An improved YOLO network for unopened cotton boll detection in the field

Detection of cotton bolls in the field environments is one of crucial techniques for many precision agriculture applications, including yield estimation, disease and pest recognition and automatic harvesting. Because of the complex conditions, such as different growth periods and occlusion among leaves and bolls, detection in the field environments is a task with considerable challenges. Despite this, the development of deep learning technologies have shown great potential to effectively solve this task. In this work, we propose an Improved YOLOv5 network to detect unopened cotton bolls in the field accurately and with lower cost, which combines DenseNet, attention mechanism and Bi-FPN. Besides, we modify the architecture of the network to get larger feature maps from shallower network layers to enhance the ability of detecting bolls due to the size of cotton boll is generally small. We collect image data of cotton in Aodu Farm in Xinjiang Province, China and establish a dataset containing 616 high-resolution images. The experiment results show that the proposed method is superior to the original YOLOv5 model and other methods such as YOLOv3,SSD and FasterRCNN considering the detection accuracy, computational cost, model size and speed at the same time. The detection of cotton boll can be further applied for different purposes such as yield prediction and identification of diseases and pests in earlier stage which can effectively help farmers take effective approaches in time and reduce the crop losses and therefore increase production.

Acquisition and Transmission of Fusarium oxysporum f. sp. vasinfectum VCG 0114 (Race 4) by Stink Bugs

Fusarium oxysporum f. sp. vasinfectum VCG 0114 (race 4; i.e., FOV4) is an emerging pathogen that causes severe root rot and wilt of cotton. FOV4 is seed-borne, but the mode of seed invasion is uncertain. In an initial study, seeds in bolls that were puncture inoculated with FOV4 conidia when they were 25- or 30-days old became infected but remained viable. Because stink bugs can ingest and introduce bacterial and yeast pathogens into cotton bolls, we hypothesized that stink bugs may ingest and transmit FOV4. Southern green stink bugs and brown stink bugs were exposed to potato dextrose agar cultures of FOV4 and subsequently caged with cotton bolls to assess transmission potential. Both species fed on the cultures and acquired FOV4, and brown stink bugs transmitted FOV4 to cotton bolls. Thus, management of FOV4 may require management of stink bugs to mitigate the spread of the disease in cotton.

CHAP: Cotton-Harvesting Autonomous Platform

The US cotton industry provided over 190,000 jobs and more than $28 billion total economic contributions to the United States in 2012. The US is the third-largest cotton-producing country in the world, following India and China. US cotton producers have been able to stay competitive with countries like India and China by adopting the latest technologies. Despite the success of technology adoption, there are still many challenges, e.g., increased pest resistance, mainly glyphosate resistant weeds, and early indications of bollworm resistance to Bt cotton (genetically modified cotton that contains genes for an insecticide). Commercial small unmanned ground vehicle (UGV) or mobile ground robots with navigation-sensing modality provide a platform to increase farm management efficiency. The platform can be retrofitted with different implements that perform a specific task, e.g., spraying, scouting (having multiple sensors), phenotyping, harvesting, etc. This paper presents a proof-of-concept cotton harvesting robot. The robot was retrofitted with a vacuum-type system with a small storage bin. A single harvesting nozzle was used and positioned based on where most cotton bolls were expected. The idea is to create a simplified system where cotton bolls′ localization was undertaken as a posteriori information, rather than a real-time cotton boll detection. Performance evaluation for the cotton harvesting was performed in terms of how effective the harvester suctions the cotton bolls and the effective distance of the suction to the cotton bolls. Preliminary results on field test showed an average of 57.4% success rate in harvesting locks about 12 mm from the harvester nozzle. The results showed that 40.7% was harvested on Row A while 74.1% in Row B for the two-row test. Although both results were promising, further improvements are needed in the design of the harvesting module to make it suitable for farm applications.

Source of Metal Ions on Raw Cotton Fibers and their Influence on Dyeing

This work reports on two debated points related to the metal content of cotton fiber and its influence on processing. The first issue is if the metal levels of raw fibers are naturally deposited during fiber development or if the levels are influenced by weathering and harvesting conditions present after boll opening. This was tested by harvesting bolls just as they were opening and after the opened bolls were allowed to field age. The second issue relates to the importance of metal levels on fiber dyeability. Results indicate that the metal levels of newly-opened cotton were not appreciably different from those of aged cotton bolls and that the fiber metal levels after scouring and bleaching had little correlation with dye uptake. Additionally, some metal levels exceeded those previously reported and the environment appeared to have a stronger influence on fiber Ca and Mg levels than did cultivar differences.

Fusarium Hardlock Associated With Lygus lineolaris (Hemiptera: Miridae) Injury in Southeastern Cotton

The tarnished plant bug, Lygus lineolaris (Palisot de Beauvois), is an important insect pest in cotton that feeds on reproductive fruit, contributing to yield loss. Economically damaging infestations of L. lineolaris have doubled in Virginia since 2013. Escalation of L. lineolaris abundance may increase Fusarium hardlock disease observed in this region, compounding economic losses. Research has linked Fusarium hardlock with fungal species Fusarium verticillioides and F. proliferatum. Field and greenhouse experiments were performed to investigate (i) Fusarium hardlock occurrence in field plots managed and unmanaged for L. lineolaris, (ii) severity of F. verticillioides infection of cotton bolls with and without the presence of L. lineolaris feeding in a greenhouse setting, and (iii) Fusarium species composition and prevalence within field-collected L. lineolaris and cotton lint with and without insect feeding injury and hardlock symptoms present. Nearly twice the amount of hardlock (i.e., proportion of hardlocked locules) occurred in field-collected bolls with L. lineolaris feeding symptoms (0.40 ± 0.02) compared with bolls without (0.21 ± 0.01). Based on real-time quantitative PCR, cotton bolls exposed to F. verticillioides inoculum and caged with L. lineolaris adults had greater levels of F. verticillioides DNA compared with untreated bolls. F. proliferatum, F. verticillioides, and F. fujikuroi were isolated from field-collected L. lineolaris and hardlocked cotton lint at harvest. These findings suggest that the presence of L. lineolaris is associated with an increased risk of Fusarium hardlock in Southeastern cotton, and both should be carefully managed using timely insecticide applications and cultural control practices to minimize yield loss.

Ensemble Method of Deep Learning, Color Segmentation, and Image Transformation to Track, Localize, and Count Cotton Bolls Using a Moving Camera in Real-Time

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.

Effect of four irrigation doses and four varieties on cotton bolls component, lint ratio and quality

Cotton is an industrial crop grown both in the north and in the Southern hemisphere and is one of the most profitable crops. Water is the resource that will be the most limited, especially for agriculture in the coming years. Irrigation availability is a critical factor in growing cotton in hot and dry climates. The experiments were performed in central Greece, in Palamas of the Karditsa region, for two years (2015-2016). The treatments were four different irrigation regimes, where IRR. 2 and IRR. 4 were deficient irrigations, IRR. 6, was a sufficient and IRR. 8, were overflow. Four varieties of cotton (Dp 419, Campo, Andromeda, Lider) were used where the effects of irrigation on cotton boll characteristics were recorded. The measurements made concerned the agronomic as well as the qualitative characteristics of the cotton bolls such as lint proportion, seed percentage, oil content, oil yield and micronaire. The oil content had positive correlation with the lint proportion and negative correlation with the seed percentage. In the both years of experiments the IRR. 2 and IRR. 8, irrigation regimes had negative effects while IRR. 4 and IRR. 6 had positive effects. Also among the varieties, Andromeda and Lider were the ones that stood out in both years.