• Rural Digital Europe

Weeding operations represent an effective approach to increase crop yields. Reliable and precise weed detection is a prerequisite for achieving high-precision weed monitoring and control in precision agriculture. To develop an effective approach for detecting weeds within the red, green, and blue (RGB) images, two state-of-the-art object detection models, EfficientDet (coefficient 3) and YOLOv5m, were trained on more than 26,000 in situ labeled images with monocot/dicot classes recorded from more than 200 different fields in Denmark. The dataset was collected using a high velocity camera (HVCAM) equipped with a xenon ring flash that overrules the sunlight and minimize shadows, which enables the camera to record images with a horizontal velocity of over 50 km h-1. Software-wise, a novel image processing algorithm was developed and utilized to generate synthetic images for testing the model performance on some difficult occluded images with weeds that were properly generated using the proposed algorithm. Both deep-learning networks were trained on in-situ images and then evaluated on both synthetic and new unseen in-situ images to assess their performances. The obtained average precision (AP) of both EfficientDet and YOLOv5 models on 6625 synthetic images were 64.27% and 63.23%, respectively, for the monocot class and 45.96% and 37.11% for the dicot class. These results confirmed that both deep-learning networks could detect weeds with high performance. However, it is essential to verify both the model’s robustness on in-situ images in which there is heavy occlusion with a complicated background. Therefore, 1149 in-field images were recorded in 5 different fields in Denmark and then utilized to evaluate both proposed model’s robustness. In the next step, by running both models on 1149 in-situ images, the AP of monocot/dicot for EfficientDet and YOLOv5 models obtained 27.43%/42.91% and 30.70%/51.50%, respectively. Furthermore, this paper provides information regarding challenges of monocot/dicot weed detection by releasing 1149 in situ test images with their corresponding labels (RoboWeedMap) publicly to facilitate the research in the weed detection domain within the precision agriculture field.

Weed spatial distribution was measured with a ground-based weed mapping system. The system consists of three different components: i) weed detection by optoelectronic sensors; ii) weed geopositioning by DGPS receiver; and iii) a data acquisition and processing system. Three optoelectronic modules were mounted on the front of a tractor at a 0.75 cm distance between them and at 60 cm height above ground level. Consequently, the system was able to explore a 2.25 m band [isn't that more than one row? This is with all three sensors?], corresponding to three crop rows, detecting the vegetation present in the middle of the inter-rows maize area. The working capacity of the system was higher than 1 ha h-1. The weed mapping system was evaluated in three maize fields during spring, when the crop was [in/at] 4-to-6 leaves stage. In order to verify the system with highly reliable data, digital images were obtained in random geo-referenced points distributed throughout the three fields. Three experienced observers rated these images for weed presence/absence, using a presence threshold of 15% weed cover. The comparison between the data obtained with the ground-weed mapping system and from the values derived from visual assessments of the digital images indicated a good agreement (84% on average) between the two sets of data. The comparison among the results obtained with various simulated distances between sensors (from 1.5 m to 6.0 m) indicated that the ground-based system could construct weed maps accurately using a distance between optic sensors of 4.5 m. This research was funded by the Spanish CICyT (project AGL 2005-06180-C03 and project AGL 2008-04670-C03). Peer reviewed

Vegetation on traffic routes is not only an aesthetic problem. On railways and roads, it poses a safety risk by reducing the elasticity of track beds or damaging road surfaces. Therefore, complex weed management is indispensable. This is currently achieved mainly through the extensive use of herbicides or manual removal, which pollutes the environment and incurs high costs. These negative impacts can be mitigated by an automated vegetation detection which allows efficient, targeted treatment and preventive long-term monitoring. A reliable method to achieve this is to exploit the characteristic spectral fingerprint of vegetation: Chlorophyll shows a high reflectivity in the green and infrared spectral region while strongly absorbing red and blue light. We present such a visual monitoring system comprising multiple cameras and an active illumination which is employed on railroads. The individual cameras address different spectral regions and are superimposed through a position-synchronized triggering to obtain a multi-spectral image. Multi-pixel binning greatly extends the dynamic range of the cameras and, in combination with active illumination and high-speed dark frame recording, allows operation during day and night without degradation from ambient light conditions. The system achieves about 5 mm effective resolution and can operate up to a speed of 100 km/h. This is possible through embedded real-time pre-processing and data reduction already in the camera units. A processing delay of less than 100 ms is the consequence which allows targeted actuation of weed-treatment methods (e.g., spray nozzles) during movement. In combination with GNSS-sensors geo-referenced documentation of the coverage rate is possible.

