Weed species differentiation using spectral reflectance land image classification

Abstract. Land cover mapping using remote-sensing imagery has attracted significant attention in recent years. Classification of land use and land cover is an advantage of remote sensing technology which provides all information about land surface. Numerous studies have investigated land cover classification using different broad array of sensors, resolution, feature selection, classifiers, Classification Techniques and other features of interest from over the past decade. One, Pixel based image classification technique is widely used in the world which works on their per pixel spectral reflectance. Classification algorithms such as parallelepiped, minimum distance, maximum likelihood, Mahalanobis distance are some of the classification algorithms used in this technique. Other, Object based image classification is one of the most adapted land cover classification technique in recent time which also considers other parameters such as shape, colour, smoothness, compactness etc. apart from the spectral reflectance of single pixel.At present, there is a possibility of getting the more accurate information about the land cover classification by using latest technology, recent and relevant algorithms according to our study. In this study a combination of pixel-by-pixel image classification and object based image classification is done using different platforms like ArcGIS and e-cognition, respectively. The aim of the study is to analyze LULC pattern using satellite imagery and GIS for the Ahmedabad district in the state of Gujarat, India using a LISS-IV imagery acquired from January to April, 2017. The over-all accuracy of the classified map is 84.48% with Producer’s and User’s accuracy as 89.26% and 84.47% respectively. Kappa statistics for the classified map are calculated as 0.84. This classified map at 1:10,000 scale generated using recent available high resolution space borne data is a valuable input for various research studies over the study area and also provide useful information to town planners and civic authorities. The developed technique can be replicated for generating such LULC maps for other study areas as well.

Download Full-text

Utility of Multispectral Imagery for Soybean and Weed Species Differentiation

Weed Technology ◽

10.1614/wt-07-116.1 ◽

2008 ◽

Vol 22 (4) ◽

pp. 713-718 ◽

Cited By ~ 19

Author(s):

Cody J. Gray ◽

David R. Shaw ◽

Patrick D. Gerard ◽

Lori M. Bruce

Keyword(s):

Soil Classification ◽

Bare Soil ◽

Planting Density ◽

Species Differentiation ◽

Multispectral Imagery ◽

Weed Species ◽

Weed Detection ◽

Class System ◽

Pitted Morningglory ◽

Prickly Sida

An experiment was conducted to determine the utility of multispectral imagery for identifying soybean, bare soil, and six weed species commonly found in Mississippi. Weed species evaluated were hemp sesbania, palmleaf morningglory, pitted morningglory, prickly sida, sicklepod, and smallflower morningglory. Multispectral imagery was analyzed using supervised classification techniques based upon 2-class, 3-class, and 8-class systems. The 2-class system was designed to differentiate bare soil and vegetation. The 3-class system was used to differentiate bare soil, soybean, and weed species. Finally, the 8-class system was designed to differentiate bare soil, soybean, and all weed species independently. Soybean classification accuracies classified as vegetation for the 2-class system were greater than 95%, and bare soil classification accuracies were greater than 90%. In the 3-class system, soybean classification accuracies were 70% or greater. Classification of soybean decreased slightly in the 3-class system when compared to the 2-class system because of the 3-class system separating soybean plots from the weed plots, which was not done in the 2-class system. Weed classification accuracies increased as weed density or weeks after emergence (WAE) increased. The greatest weed classification accuracies were obtained once weed species were allowed to grow for 10 wk. Palmleaf morningglory and pitted morningglory classification accuracies were greater than 90% for 10 WAE using the 3-class system. Palmleaf morningglory and pitted morningglory at the highest densities of 6 plants/m2produced the highest classification accuracies for the 8-class system once allowed to grow for 10 wk. All other weed species generally produced classification accuracies less than 50%, regardless of planting density. Thus, multispectral imagery has the potential for weed detection, especially when being used in a management system when individual weed species differentiation is not essential, as in the 2-class or 3-class system. However, weed detection was not obtained until 8 to 10 WAE, which is unacceptable in production agriculture. Therefore, more refined imagery acquisition with higher spatial and/or spectral resolution and more sophisticated analyses need to be further explored for this technology to be used early-season when it would be most valuable.

