PSXI-15 Estimating Vegetation Index for Outdoor Free-Range Pig Production Using Yolo

Abstract

Abstract In the United States, outdoor pig production is steadily increasing thanks to the niche market strategy for small farmers, consumer antipathy to factory farm products, and the trend of eco-friendly and animal welfare, and research on this is continuing. One of the advantages of outdoor pig production is that farms can be run with small capital, and one of the disadvantages is that cover crops can be devastated due to the burrowing nature of pigs, resulting in underground water being overnourished if management is neglected. Recent scientific advances have made it possible to take images from unmanned aerial vehicles. Utilizing this technology to ascertain the situation of grazing land in outdoor grazing pig production will greatly help farmers maintain pastures at the recommended rate without leaving pastures until they are irreparable. The objective of this study was to quantitatively estimate the level of grazing area damage in outdoor free-range pig production using an UAV with an RGB image sensor. Ten corn field images were captured by an UAV over a period of approximately two weeks, during which gestating sows were allowed to graze freely on the corn field measuring 100×50 m2. The images were corrected to a bird's-eye view, and then divided into 32 segments and sequentially inputted into the YOLOv4 detector to detect the corn images according to their condition. The 43 raw training images selected randomly out of 320 segmented images, each with different degrees of corn devastation, were flipped to create 86 images, and then these images were further augmented by rotating them in 5-degree increments to create a total of 6,192 images. The increased 6,192 images are further augmented by applying three random color transformations to each image, resulting in a total of 24,768 datasets. The system accumulates the number and area of the detected labels to calculate the corn occupancy rate. The occupancy rate of corn in the field was estimated efficiently using YOLO. As of the first day of observation (day 2), it was evident that almost all the corn had disappeared by the ninth day. When grazing 20 sows in a 50×100 m2 cornfield (250 m2/sow), it appears that the animals should be rotated to other grazing areas to protect the cover crop after at least five days. In agricultural technology, most of the research using machine and deep learning is related to the detection of fruits and pests, and research on other application fields is needed. In addition, large-scale image data collected by experts in the field are required as training data to apply deep learning. If data required for deep learning is insufficient, a large number of data augmentation is required.