Weed Detection in Farm Crops using Parallel Image Processing

Umamaheswari, S.; Arjun, R; Meganathan, D.

doi:10.1109/infocomtech.2018.8722369

Cited by 25 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our model achieved a classification accuracy of 87.9% as an ensemble of shallow NN networks. Although our model could not compete with the highest score when compared to deep learning techniques such as Adapted-IV3 [24], but as an ensemble of shallow networks compared to a CNN model PWDS [36] and an ensemble method random forest tree [14], our model managed to achieve the highest recall and F1-score. Our paper has demonstrated that rotation-invariant uniform LBP is viable in pixel-level weed classification.…”

Section: Resultsmentioning

confidence: 94%

See 1 more Smart Citation

Pixel-Level Weed Classification Using Evolutionary Selection of Local Binary Pattern in a Stochastic Optimised Ensemble

et al. 2020

View full text Add to dashboard Cite

In the early growth stages of young crops, weeds compete for living resources while often grow close together and with overlaps. Conventional weeding techniques such as mechanical weeding and herbicide application are not precision methods. To allow for high precision target and spraying of weeds, autonomous field robots equipped with computer vision systems could be deployed to manage and control the weeds in the crop line. The robots are therefore required to classify weeds at pixel-level accuracy with high recall rates. This paper presents a pixel-level weed classification model using rotation-invariant uniform local binary pattern (LBP) features. The model design is based on an ensemble with a two-level optimisation structure. The first-level leverages on Genetic Algorithm (GA) optimisation to select the best rotation-invariant uniform LBP configurations. The second level utilises covariance matrix adaptation evolution strategy (CMA-ES) in the Neural Network (NN) ensemble to select the best combinations of voting weights of the predicted outcome for each classifier. This model design allows for different feature inputs selected by GA for each of the NN classifiers in the ensemble, unlike classical ensembles which share the same input data. For ensemble weight optimisation, we compared differential evolution, particle swarm optimisation, and CMA-ES. A crop/weed field image dataset public dataset consisting of 60 images of weeds and carrots at early true leaf stage was used for validation with existing works. The results demonstrated that our LBP-based pixel-level classifier exhibits excellent predictive capability with high recall and F1 scores when compared to the literature. It was found that CMA-ES optimised ensemble gave the best configuration and demonstrated a classification accuracy of 87.9%, which exceeded the existing statistical feature classification of 85.9%. This highlights some potentialities for chip-based application-specific integrated circuit LBP pixel-level weed classification in smart agriculture applications.

show abstract

Section: Resultsmentioning

confidence: 94%

“…PWDS [36] model is based on a convolutional neural network without pre-training. The NN without ensemble achieved 82.8% which is subpar when compared to the baseline deep learner PWDS of 85.8%.…”

Section: Resultsmentioning

confidence: 99%

Pixel-Level Weed Classification Using Evolutionary Selection of Local Binary Pattern in a Stochastic Optimised Ensemble

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Base station communication is through wireless mode and the Raspberry pi is used for the implementation. The goal of work in [3] is to have the high productivity with less wastage using precision agriculture. The work flow includes the training with the images of the plants using deep learning algorithm.…”

Section: Related Workmentioning

confidence: 99%

Raspberry Pi based crop and weed classification using Machine Learning Algorithm

Joshitha¹,

Nishanthini²,

Harshini³

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Farming with fun has uplifted the agritourism in our country. The technological development and support have made farming a passion nowadays. Farming is not only important to cater the needs of the growing population but also to develop agritourism. The major challenge in crop production like irrigation, de-weeding, etc can be handled with good improvement in quality crops through the implementation of automated systems in monitoring and controlling application. With more Techies joining into the farming wishing to lead a stress-free life, automation. The work presented aims at identifying the weeds from the desired crop using the learning algorithm. The weed location identified can be used as the inputs to the de-weeding Robots. Besides, the work can equally be applicable in intercropping process, irrigation management, quality assurance in crops, etc. The input images of the crop to be classified are taken using the camera interfaced with Raspberry pi. Classification is done using the supervised learning algorithm with a set of target classes. The model is trained to recognize the target class. The accuracy of the classification varies from 75% to 100% as the proportion of the training and test data set varies from 60-40% to 80-20%.

show abstract

“…A few datasets feature images of weed seedlings, enabling the development of models that can detect weed infestation at an early stage. Studies using similar datasets employed computer vision and machine learning algorithms for weed detection, though these presented a high variability in the precision rate (69%–98%) depending on the crop field analyzed ( Wang et al, 2007 ; dos Santos Ferreira et al, 2017 ; Pallottino et al, 2018 ; Umamaheswari et al, 2018 ; Bah et al, 2019 ; Partel et al, 2019 ). These results emphasize the need to produce more datasets with an increased variety of crop and weed species at different growth stages.…”

Section: Applications Of Htpmentioning

confidence: 99%

Resources for image-based high-throughput phenotyping in crops and data sharing challenges

et al. 2021

View full text Add to dashboard Cite

High throughput phenotyping (HTP) platforms are capable of monitoring the phenotypic variation of plants through multiple types of sensors such as RGB cameras, hyperspectral sensors and computed tomography, which can be associated with environmental and genotypic data. Because of the wide range of information provided, HTP datasets represent a valuable asset to characterise crop phenotypes. As HTP becomes widely employed with more tools and data being released, it is important that researchers are aware of these resources and how they can be applied to accelerate crop improvement. Researchers may exploit these datasets either for phenotype comparison or employ them as a benchmark to assess tool performance and to support the development of tools that are better at generalising between different crops and environments. In this review, we describe the use of image-based HTP for yield prediction, root phenotyping, development of climate-resilient crops, detecting pathogen and pest infestation and quantitative trait measurement. We emphasise the need for researchers to share phenotypic data, and offer a comprehensive list of available datasets to assist crop breeders and tool developers to leverage these resources in order to accelerate crop breeding.

show abstract

Weed Detection in Farm Crops using Parallel Image Processing

Cited by 25 publications

References 13 publications

Pixel-Level Weed Classification Using Evolutionary Selection of Local Binary Pattern in a Stochastic Optimised Ensemble

Pixel-Level Weed Classification Using Evolutionary Selection of Local Binary Pattern in a Stochastic Optimised Ensemble

Raspberry Pi based crop and weed classification using Machine Learning Algorithm

Resources for image-based high-throughput phenotyping in crops and data sharing challenges

Contact Info

Product

Resources

About