Weed Density Detection Method Based on Absolute Feature Corner Points in Field

Field weeds identification is challenging for precision spraying, i.e., the automation identification of the weeds from the crops. For rapidly obtaining weed distribution in field, this study developed a weed density detection method based on absolute feature corner point (AFCP) algorithm for the first time. For optimizing the AFCP algorithm, image preprocessing was firstly performed through a sub-module processing capable of segmenting and optimizing the field images. The AFCP algorithm improved Harris corner to extract corners of single crop and weed and then sub-absolute corner classifier as well as absolute corner classifier were proposed for absolute corners detection of crop rows. Then, the AFCP algorithm merged absolute corners to identify crop and weed position information. Meanwhile, the weed distribution was obtained based on two weed density parameters (weed pressure and cluster rate). At last, the AFCP algorithm was validated based on the images that were obtained using one typical digital camera mounted on the tractor in field. The results showed that the proposed weed detection method manifested well given its ability to process an image of 2748 × 576 pixels using 782 ms as well as its accuracy in identifying weeds reaching 90.3%. Such results indicated that the weed detection method based on AFCP algorithm met the requirements of practical weed management in field, including the real-time images computation processing and accuracy, which provided the theoretical base for the precision spraying operations.

Download Full-text

Distribution, Density, and Abundance of Parthenium Weed (Parthenium hysterophorus L.) at Kuala Muda, Malaysia

International Journal of Agronomy ◽

10.1155/2018/1046214 ◽

2018 ◽

Vol 2018 ◽

pp. 1-8 ◽

Cited By ~ 1

Author(s):

C. M. Maszura ◽

S. M. R. Karim ◽

M. Z. Norhafizah ◽

F. Kayat ◽

M. Arifullah

Keyword(s):

Relative Density ◽

Weed Management ◽

Distribution Density ◽

Integrated Weed Management ◽

Management Approach ◽

Weed Density ◽

Weed Distribution ◽

Weed Infestation ◽

Using Data ◽

Parthenium Weed

Knowledge of distribution, density, and abundance of weed in a place is a prerequisite for its proper management. Parthenium hazard is a national agenda in Malaysia, and Kedah is the worst infested state in the country. Despite it, the distribution and abundance of the weed is not systematically documented. Periodical weed surveys were conducted at Kuala Muda, Kedah, during March and September 2015 to identify infested locations, to determine density, abundance, and severity of infestation, and to do mapping of weed distribution of the area. Geographic locations were recorded using a GPS. Weed density was measured following the list count quadrat method. The mapping of weed infestation was done by the ArcGIS software using data of GPS and weed density. Different letters were used to indicate the severity of infestation. Results indicated that in Kuala Muda, sixteen sites are infested having average weed density of 10.6 weeds/m2. The highest density was noted at Kg. Kongsi 6 (24.3 plants/m2). The relative density was highest at Semeling (27.25%) followed by Kg. Kongsi 6 (23.14%). The average severity of infestation was viewed as the medium. Parthenium abundance and relative density increased by 18.0% and 27%, respectively, in the second survey conducted. The intervention of concerned authority to tackle the weed problem using integrated weed management approach is emphasized.

Download Full-text

Can Commercial Low-Cost Drones and Open-Source GIS Technologies Be Suitable for Semi-Automatic Weed Mapping for Smart Farming? A Case Study in NE Italy

Remote Sensing ◽

10.3390/rs13101869 ◽

2021 ◽

Vol 13 (10) ◽

pp. 1869

Author(s):

Pietro Mattivi ◽

Salvatore Eugenio Pappalardo ◽

Nebojša Nikolić ◽

Luca Mandolesi ◽

Antonio Persichetti ◽

...

Keyword(s):

Open Source ◽

Open Source Software ◽

Weed Management ◽

Low Cost ◽

Medium Size ◽

Spatially Explicit ◽

Weed Detection ◽

Management Scenario ◽

Weed Mapping ◽

Weed Distribution

Weed management is a crucial issue in agriculture, resulting in environmental in-field and off-field impacts. Within Agriculture 4.0, adoption of UASs combined with spatially explicit approaches may drastically reduce doses of herbicides, increasing sustainability in weed management. However, Agriculture 4.0 technologies are barely adopted in small-medium size farms. Recently, small and low-cost UASs, together with open-source software packages, may represent a low-cost spatially explicit system to map weed distribution in crop fields. The general aim is to map weed distribution by a low-cost UASs and a replicable workflow, completely based on open GIS software and algorithms: OpenDroneMap, QGIS, SAGA and OpenCV classification algorithms. Specific objectives are: (i) testing a low-cost UAS for weed mapping; (ii) assessing open-source packages for semi-automatic weed classification; (iii) performing a sustainable management scenario by prescription maps. Results showed high performances along the whole process: in orthomosaic generation at very high spatial resolution (0.01 m/pixel), in testing weed detection (Matthews Correlation Coefficient: 0.67–0.74), and in the production of prescription maps, reducing herbicide treatment to only 3.47% of the entire field. This study reveals the feasibility of low-cost UASs combined with open-source software, enabling a spatially explicit approach for weed management in small-medium size farmlands.