Download Full-text

Utility of Hyperspectral Reflectance for Differentiating Soybean (Glycine max) and Six Weed Species

Weed Technology ◽

10.1614/wt-07-117.1 ◽

2009 ◽

Vol 23 (1) ◽

pp. 108-119 ◽

Cited By ~ 19

Author(s):

Cody J. Gray ◽

David R. Shaw ◽

Lori M. Bruce

Keyword(s):

Short Wavelength ◽

Spectral Band ◽

Vegetation Indices ◽

Species Discrimination ◽

Species Differentiation ◽

Electromagnetic Spectrum ◽

Hyperspectral Reflectance ◽

Weed Species ◽

Linear Discriminant ◽

Reflectance Data

Reflectance data were subjected to a variety of analysis methods to determine the utility of hyperspectral reflectance for differentiating soybean, soil, and six weed species commonly found in Mississippi agricultural fields. Weed species evaluated were hemp sesbania, palmleaf morningglory, pitted morningglory, prickly sida, sicklepod, and smallflower morningglory. Hyperspectral reflectance data were collected from mature plant leaves three times in 2002 and two times in 2003. Vegetation indices were calculated and subjected to principal component analysis (PCA) and linear discriminant analysis (LDA). The PCA, using vegetation indices, produced the poorest classification accuracies for the plant species studied, generally less than 50%, whereas LDA resulted in classification accuracies greater than those from PCA. Best spectral band combination (BSBC) provided the greatest classification accuracies, with all better than 80% for all data sets. The BSBC indicated three wavelength bands of interest for species discrimination in the short wavelength infrared portion of the electromagnetic spectrum, which are not commonly used in current vegetation indices for species differentiation. These areas of interest were located from 1,445 to 1,475 nm, 2,030 to 2,090 nm, and 2,115 to 2,135 nm. The top 10 wavelengths determined by BSBC were then added to the vegetation indices and reanalyzed using PCA and LDA. Classification accuracies increased for all species when these wavelengths were added rather than using vegetation indices alone, suggesting greater crop and weed species differentiation can be obtained when using sensors that include these wavelength regions of the short wavelength infrared portion of the electromagnetic spectrum.

Download Full-text

Analysis of Weed Growth in Rabi Crop Agriculture Using Deep Convolutional Neural Networks

Journal of Physics Conference Series ◽

10.1088/1742-6596/2070/1/012101 ◽

2021 ◽

Vol 2070 (1) ◽

pp. 012101

Author(s):

Anand Muni Mishra ◽

Prabhjot kaur ◽

Yogesh Shahare ◽

Vinay Gautam

Keyword(s):

Image Classification ◽

Crop Production ◽

Fall Detection ◽

Madhya Pradesh ◽

Crop Damage ◽

North India ◽

Weed Species ◽

Deep Convolutional Neural Networks ◽

Crop Agriculture ◽

Rabi Crops

Abstract Weed interference for the duration of crop establishment is a severe difficulty for wheat in North India [22.9734 ° N, 78.6569 ° E]. In situ far-flung detection for precision herbicide application minimizes the danger of both crop damage and herbicide input. This research paper focuses on the comparative study of crop growth and its effect at three different places in Madhya Pradesh [24.5840° N, 81.5020° E] India[20.5937° N, 78.9629° E]. These weed species included Pigweed (Amaranthaceae ), Goosefoot [Chenopodiaceae], Wild oat species (Poaceae), livid amaranth (Amaranthus blitum L.), Fathen[Chenopodiaceae (L.) Wild.], and Bermuda grass (Poaceae L.) a significant weed for rabi crop production in India with sensitivity to clopyralid, is the best available put up broadleaf herbicide. The intention of the Takes a look to assess the accuracy of four different CNNs architectures to locate the weed images of the Rabi crop of the family of various Rabi crops growing in competition with Rabi crops at 3 sites in Madhya Pradesh. Four CNNs have been compared, including object detection-primarily based ResNet-50, image classification-based VGGNet-16, Inception v4 and EfficientNet-B7 the EfficientNet-B7 networks have been trained to hit upon both leaves or canopies Everlasting of weeds. Image classification the use of ResNet-50 and VGGNet-16 was largely unsuccessful all through validation with whole pics (Fl-score < 0.04). CNN training elevated the usage of cropped photographs Eternal Broad Fall detection at some stage invalidation for VGGNet (F1-score = 0.77) and ResNet-50 (F1-Score = 0.62). The rabi crop weed leaf-trained inception V4 and EfficientNet-B7 achieved the highest F1-Score (0.94) and F1 Score (0.96) respectively, The aim of leaf-based EfficientNet-B7 extended false positives, even though such errors could be won over with extra training images for network desensitization training. Photograph-based faraway sensing rabi crop will become the most viable CNN test for weeds in competition with the EfficientNet-B7 crop.

