Development of a spatial method for weed detection and localization

Vioix, Jean-Baptiste; Douzals, Jean‐Paul; Truchetet, Frédéric

doi:10.1117/12.516253

Cited by 4 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They cite problems in accurate classification of areas with no weeds due to the influence of highly variable soil conditions. Vioix et al (2001) used a remote control aircraft to obtain color photographs at spatial resolutions of less than one centimeter. After digitizing to RGB bitmaps, vegetation was separated from soil using color properties, and weeds were separated from crop rows with an algorithm that included a Gabor filter.…”

Section: Aerial and Satellite Weed Sensingmentioning

confidence: 99%

A Review on Remote Sensing of Weeds in Agriculture

Thorp

Tian

2004

Precision Agriculture

235

127

View full text Add to dashboard Cite

In the effort of developing precision agriculture tools, remote sensing has been commonly considered as an effective technique for weed patch delineation, where weed infestations are detected based on variations in the plant canopy spectral response. Because the canopy spectral response is important for weed detection, discussions on the irradiative interaction of light in plant canopies and the effect of variable soil background on the canopy spectral response are presented in this review. Also, a presentation of the current techniques for removal of soil effects, including vegetation indices and spectral mixture analysis, shows that these techniques have not been adequately developed for use in remote sensing-based weed detection applications. Given the nature of light interaction in a plant canopy, this review proposes that the spectral response of a plant canopy depends on both the species and the biomass density. Remote detection of weeds from ground-, aircraft-, and satellite-based platforms has been accomplished on a wide scale, yet the use of these weed detection methods to make variable-rate herbicide applications has not occurred as often. By judging success based on variable-rate herbicide applications rather than precise weed localization, some of the current problems in weed sensing may be skirted.

show abstract

Section: Aerial and Satellite Weed Sensingmentioning

confidence: 99%

A Review on Remote Sensing of Weeds in Agriculture

Thorp

Tian

2004

Precision Agriculture

235

127

View full text Add to dashboard Cite

show abstract

“…The global average pooling layer extracts a 544-dimensional feature vector and directly inputs it into the classification layer, which correlates the high-level features of ATLDs with the classification task directly. A large number of practices have proved that SVM is effective in dealing with small samples, non-linear and high-dimensional pattern recognition and diagnosis [41], and CNNs achieve a small but consistent advantage of replacing the Softmax layer with linear SVM at the top [42]. At the same time, the experiments show that the compared DCNNs have the consistent advantage after using linear SVM instead of Softmax, and the classification accuracy of XDNet with linear one-vs-all SVM on the testing dataset is 0.17% higher than that of Softmax.…”

Section: The Proposed Xdnetmentioning

confidence: 99%

Identification of Apple Tree Leaf Diseases Based on Deep Learning Models

et al. 2020

View full text Add to dashboard Cite

Early diagnosis and accurate identification of apple tree leaf diseases (ATLDs) can control the spread of infection, to reduce the use of chemical fertilizers and pesticides, improve the yield and quality of apple, and maintain the healthy development of apple cultivars. In order to improve the detection accuracy and efficiency, an early diagnosis method for ATLDs based on deep convolutional neural network (DCNN) is proposed. We first collect the images of apple tree leaves with and without diseases from both laboratories and cultivation fields, and establish dataset containing five common ATLDs and healthy leaves. The DCNN model proposed in this paper for ATLDs recognition combines DenseNet and Xception, using global average pooling instead of fully connected layers. We extract features by the proposed convolutional neural network then use a support vector machine to classify the apple leaf diseases. Including the proposed DCNN, several DCNNs are trained for ATLDs recognition. The proposed network achieves an overall accuracy of 98.82% in identifying the ATLDs, which is higher than Inception-v3, MobileNet, VGG-16, DenseNet-201, Xception, VGG-INCEP. Moreover, the proposed model has the fastest convergence rate, and a relatively small number of parameters and high robustness compared with the mentioned models. This research indicates that the proposed deep learning model provides a better solution for ATLDs control. It could be also integrated into smart apple cultivation systems.

show abstract

“…The spatial methods consider the geometrical characteristics of the seedling. They are often based on row detection and assume the weeds to be the vegetation between rows (Bossu et al 2009;Jones et al 2009;Peña et al 2013;Vioix et al 2003). The spectral methods use classification and segmentation tools to classify the image pixels according to their reflectance values (De Castro et al 2012;Garcia-Ruiz et al 2015;Pérez-Ortiz et al 2015).…”

Section: Introductionmentioning

confidence: 99%

Weed detection by UAV: simulation of the impact of spectral mixing in multispectral images

et al. 2017

View full text Add to dashboard Cite

This study aimed to assess the spectral information potential of images captured with an unmanned aerial vehicle, in the context of crop-weed discrimination. A model is proposed in which the entire image acquisition chain is simulated in order to compute the digital values of image pixels according to several parameters (light, plant characteristics, optical filters, sensors…) to reproduce in-field acquisition conditions. The spectral mixings in the pixels are modeled, based on an image with a 60 mm spatial resolution, to estimate the impact of the resolution on the ability to discriminate small plants. The classification potential (i.e. the ability to separate two classes) in soil and vegetation and in monocotyledon and dicotyledon classes is studied using simulations for different vegetation rates (defined as the proportion of vegetation covering the surface projected in the considered pixel). The classification is unsupervised and based on the Mahalanobis distance computation. The results of soil-vegetation discrimination show that pixels with low vegetation rates can be classified as vegetation: pixels with vegetation rate greater than 0.5 had a probability to be correctly classified between 80 and 100%. Classification between monocotyledonous and dicotyledonous plants requires pixels with a high vegetation rate: to obtain a probability to be correctly classified better than 80%, vegetation rates in the pixels have to be over 0.9. To compare the results with data from real images, the same classification was tested on multispectral images of a weed infested field. The comparison confirmed the ability of the model to assess vegetation-soil and crop-weed discrimination potential for specific sensors (such as the multiSPEC 4C sensor, AIRINOV, Paris, France), where the acquisition chain parameters can be tested.Electronic supplementary material The online version of this article

show abstract

Development of a spatial method for weed detection and localization

Cited by 4 publications

References 1 publication

A Review on Remote Sensing of Weeds in Agriculture

A Review on Remote Sensing of Weeds in Agriculture

Identification of Apple Tree Leaf Diseases Based on Deep Learning Models

Weed detection by UAV: simulation of the impact of spectral mixing in multispectral images

Contact Info

Product

Resources

About