Download Full-text

Palweed:Wheat: A Bioeconomic Decision Model for Postemergence Weed Management in Winter Wheat (Triticum aestivum)

Weed Science ◽

10.1017/s0043174500081704 ◽

1995 ◽

Vol 43 (4) ◽

pp. 595-603 ◽

Cited By ~ 14

Author(s):

Tae-Jin Kwon ◽

Douglas L. Young ◽

Frank L. Young ◽

Chris M. Boerboom

Keyword(s):

Winter Wheat ◽

Weed Management ◽

Decision Model ◽

Damage Function ◽

Yield Response ◽

Density Functions ◽

Yield Model ◽

Weed Density ◽

Annual Grasses ◽

Winter Annual

Based on six years of data from a field experiment near Pullman, WA, a bioeconomic decision model was developed to annually estimate the optimal post-emergence herbicide types and rates to control multiple weed species in winter wheat under various tillage systems and crop rotations. The model name, PALWEED:WHEAT, signifies a Washington-Idaho Palouse region weed management model for winter wheat The model consists of linear preharvest weed density functions, a nonlinear yield response function, and a profit function. Preharvest weed density functions were estimated for four weed groups: summer annual grasses, winter annual grasses, summer annual broadleaves, and winter annual broadleaves. A single aggregated weed competition index was developed from the four density functions for use functions for use in the yield model. A yield model containing a logistic damage function performed better than a model containing a rectangular hyperbolic damage function. Herbicides were grouped into three categories: preplant nonselective, postemergence broadleaf, and postemergence grass. PALWEED:WHEAT was applied to average conditions of the 6-yr experiment to predict herbicide treatments that maximized profit. In comparison to average treatment rates in the 6-yr experiment, the bioeconomic decision model recommended less postemergence herbicide. The weed management recommendations of PALWEED:WHEAT behaved as expected by agronomic and economic theory in response to changes in assumed weed populations, herbicide costs, crop prices, and possible restrictions on herbicide application rates.

Download Full-text

Comparative Study of the Effect of Different Weed Management Strategies on Disease Severity and Marketable Yield of Paprika (Capsicum Annuum L.) in the Smallholder Farming Sector of Zimbabwe

Journal of Plant Protection Research ◽

10.2478/v10045-008-0011-z ◽

2008 ◽

Vol 48 (1) ◽

pp. 107-117 ◽

Cited By ~ 1

Author(s):

Maxwell Handiseni ◽

Julia Sibiya ◽

Vincent Ogunlela ◽

Irene Koomen

Keyword(s):

Comparative Study ◽

Capsicum Annuum ◽

Weed Management ◽

Leaf Spot ◽

Management Strategies ◽

Smallholder Farming ◽

Marketable Yield ◽

Weed Density ◽

Marketable Fruit ◽

Hand Weeding

Comparative Study of the Effect of Different Weed Management Strategies on Disease Severity and Marketable Yield of Paprika (Capsicum AnnuumL.) in the Smallholder Farming Sector of ZimbabweOn-farm trials were conducted in the Chinyika Resettlement Area of Zimbabwe under dryland conditions to investigate the effects of different weed management methods on disease incidence, severity and paprika (Capsicum annuum) pod yield. The weed control treatments included hand weeding at 2 and 6 weeks after transplanting (WAT); ridge re-moulding at 3,6 and 9 WAT; application 4l/ha Lasso (alachlor) immediately after transplanting, and Ronstar (oxidiazinon) at 2l/ha tank mixed with Lasso at 2l/ha one day before transplanting. The herbicide-water solution was applied at the rate of 200l/ha using a knapsack sprayer. Major diseases identified were bacterial leaf spot (Xanthomonas campestrispv.vesicatoria), cercospora leaf spot (Cercospora unamunoi), grey leaf spot (Stemphylium solani) and powdery mildew (Leveillula taurica) in both seasons. For the 2000/2001 season hand weeding at 2 and 6 WAT and ridge re-moulding at 3, 6 and 9 WAT had the greatest reduction effect on the area under disease progress curve (AUDPC) and the highest marketable fruit yield. In the 2001/2002 season, both herbicide treatments had the same effect as hand weeding and ridge re-moulding on AUDPC and marketable fruit yield. The least weed density was obtained by ridge re-moulding at 3, 6, and 9 WAT in the 2000/2001 season. Weed density was statistically the same across all treatments except the check treatment in 2001/2002 season. Hand weeding operations were significantly (p < 0.05) effective and consequently gave the highest added profits mainly because of their effect on major weeds such asDatura stramonium.