In this paper, we propose a new approach for discriminating maize and weed plants from soil surface, evaluating the accuracy and performance of a LiDAR sensor for vegetation detection using distance and reflection values. Field measurements were conducted in a maize field at growth stage BBCH 12-14. Static measurements were taken at different sampling areas with different weed densities. Regression analyses were carried out to assess the capabilities of the system for vegetation and soil measurement. A high relationship between LiDAR measured distance (LiDAR heights) and actual height was found. A binary logistic regression was used to predict the presence or absence of vegetation. The results permitted the discrimination of vegetation from the soil with accuracy up to 95%. This technique offers significant promise for the development of real-time spatially selective weed control techniques, either as the sole weed detection system or in combination with other detection tools. This project was funded by the foundation ‘Alfonso Martín Escudero’. The stay of Mr Hugo Moreno in Uni-Hohenheim as a Master de Agroingenieria– UPM student was funded by a mobility grant from Ministerio de Educación, Cultura y Deporte by the Spanish Government. Peer reviewed

In this study, an automatic system based on open AI architectures was developed and fed with an in-house built image dataset to recognize seven of the most widespread and hard-to-control weeds in wheat in the Mediterranean environment. A total of 10810 images were collected from the post-emergence (S1 dataset) to the pre-flowering stage (S2 dataset). A selection of pictures available from online sources (S3, 825 images) was used as a final and further independent test of the proposed recognition tool. The AI tool in the ensemble configuration achieved 100% accuracy on the validation and test set both for S1 and S2, while for S3 an accuracy of approximately 70% was achieved for weed species in the post-emergence stage.

Artificial Intelligence, specifically deep learning, is a fast-growing research field today. One of its various applications is object recognition, making use of computer vision. The combination of these two technologies leads to the purpose of this thesis. In this project, a system for the identification of different crops and weeds has been developed as an alternative to the system present on the FarmBot company’s robots. This is done by accessing the images through the FarmBot API, using computer vision for image processing, and artificial intelligence for the application of transfer learning to a RCNN that performs the plants identification autonomously. The results obtained show that the system works with an accuracy of 78.10% for the main crop and 53.12% and 44.76% for the two weeds considered. Moreover, the coordinates of the weeds are also given as results. The performance of the resulting system is compared both with similar projects found during research, and with the current version of the FarmBot weed detector. Form a technological perspective, this study presents an alternative to traditional weed detectors in agriculture and open the doors to more intelligent and advanced systems.

{"references": ["ISBN 0-7167-1031-5 Janick, Jules. Horticultural Science. San Francisco:\nW.H. Freeman, 1979. Page 308.", "B. L. Steward And L. F. Tian, \"Real-Time Weed Detection In Outdoor\nField Conditions,\" In Proc. Spie Vol. 3543, Precision Agriculture And\nBiological Quality, Boston, Ma, Jan. 1999, Pp. 266-278.", "J. E. Hanks, \"Smart Sprayer Selects Weeds for Elimination,\"\nAgricultural Research, Vol. 44, No 4, Pp. 15, 1996.", "J. S. Weszka, C. R. Dyer, And A. Rosenfeld, \"A Comparative Study\nOf Texture Measures For Terrain Classification,\" IEEE Transactions on\nSystems, Man, And Ccybernetics , Smc, Vol. 6, Pp. 269-285, 1976.", "Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing. 2nd\nEd. Delhi: Pearson Education, Inc, 2003, Page 617,618.", "Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing. 2nd\nEd. Delhi: Pearson Education, Inc, 2003, Page 119,161,167,172.", "Rulph Chasseing, Digital Signal Processing With C and the Tms320c30,\nMcgraw-Hill, Inc.", "M.A.Sid-Ahmed, Image Processing Theroyalgorithms & Arghitectures,\nMcgraw-Hill, Inc.", "Graig A. Lindley. Practal Image Processing In C. Acquisition.\nManipulation. Storage.\n[10] Paul Davies. The Indispensable Guide To C, First Printed 1995,\nReprinted 1996.\n[11] Arun D. Kulkarni, Computer Vision And Fuzzy-Neural Systems,\nPrentice Hall Ptr.\n[12] Beck, J. A. Sutter And R. Ivry. 1987. Spatial Frequency Channels and\nPerceptual Grouping In Texture Segregation. Computer Vision,\nGraphics, And Image Processing."]} The identification and classification of weeds are of major technical and economical importance in the agricultural industry. To automate these activities, like in shape, color and texture, weed control system is feasible. The goal of this paper is to build a real-time, machine vision weed control system that can detect weed locations. In order to accomplish this objective, a real-time robotic system is developed to identify and locate outdoor plants using machine vision technology and pattern recognition. The algorithm is developed to classify images into broad and narrow class for real-time selective herbicide application. The developed algorithm has been tested on weeds at various locations, which have shown that the algorithm to be very effectiveness in weed identification. Further the results show a very reliable performance on weeds under varying field conditions. The analysis of the results shows over 90 percent classification accuracy over 140 sample images (broad and narrow) with 70 samples from each category of weeds.

The accurate weed detection is the premise for precision prevention and control of weeds in fields. Machine vision offers an effective means to detect weeds accurately. For precision detection of various weeds in carrot fields, this paper improves You Only Look Once v4 (YOLO v4) into a lightweight weed detection model called YOLO v4-weeds for the weeds among carrot seedlings. Specifically, the backbone network of the original YOLOv4 was replaced with MobileNetV3-Small. Combined with depth-wise separable convolution and inverted residual structure, a lightweight attention mechanism was introduced to reduce the memory required to process images, making the detection model more efficient. The research results provide a reference for the weed detection, robot weeding, and selective spraying.