Research Article
An Efficient Weed Growth Rate Estimator
@INPROCEEDINGS{10.4108/eai.16-4-2022.2318148, author={Yash Vishwakarma and Akhilesh A. Waoo}, title={An Efficient Weed Growth Rate Estimator}, proceedings={Proceedings of The International Conference on Emerging Trends in Artificial Intelligence and Smart Systems, THEETAS 2022, 16-17 April 2022, Jabalpur, India}, publisher={EAI}, proceedings_a={THEETAS}, year={2022}, month={6}, keywords={computer vision image classification leaf counting convolutional neural network efficientnet}, doi={10.4108/eai.16-4-2022.2318148} }- Yash Vishwakarma
Akhilesh A. Waoo
Year: 2022
An Efficient Weed Growth Rate Estimator
THEETAS
EAI
DOI: 10.4108/eai.16-4-2022.2318148
Abstract
This study drafts a new EfficientNetB0 CNN-based process of automatically classifying weed plants into different developmental phases. Images of weed plants growing within various crops across varying environmental constraints were used. About 90% of the images were used for training the proposed model. The performance of this EfficientNetB0 based convolutional neural network model was measured on a different additional set of 10% images never seen by the model. The model attained a very high 91% accuracy in identifying young singleleaf weed plants. Additionally, it attained an average accuracy of 73% in evaluating the count of leaves across all classes and an accuracy of 81% among all classes except one. The accuracy of the results conveys that this new method of using the EfficientNetB0 based model has a high potential to classify different developmental phases among distinct weed plants.
