Weed detection in soybean crops using ConvNets

Ferreira, Alessandro dos Santos; Freitas, Daniel Matte; Silva, Gercina Gonçalves da; Pistori, Hemerson; Folhes, Marcelo Theophilo

doi:10.1016/j.compag.2017.10.027

Cited by 367 publications

(143 citation statements)

References 22 publications

Supporting

Mentioning

140

Contrasting

Unclassified

Order By: Relevance

“…Very few woks have used CNNs to detect plants in UAV images. Noteworthy is the work by Ferreira et al [21], where weed was detected in soybean cultures using CNN based on the CaffeNet architecture. The authors used a set of data acquired with an UAV in manual mode at a height of 4 m above the Earth level using an RGB camera.…”

Section: Classification Of Trees In High Resolution Imagery and Relatmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Fir Trees (Abies sibirica) Damaged by the Bark Beetle in Unmanned Aerial Vehicle Images with Deep Learning

et al. 2019

View full text Add to dashboard Cite

Invasion of the Polygraphus proximus Blandford bark beetle causes catastrophic damage to forests with firs (Abies sibirica Ledeb) in Russia, especially in Central Siberia. Determining tree damage stage based on the shape, texture and colour of tree crown in unmanned aerial vehicle (UAV) images could help to assess forest health in a faster and cheaper way. However, this task is challenging since (i) fir trees at different damage stages coexist and overlap in the canopy, (ii) the distribution of fir trees in nature is irregular and hence distinguishing between different crowns is hard, even for the human eye. Motivated by the latest advances in computer vision and machine learning, this work proposes a two-stage solution: In a first stage, we built a detection strategy that finds the regions of the input UAV image that are more likely to contain a crown, in the second stage, we developed a new convolutional neural network (CNN) architecture that predicts the fir tree damage stage in each candidate region. Our experiments show that the proposed approach shows satisfactory results on UAV Red, Green, Blue (RGB) images of forest areas in the state nature reserve “Stolby” (Krasnoyarsk, Russia).

show abstract

Section: Classification Of Trees In High Resolution Imagery and Relatmentioning

confidence: 99%

“…DenseNet is the result of the development of the ResNet network and is based on its residual blocks [21]. The basic idea is that connections have all the possible combinations within each block, which represents a gradient of more paths and the network becomes more resistant to learning.…”

Section: Appendix B Brief Description Of the Cnns That Are Compared mentioning

confidence: 99%

Detection of Fir Trees (Abies sibirica) Damaged by the Bark Beetle in Unmanned Aerial Vehicle Images with Deep Learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…[36] assessed individual biomass extents of numerous dissimilar kinds of crops. Using RGB + Near-Infrared Reflectance (NIR)descriptions, two different CNN designs for classifying crop and weed are utilized [37].Recent developments show the importance of deep learning techniques for weed classification [12,38]. Cost-effective automatic weed classification can be done using UAV/airborne sensors.…”

mentioning

confidence: 99%

“…Recent developments show the importance of deep learning techniques for weed classification [12,38]. Cost-effective automatic weed classification can be done using UAV/airborne sensors.…”

mentioning

confidence: 99%

Multi-Resolution Weed Classification via Convolutional Neural Network and Superpixel Based Local Binary Pattern Using Remote Sensing Images

Farooq

Jia

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Automatic weed detection and classification faces the challenges of large intraclass variation and high spectral similarity to other vegetation. With the availability of new high-resolution remote sensing data from various platforms and sensors, it is possible to capture both spectral and spatial characteristics of weed species at multiple scales. Effective multi-resolution feature learning is then desirable to extract distinctive intensity, texture and shape features of each category of weed to enhance the weed separability. We propose a feature extraction method using a Convolutional Neural Network (CNN) and superpixel based Local Binary Pattern (LBP). Both middle and high level spatial features are learned using the CNN. Local texture features from superpixel-based LBP are extracted, and are also used as input to Support Vector Machines (SVM) for weed classification. Experimental results on the hyperspectral and remote sensing datasets verify the effectiveness of the proposed method, and show that it outperforms several feature extraction approaches.

show abstract

“…These morphological features including length, width, perimeter dimensions, roundness, circularity, convexity, and moment of plant leaves or plant canopy were widely used for feature-based plant identification (Dyrmann, Christiansen, & Midtiby, 2018;Tang & Tian, 2008;Wu et al, 2007). Other than these features, general image features extractors such as scale-invariant feature transform, features from accelerated segment test, histogram of gradient, local binary pattern, and Gabor wavelet transformation, which are descriptors of local textures and key points, were also found effective in plant detection and discrimination, and robust to illumination variations (Bawden et al, 2017;dos Santos Ferreira, Matte Freitas, Gonçalves da Silva, Pistori, & Theophilo Folhes, 2017;Tang, Tian, & Steward, 2003).…”

mentioning

confidence: 99%

Automated crop plant detection based on the fusion of color and depth images for robotic weed control

Gai

Tang

Steward

2019

Journal of Field Robotics

View full text Add to dashboard Cite

Robotic weeding enables weed control near or within crop rows automatically, precisely and effectively. A computer‐vision system was developed for detecting crop plants at different growth stages for robotic weed control. Fusion of color images and depth images was investigated as a means of enhancing the detection accuracy of crop plants under conditions of high weed population. In‐field images of broccoli and lettuce were acquired 3–27 days after transplanting with a Kinect v2 sensor. The image processing pipeline included data preprocessing, vegetation pixel segmentation, plant extraction, feature extraction, feature‐based localization refinement, and crop plant classification. For the detection of broccoli and lettuce, the color‐depth fusion algorithm produced high true‐positive detection rates (91.7% and 90.8%, respectively) and low average false discovery rates (1.1% and 4.0%, respectively). Mean absolute localization errors of the crop plant stems were 26.8 and 7.4 mm for broccoli and lettuce, respectively. The fusion of color and depth was proved beneficial to the segmentation of crop plants from background, which improved the average segmentation success rates from 87.2% (depth‐based) and 76.4% (color‐based) to 96.6% for broccoli, and from 74.2% (depth‐based) and 81.2% (color‐based) to 92.4% for lettuce, respectively. The fusion‐based algorithm had reduced performance in detecting crop plants at early growth stages.

show abstract

Weed detection in soybean crops using ConvNets

Cited by 367 publications

References 22 publications

Detection of Fir Trees (Abies sibirica) Damaged by the Bark Beetle in Unmanned Aerial Vehicle Images with Deep Learning

Detection of Fir Trees (Abies sibirica) Damaged by the Bark Beetle in Unmanned Aerial Vehicle Images with Deep Learning

Multi-Resolution Weed Classification via Convolutional Neural Network and Superpixel Based Local Binary Pattern Using Remote Sensing Images

Automated crop plant detection based on the fusion of color and depth images for robotic weed control

Contact Info

Product

Resources

About