• Journal of Biosystems Engineering
• /
• v.28 no.6
• /
• pp.485-490
• /
• 2003

Flexural rigidity(EI) and deflection characteristics of rice stalks were studied to investigate the mechanical interaction between a rice stalk and a combine reel in harvesting. Deflection of a rice stalk caused by reel operation is so large that conventional equation of small deflection fer elastic beam cannot be applied to the study of deflection characteristics. Therefore, an equation of large deflection for elastic beam was introduced in this study. Feasibility of this equation was examined by comparing theoretical calculation with the measured results for piano wire, and by the relationship between deflection and load acting on a rice stalk which was presumed by this equation. Results showed that the large deflection equation could predict the measurement data quite well. From this research, the following results were obtained. 1. Flexural rigidity(EI) calculated from the equation of large deflection was 4.0${\times}$l0$^4$N$.$$\textrm{mm}^2$(diameter 1.4mm, deflection 300mm) while the actual EI value of a piano wire(diameter 1.4mm) was 3.9${\times}$10$^4$N$.$$\textrm{mm}^2$. 2. The relationship between deflection and load acting on a rice stalk could be presumed by the large deflection equation. Flexural rigidity values of tested rice stalks calculated from the equation of large deflection were 1.6∼2.4${\times}$ l0$^4$N$.$$\textrm{mm}^2$(Hwa sung), 2.7∼3.5${\times}$ l0$^4$N$.$$\textrm{mm}^2$(Il pum) and 1.7∼2.4${\times}$ l0$^4$N$.$$\textrm{mm}^2$(Damakum)

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.681-692
• /
• 2019

In this paper, a hybrid deep learning model, called 2D convolution with bidirectional long short-term memory (2DCBLSTM), is presented that can effectively combine both spatial and temporal features for crop classification. In the proposed model, 2D convolution operators are first applied to extract spatial features of crops and the extracted spatial features are then used as inputs for a bidirectional LSTM model that can effectively process temporal features. To evaluate the classification performance of the proposed model, a case study of crop classification was carried out using multi-temporal unmanned aerial vehicle images acquired in Anbandegi, Korea. For comparison purposes, we applied conventional deep learning models including two-dimensional convolutional neural network (CNN) using spatial features, LSTM using temporal features, and three-dimensional CNN using spatio-temporal features. Through the impact analysis of hyper-parameters on the classification performance, the use of both spatial and temporal features greatly reduced misclassification patterns of crops and the proposed hybrid model showed the best classification accuracy, compared to the conventional deep learning models that considered either spatial features or temporal features. Therefore, it is expected that the proposed model can be effectively applied to crop classification owing to its ability to consider spatio-temporal features of crops.