Estimation of Shade Tree Density in Tea Garden using Remote Sensing Images and Deep Convolutional Neural Network

Paul, Arati; Bhattacharyya, Sayari; Chakraborty, Debasish

doi:10.1080/14498596.2021.2013966

Cited by 7 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Plantation forests are managed sites and therefore tend to report fewer errors from background noise in contrast to crown characteristics and stand density. Crown characteristic errors in plantation forests are mostly caused by under-sampled variation, including smaller crowns and different growing conditions [28, 48•, 62], unique species [58], and unseen tree forms [50,71]. Stand density errors are also commonly reported, including overlapping crowns [27,28,55,59,66] and errors from shadows [48•].…”

Section: Forest Environmentsmentioning

confidence: 99%

A Systematic Review of Individual Tree Crown Detection and Delineation with Convolutional Neural Networks (CNN)

et al. 2023

View full text Add to dashboard Cite

Purpose of Review Crown detection and measurement at the individual tree level provide detailed information for accurate forest management. To efficiently acquire such information, approaches to conduct individual tree detection and crown delineation (ITDCD) using remotely sensed data have been proposed. In recent years, deep learning, specifically convolutional neural networks (CNN), has shown potential in this field. This article provides a systematic review of the studies that used CNN for ITDCD and identifies major trends and research gaps across six perspectives: accuracy assessment methods, data types, platforms and resolutions, forest environments, CNN models, and training strategies and techniques. Recent Findings CNN models were mostly applied to high-resolution red–green–blue (RGB) images. When compared with other state-of-the-art approaches, CNN models showed significant improvements in accuracy. One study reported an increase in detection accuracy of over 11%, while two studies reported increases in F1-score of over 16%. However, model performance varied across different forest environments and data types. Several factors including data scarcity, model selection, and training approaches affected ITDCD results. Summary Future studies could (1) explore data fusion approaches to take advantage of the characteristics of different types of remote sensing data, (2) further improve data efficiency with customised sample approaches and synthetic samples, (3) explore the potential of smaller CNN models and compare their learning efficiency with commonly used models, and (4) evaluate impacts of pre-training and parameter tunings.

show abstract

Section: Forest Environmentsmentioning

confidence: 99%

A Systematic Review of Individual Tree Crown Detection and Delineation with Convolutional Neural Networks (CNN)

et al. 2023

View full text Add to dashboard Cite

show abstract

“…At present, the most used scope is to identify the type of tea, identify pests and diseases, etc. Some studies used a convolutional neural network algorithm to train the network in the set of extracted tea images in order to identify the status of tea leaves, and eventually, the status of tea leaves could be accurately identified [11][12][13][14][15][16][17][18][19][20]. Among them are studies that built a convolutional neural network recognition model based on a 7-layer structure, which improved the training performance of the system by sharing weights and gradually decreasing the learning efficiency, and achieving automatic recognition and sorting of fresh tea leaves.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea

Cai

Yuan

Liu

et al. 2022

Forests

View full text Add to dashboard Cite

Pu-erh tea, Camellia sinensis is a traditional Chinese tea, one of the black teas, originally produced in China’s Yunnan Province, named after its origin and distribution center in Pu-erh, Yunnan. Yunnan Pu-erh tea is protected by geographical Indication and has unique quality characteristics. It is made from Yunnan large-leaf sun-green tea with specific processing techniques. The quality formation of Pu-erh tea is closely related to the soil’s environmental conditions. In this paper, time-by-time data of the soil environment of tea plantations during the autumn tea harvesting period in Menghai County, Xishuangbanna, Yunnan Province, China, in 2021 were analyzed. Spearman’s correlation analysis was conducted between the inner components of Pu’er tea and the soil environmental factor. The analysis showed that three soil environmental indicators, soil temperature, soil moisture, and soil pH, were highly significantly correlated. The soil environmental quality evaluation method was proposed based on the selected soil environmental characteristics. Meanwhile, a deep learning model of Long Short Term Memory (LSTM) Network for the soil environmental quality of tea plantation was established according to the proposed method, and the soil environmental quality of tea was classified into four classes. In addition, the paper also compares the constructed models based on BP neural network and random forest to evaluate the coefficient of determination (R2), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of the indicators for comparative analysis. This paper innovatively proposes to introduce the main inclusions of Pu’er tea into the classification and discrimination model of the soil environment in tea plantations, while using machine learning-related algorithms to classify and predict the categories of soil environmental quality, instead of relying solely on statistical data for analysis. This research work makes it possible to quickly and accurately determines the physiological status of tea leaves based on the establishment of a soil environment quality prediction model, which provides effective data for the intelligent management of tea plantations and has the advantage of rapid and low-cost assessment compared with the need to measure the intrinsic quality of Pu-erh tea after harvesting is completed.

show abstract

“…Despite the importance of new methodologies to automatize the detection of planting systems, no studies directly related to this necessity were found. The studies that were found determine the density of plants [48][49][50][51], but they do not directly predict the plantation system of the study area. To achieve this, the analysis must take into account both the density of the plants and the spatial relationship among them (position and distance of each plant with respect to the others), or even the size of the plant canopy.…”

Section: Introductionmentioning

confidence: 99%

Detection of Planting Systems in Olive Groves Based on Open-Source, High-Resolution Images and Convolutional Neural Networks

et al. 2022

View full text Add to dashboard Cite

This paper aims to evaluate whether an automatic analysis with deep learning convolutional neural networks techniques offer the ability to efficiently identify olive groves with different intensification patterns by using very high-resolution aerial orthophotographs. First, a sub-image crop classification was carried out. To standardize the size and increase the number of samples of the data training (DT), the crop images were divided into mini-crops (sub-images) using segmentation techniques, which used a different threshold and stride size to consider the mini-crop as suitable for the analysis. The four scenarios evaluated discriminated the sub-images efficiently (accuracies higher than 0.8), obtaining the largest sub-images (H = 120, W = 120) for the highest average accuracy (0.957). The super-intensive olive plantings were the easiest to classify for most of the sub-image sizes. Nevertheless, although traditional olive groves were discriminated accurately, too, the most difficult task was to distinguish between the intensive plantings and the traditional ones. A second phase of the proposed system was to predict the crop at farm-level based on the most frequent class detected in the sub-images of each crop. The results obtained at farm level were slightly lower than at the sub-images level, reaching the highest accuracy (0.826) with an intermediate size image (H = 80, W = 80). Thus, the convolutional neural networks proposed made it possible to automate the classification and discriminate accurately among traditional, intensive, and super-intensive planting systems.

show abstract

Estimation of Shade Tree Density in Tea Garden using Remote Sensing Images and Deep Convolutional Neural Network

Cited by 7 publications

References 34 publications

A Systematic Review of Individual Tree Crown Detection and Delineation with Convolutional Neural Networks (CNN)

A Systematic Review of Individual Tree Crown Detection and Delineation with Convolutional Neural Networks (CNN)

Deep Learning Model for Soil Environment Quality Classification of Pu-erh Tea

Detection of Planting Systems in Olive Groves Based on Open-Source, High-Resolution Images and Convolutional Neural Networks

Contact Info

Product

Resources

About