Download Full-text

Phenology affects differentiation of crop and weed species using hyperspectral remote sensing

Weed Technology ◽

10.1017/wet.2020.92 ◽

2020 ◽

Vol 34 (6) ◽

pp. 897-908

Author(s):

Nicholas T. Basinger ◽

Katherine M. Jennings ◽

Erin L. Hestir ◽

David W. Monks ◽

David L. Jordan ◽

...

Keyword(s):

Near Infrared ◽

Canopy Structure ◽

Growing Season ◽

Plant Phenology ◽

Species Differentiation ◽

In Situ Spectroscopy ◽

Weed Species ◽

Leaf Level ◽

Shortwave Infrared

AbstractThe effect of plant phenology and canopy structure of four crops and four weed species on reflectance spectra were evaluated in 2016 and 2017 using in situ spectroscopy. Leaf-level and canopy-level reflectance were collected at multiple phenologic time points in each growing season. Reflectance values at 2 wk after planting (WAP) in both years indicated strong spectral differences between species across the visible (VIS; 350–700 nm), near-infrared (NIR; 701–1,300 nm), shortwave-infrared I (SWIR1; 1,301–1,900 nm), and shortwave-infrared II (SWIR2; 1,901–2,500 nm) regions. Results from this study indicate that plant spectral reflectance changes with plant phenology and is influenced by plant biophysical characteristics. Canopy-level differences were detected in both years across all dates except for 1 WAP in 2017. Species with similar canopy types (e.g., broadleaf prostrate, broadleaf erect, or grass/sedge) were more readily discriminated from species with different canopy types. Asynchronous phenology between species also resulted in spectral differences between species. SWIR1 and SWIR2 wavelengths are often not included in multispectral sensors but should be considered for species differentiation. Results from this research indicate that wavelengths in SWIR1 and SWIR2 in conjunction with VIS and NIR reflectance can provide differentiation across plant phenologies and, therefore should be considered for use in future sensor technologies for species differentiation.

Download Full-text

SAFARI 2000 SURFACE SPECTRAL REFLECTANCE AT SUA PAN, BOTSWANA, DRY SEASON 2000

ORNL Distributed Active Archive Center Datasets ◽

10.3334/ornldaac/780 ◽

2005 ◽

Author(s):

W. BUERMANN ◽

F. ECKARDT ◽

M. HELMLINGER

Keyword(s):

Spectral Reflectance ◽

Dry Season

Download Full-text

Influence of NPK fertilization on weed flora in maize field

Agrokémia és Talajtan ◽

10.1556/agrokem.63.2014.1.15 ◽

2014 ◽

Vol 63 (1) ◽

pp. 139-148 ◽

Cited By ~ 1

Author(s):

Éva Lehoczky ◽

M. Kamuti ◽

N. Mazsu ◽

J. Tamás ◽

D. Sáringer-Kenyeres ◽

...

Keyword(s):

Plant Nutrition ◽

Crop Production ◽

N Availability ◽

Weed Species ◽

Negative Effects ◽

Production Factors ◽

Maize Field ◽

Weed Flora ◽

Npk Fertilization

Plant nutrition is one of the most important intensification factors of crop production. The utilization of nutrients, however, may be modified by a number of production factors, including weed presence. Thus, the knowledge of occurring weed species, their abundance, nutrient and water uptake is extremely important to establish an appropriate basis for the evaluation of their risks or negative effects on crops. That is why investigations were carried out in a long-term fertilization experiment on the influence of different nutrient supplies (Ø, PK, NK, NPK) on weed flora in maize field.The weed surveys recorded similar diversity on the experimental area: the species of A. artemisiifolia, S. halepense and D. stramonium were dominant, but C. album and C. hybridum were also common. These species and H. annuus were the most abundant weeds.Based on the totalized and average data of all treatments, density followed the same tendency in the experimental years. It was the highest in the PK treated and untreated plots, and significantly exceeded the values of NK fertilized areas. Presumably the better N availability promoted the development of nitrophilic weeds, while the mortality of other small species increased.Winter wheat and maize forecrops had no visible influence on the diversity and the intensity of weediness. On the contrary, there were consistent differences in the density of certain weed species in accordance to the applied nutrients. A. artemisiifolia was present in the largest number in the untreated control and PK fertilized plots. The density of S. halepense and H. annuus was also significantly higher in the control areas. The number of their individuals was smaller in those plots where N containing fertilizers were used. Contrary to them, the density of D. stramonium, C. album and C. hybridum was the highest in the NPK treatments.

Download Full-text