Deep convolutional neural network models for weed detection in polyhouse grown bell peppers

Subeesh, A.; Bhole, Swapnil; Singh, Karan; Chandel, Narendra Singh; Rajwade, Yogesh Anand; Rao, K. V.; Kumar, Satya; Jat, Dilip

doi:10.1016/j.aiia.2022.01.002

Cited by 55 publications

(22 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional detection methods apply color characteristics, surface texture characteristics, chemical composition, and odor to fruits and crops [5]. Surya et al [6]evaluated the growth stages of bananas based on their color characteristics to determine the correct harvest time for banana growers.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Monitoring Method of Strawberry Fruit Growth State Based on YOLO Improved Model

Wang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

A key challenge for automated orchard management robots is the rapid and accurate identification of crop growth and maturity conditions for subsequent operations, such as automatic pollination, fertilization, and picking. In particular, strawberries have a short ripening period and the fruits are heavily overlapped and shaded by each other, which is time-consuming and inefficient under traditional detection methods. Therefore, we designed and developed a strawberry growth detection algorithm, SDNet (Strawberry Detect Net). The algorithm is based on the YOLOX model and replaces the original CSP block in the backbone network with a self-designed feature extraction module C3HB block to improve the spatial interaction capability and monitoring accuracy of the detection algorithm; Then, the normalized attention module (NAM) is embedded in the neck to improve the detection accuracy and attention weight of small target fruits; and we use the latest SIOU objective loss function to improve the prediction accuracy of the detection model, which finally achieves the monitoring of strawberry fruits under five growth states. The experimental results show that the mAP, precision, and recall of SDNet are 94.26%, 93.15%, and 90.72%, respectively, and the monitoring speed is 30.5 ms. It is 4.08%, 3.64 and 2.04% higher than the precision, accuracy, and recall of YOLOX, respectively, and there is no significant change in the model size. The research results can effectively solve the problem of low accuracy of strawberry fruit growth state monitoring under complex environments, and provide important technical reference for realizing unmanned farm and precision agriculture.INDEX TERMS Fruit detection,Object detection,Real-time counting,Digital agriculture.

show abstract

Section: Introductionmentioning

confidence: 99%

Real-Time Monitoring Method of Strawberry Fruit Growth State Based on YOLO Improved Model

Wang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The CNN-based approach for feature extraction and classification under the same architecture achieves good results because it has a convolutional input layer, which acts as a self-learning feature extractor that can learn the optimal features directly from the original pixels of the input image, and the integrated features learned are not limited to shape, texture, or color, but also extend to specific kinds of leaf features, such as structural split, leaf tip, leaf base, leaf margin types, etc. [42][43][44]. The shortcomings are the lack of actual training samples and the large amount of time required to train the network.…”

Section: Discussionmentioning

confidence: 99%

Research on Plant Species Identification Based on Improved Convolutional Neural Network

Yuan¹,

Liu²,

Song³

et al. 2023

Phyton

View full text Add to dashboard Cite

Plant species recognition is an important research area in image recognition in recent years. However, the existing plant species recognition methods have low recognition accuracy and do not meet professional requirements in terms of recognition accuracy. Therefore, ShuffleNetV2 was improved by combining the current hot concern mechanism, convolution kernel size adjustment, convolution tailoring, and CSP technology to improve the accuracy and reduce the amount of computation in this study. Six convolutional neural network models with sufficient trainable parameters were designed for differentiation learning. The SGD algorithm is used to optimize the training process to avoid overfitting or falling into the local optimum. In this paper, a conventional plant image dataset TJAU10 collected by cell phones in a natural context was constructed, containing 3000 images of 10 plant species on the campus of Tianjin Agricultural University. Finally, the improved model is compared with the baseline version of the model, which achieves better results in terms of improving accuracy and reducing the computational effort. The recognition accuracy tested on the TJAU10 dataset reaches up to 98.3%, and the recognition precision reaches up to 93.6%, which is 5.1% better than the original model and reduces the computational effort by about 31% compared with the original model. In addition, the experimental results were evaluated using metrics such as the confusion matrix, which can meet the requirements of professionals for the accurate identification of plant species.

show abstract

“…Islam et al (2021) describe the application of various machine learning-based classifiers such as Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), to detect weeds using UAV images from a chili crop field. Subeesh et al (2022) demonstrated the use of deep learning-based techniques (Alex Net, Google net, InceptionV3, Exception) for the weed identification from RGB images of bell pepper fields with the varied accuracy of 94.5 to 97.7% of different models where InceptionV3 model exhibited the higher performance with a 97.7% accuracy. This study facilitates further integration of both the herbicide applications and weed management system with more preciseness and accuracy.…”

Section: Neural Network and Deep Learning For Weed Detectionmentioning

confidence: 99%

Applications of Artificial Intelligence Based Technologies in Weed and Pest Detection

Gupta¹,

Gupta²,

Passi³

et al. 2022

Journal of Computer Science

View full text Add to dashboard Cite

Unprecedented population growth and climate change has burdened food security and scarcity worldwide, where the agriculture sector can significantly contribute to accomplishing the demands and contribute to the economic growth of a country. Artificial Intelligence (AI) has revolutionized the agricultural domain. Pest and weed detection is significant to yielding good quality crops. The AI-based tools and technologies such as drones and robots bring advancement in crop production by performing the early detection of weeds and pests. The tools utilize image processing and machine learning algorithms to capture, analyze and detect the presence of weeds and pests in plants. The research work carried out provides a comprehensive survey for the application of artificial intelligence for both weed and pest detection. It presents widely used techniques, their evaluation parameters, and publicly available datasets which provide the current status of work for the researchers working in the domain of weed and pest detection.

show abstract

Deep convolutional neural network models for weed detection in polyhouse grown bell peppers

Cited by 55 publications

References 23 publications

Real-Time Monitoring Method of Strawberry Fruit Growth State Based on YOLO Improved Model

Real-Time Monitoring Method of Strawberry Fruit Growth State Based on YOLO Improved Model

Research on Plant Species Identification Based on Improved Convolutional Neural Network

Applications of Artificial Intelligence Based Technologies in Weed and Pest Detection

Contact Info

Product

Resources

About