenotypes GPA or MPA. This finding has been extended to the investigation of biomarkers predicting disease activity, which again more closely relate to the ANCA serotype. Discoveries related to the immunopathogenesis translated into clinical practice as targeted therapies are on the rise. This review will summarize the current understanding of the immunopathogenesis of ANCA-associated vasculitis and the interplay between ANCA serotype and proposed disease biomarkers and illustrate how the extending knowledge of the immunopathogenesis will likely translate into development of a personalized medicine approach in the management of ANCA-associated vasculitis. [ABSTRACT FROM AUTHOR]

The original version of this article unfortunately contained a mistake. The affiliation “China West Normal University” should be removed from the author Dr. Chenglin Wang. The correct affiliation details are given below. [ABSTRACT FROM AUTHOR]