Download Full-text

A rotation design to reduce weed density in organic farming

Renewable Agriculture and Food Systems ◽

10.1017/s1742170510000256 ◽

2010 ◽

Vol 25 (3) ◽

pp. 189-195 ◽

Cited By ~ 29

Author(s):

Randy L. Anderson

Keyword(s):

Population Dynamics ◽

Organic Farming ◽

Weed Management ◽

Crop Production ◽

Soil Health ◽

Population Based ◽

Weed Population ◽

Weed Density ◽

Organic Systems ◽

Herbicide Use

AbstractWeeds are a major obstacle to successful crop production in organic farming. Producers may be able to reduce inputs for weed management by designing rotations to disrupt population dynamics of weeds. Population-based management in conventional farming has reduced herbicide use by 50% because weed density declines in cropland across time. In this paper, we suggest a 9-year rotation comprised of perennial forages and annual crops that will disrupt weed population growth and reduce weed density in organic systems. Lower weed density will also improve effectiveness of weed control tactics used for an individual crop. The rotation includes 3-year intervals of no-till, which will improve both weed population management and soil health. Even though this rotation has not been field tested, it provides an example of designing rotations to disrupt population dynamics of weeds. Also, producers may gain additional benefits of higher crop yield and increased nitrogen supply with this rotation design.

Download Full-text

Calcite production by Coccolithophores in the South East Pacific Ocean: from desert to jungle

Biogeosciences Discussions ◽

10.5194/bgd-4-3267-2007 ◽

2007 ◽

Vol 4 (5) ◽

pp. 3267-3299 ◽

Cited By ~ 16

Author(s):

L. Beaufort ◽

M. Couapel ◽

N. Buchet ◽

H. Claustre

Keyword(s):

Size Range ◽

Digital Camera ◽

Euphotic Zone ◽

The South ◽

Carbonate Ions ◽

East Pacific ◽

Standing Stocks ◽

South Pacific Gyre ◽

East Pacific Ocean ◽

First Time

Abstract. BIOSOPE cruise achieved an oceanographic transect from the Marquise Islands to the Peru-Chili upwelling (PCU) via the centre of the South Pacific Gyre (SPG). Water samples from 6 depths in the euphotic zone were collected at 20 stations. The concentrations of suspended calcite particles, coccolithophores cells and detached coccoliths were estimated together with size and weight using an automatic polarizing microscope, a digital camera, and a collection of softwares performing morphometry and pattern recognition. Some of these softwares are new and described here for the first time. The coccolithophores standing stocks are usually low and reach maxima west of the PCU. The coccoliths of Emiliania huxleyi, Gephyrocapsa spp. and Crenalithus spp. (Order Isochrysidales) represent 50% of all the suspended calcite particles detected in the size range 0.1–46 μm (21% of PIC in term of the calcite weight). The latter species are found to grow preferentially in the Chlorophyll maximum zone. In the SPG their maximum concentrations was found to occur between 150 and 200 m, which is very deep for these taxa. The weight and size of coccoliths and coccospheres are correlated. Large and heavy coccoliths and coccospheres are found in the regions with relative higher fertility in the Marquises Island and in the PCU. Small and light coccoliths and coccospheres are found west of the PCU. This distribution may correspond to that of the concentration of calcium and carbonate ions.

Download Full-text

Influence of Weed Density and Distribution on Corn (Zea mays) Yield

Weed Science ◽

10.1017/s0043174500081091 ◽

1995 ◽

Vol 43 (2) ◽

pp. 215-218 ◽

Cited By ~ 19

Author(s):

Mark J. Vangessel ◽

Edward E. Schweizer ◽

Karen A. Garrett ◽

Philip Westra

Keyword(s):

Zea Mays ◽

Grain Yield ◽

Management Model ◽

Yield Reduction ◽

Corn Yield ◽

Weed Population ◽

Weed Density ◽

Weed Distribution ◽

The Impact

The impact of weed density and weed distribution on irrigated corn yield was investigated in Colorado. Weed densities examined were 0,33,50, or 100% of the indigenous weed population. A series of weed distribution treatments were achieved by varying the length of the weed-free and weedy zones within the corn row while maintaining a constant weed population of 33 or 50% of the indigenous weed level. Grain yield was affected by weed density, but not by weed distribution. Each additional weed reduced corn yield 8.5 and 2.3 kg ha−1in 1991 and 1992, respectively. When corn yields were estimated with a computer weed/corn management model, weed densities 5 to 8 wk after planting provided a better yield reduction estimate than weed densities immediately before harvest.

