PSXI-4 Study on Semantic Segmentation Technology for Efficient Manure Treatment in Pig Barn By Intelligent Cleaning Machine

Abstract

Abstract In most pig barns, intensive breeding is being carried out, and social problems such as manure disposal and large-scale infectious diseases have emerged due to this livestock farming method. In particular, organic matter from the manure is decomposed and odorous gases such as ammonia and hydrogen sulfide are emitted. The emitted harmful gases cause problems such as causing stress in pig barns, reducing immunity, and causing various diseases. To solve these problems, cleaning robots for handling manure in pig barns have been developed, and algorithms for planning optimal routes for autonomous driving or methods for cost reduction due to efficient cleaning are being studied. Most cleaning robots currently in use, employ a method of treating accumulated manure by spraying high-pressure water from a stored water tank. If water can be sprayed only on areas that need cleaning, water consumption can be reduced, so we propose a technology that can determine this through a camera. If it is possible to determine whether cleaning is necessary by segmenting only manure from the image into objects, it is expected to significantly reduce unnecessary water consumption. The purpose of this study is to determine whether cleaning is necessary by dividing excrement into objects from images taken during autonomous driving with a camera mounted on the front of a cleaning robot. The final goal is to obtain a segmented image capable of recognizing only the manure part requiring cleaning from the captured image. The first step acquires image information using an RGB camera. At the beginning of the study, when the number of images is insufficient, the segmentation performance is checked through semantic segmentation using the difference between manure and other objects or backgrounds using image information. Depending on the segmentation performance and the number of acquired images, we plan to use a deep learning-based algorithm in the future. The ultimate goal of this study is to develop a technology for obtaining segmented images capable of recognizing excreta by utilizing image information from captured images. In addition, if only the manure part can be accurately recognized through this study, we plan to apply the technology of spraying water only to the necessary part by using it as information to determine whether cleaning is necessary from the segmented image. Through this, the company plans to apply the technology to self-driving cleaning robots to develop high-efficiency intelligent cleaning robots capable of efficiently handling manure. This achievement was made by the support of the Ministry of Agriculture, Food and Rural Affairs, R&D project(421044043HD030)