Comparison of estimating vegetation index for outdoor free-range pig production using convolutional neural networks

Abstract

This study aims to predict the change in corn share according to the grazing of 20 gestational sows in a mature corn field by taking images with a camera-equipped unmanned air vehicle (UAV). Deep learning based on convolutional neural networks (CNNs) has been verified for its performance in various areas. It has also demonstrated high recognition accuracy and detection time in agricultural applications such as pest and disease diagnosis and prediction. A large amount of data is required to train CNNs effectively. Still, since UAVs capture only a limited number of images, we propose a data augmentation method that can effectively increase data. And most occupancy prediction predicts occupancy by designing a CNN-based object detector for an image and counting the number of recognized objects or calculating the number of pixels occupied by an object. These methods require complex occupancy rate calculations; the accuracy depends on whether the object features of interest are visible in the image. However, in this study, CNN is not approached as a corn object detection and classification problem but as a function approximation and regression problem so that the occupancy rate of corn objects in an image can be represented as the CNN output. The proposed method effectively estimates occupancy for a limited number of cornfield photos, shows excellent prediction accuracy, and confirms the potential and scalability of deep learning.

Keywords: Convolutional neural network; Image analysis; Outdoor; Pig; Vegetation index.

Fig. 1.. Structure of convolutional neural network (CNN).

Fig. 2.. Examples of images taken by the unmanned air vehicle (UAV).

Fig. 3.. Example of image correction.

Fig. 4.. Images after pre-processing.

Fig. 5.. Data augmentation.

Fig. 6.. The CNN structure for regression. CNN, convolutional neural network; ACI_i, The occupancy rate of intact corn; ACD_i, The occupancy rate of damaged corn; ACS_i, The occupancy rate of corn with stubble; ACT_i, The occupancy rate of corn in all conditions.

Fig. 7.. System configuration. ACI_i, The occupancy rate of intact corn; ACD_i, The occupancy rate of damaged corn; ACS_i, The occupancy rate of corn with stubble; ACT_i, The occupancy rate of corn in all conditions.

Fig. 8.. The degree of corn coverage in the training data.

Fig. 9.. The occupancy rate of corn by date (AlexNet).

Fig. 10.. The occupancy rate of corn by date (GoogLeNet).

Fig. 11.. The occupancy rate of corn by date (Vgg16).

Fig. 12.. The degree of occupancy of corn by date (Vgg19).

Fig. 13.. The degree of occupancy of corn by date (ResNet50).

Fig. 14.. The degree of occupancy of corn by date (ResNet101).