Download Full-text

Intra-row Weed Detection Method in Field Based on Texture and Color Feature

INTERNATIONAL JOURNAL ON Advances in Information Sciences and Service Sciences ◽

10.4156/aiss.vol5.issue8.96 ◽

2013 ◽

Vol 5 (8) ◽

pp. 806-812 ◽

Cited By ~ 1

Author(s):

Qin Ma ◽

Dehai Zhu ◽

Junming Liu ◽

Wei Xiong ◽

Hong Chen

Keyword(s):

Detection Method ◽

Weed Detection ◽

Color Feature

Download Full-text

Validation of HERB for Use in Peanut (Arachis hypogaea)

Weed Technology ◽

10.1017/s0890037x00045449 ◽

1997 ◽

Vol 11 (3) ◽

pp. 573-579 ◽

Cited By ~ 7

Author(s):

Anthony D. White ◽

Harold D. Coble

Keyword(s):

Environmental Impact ◽

Arachis Hypogaea ◽

Weed Management ◽

Decision Model ◽

Yield Loss ◽

Field Validation ◽

The Public ◽

Weed Density ◽

Competitive Index ◽

Peanut Production

Researchers are currently developing predictive weed management models to aid producers in maintaining or improving economic profitability of peanut production while minimizing herbicide inputs and reducing environmental impact. HERB (Version 2.1.P), a computer decision model, has recently been developed for peanut and is now awaiting validation of weed control decisions before being released to the public. Field validation trials in 1994 and 1995 indicate that the current competitive index parameters in the HERB model are invalid, and statistically estimated competitive indices were generated. Estimating new parameters improvedR2values from 0.37 to 0.61. New competitive index parameters allow the HERB model to more accurately predict the level of yield loss at a given weed density.

Download Full-text

Comparison of Object Detection and Patch-Based Classification Deep Learning Models on Mid- to Late-Season Weed Detection in UAV Imagery

Remote Sensing ◽

10.3390/rs12132136 ◽

2020 ◽

Vol 12 (13) ◽

pp. 2136 ◽

Cited By ~ 1

Author(s):

Arun Narenthiran Veeranampalayam Sivakumar ◽

Jiating Li ◽

Stephen Scott ◽

Eric Psota ◽

Amit J. Jhala ◽

...

Keyword(s):

Object Detection ◽

Weed Management ◽

Network Models ◽

Detection Performance ◽

Single Shot ◽

Neural Network Models ◽

Weed Detection ◽

Late Season ◽

Detection Model ◽

Growing Seasons

Mid- to late-season weeds that escape from the routine early-season weed management threaten agricultural production by creating a large number of seeds for several future growing seasons. Rapid and accurate detection of weed patches in field is the first step of site-specific weed management. In this study, object detection-based convolutional neural network models were trained and evaluated over low-altitude unmanned aerial vehicle (UAV) imagery for mid- to late-season weed detection in soybean fields. The performance of two object detection models, Faster RCNN and the Single Shot Detector (SSD), were evaluated and compared in terms of weed detection performance using mean Intersection over Union (IoU) and inference speed. It was found that the Faster RCNN model with 200 box proposals had similar good weed detection performance to the SSD model in terms of precision, recall, f1 score, and IoU, as well as a similar inference time. The precision, recall, f1 score and IoU were 0.65, 0.68, 0.66 and 0.85 for Faster RCNN with 200 proposals, and 0.66, 0.68, 0.67 and 0.84 for SSD, respectively. However, the optimal confidence threshold of the SSD model was found to be much lower than that of the Faster RCNN model, which indicated that SSD might have lower generalization performance than Faster RCNN for mid- to late-season weed detection in soybean fields using UAV imagery. The performance of the object detection model was also compared with patch-based CNN model. The Faster RCNN model yielded a better weed detection performance than the patch-based CNN with and without overlap. The inference time of Faster RCNN was similar to patch-based CNN without overlap, but significantly less than patch-based CNN with overlap. Hence, Faster RCNN was found to be the best model in terms of weed detection performance and inference time among the different models compared in this study. This work is important in understanding the potential and identifying the algorithms for an on-farm, near real-time weed detection and management.

Download Full-text