UNLOCKING AGRICULTURAL AUTOMATION: INTEGRATING SLAM AND COMPUTER VISION FOR LIVESTOCK MANAGEMENT
DOI:
https://doi.org/10.26577/jpcsit2024020106Keywords:
simultaneous localization and mapping, computer vision, agriculture, modeling and simulation.Abstract
The use of autonomous livestock detection is crucial in modern agriculture, providing efficient control and management of animals. This article explores the use of the SLAM (Simultaneous Localization and Mapping) algorithm in conjunction with computer vision to address various challenges in enhancing the capabilities of autonomous robots and detecting livestock. Integrating computer vision and SLAM technology allows autonomous robots to successfully navigate complex conditions, adapt to dynamic environments, and accurately determine the location of livestock in real-time. This research also presents a method for simultaneously estimating the agent's position in space and mapping the surrounding environment. This approach enables robots to adapt to different lighting and weather conditions, ensuring reliable operation in various agricultural environments. Computer vision enables autonomous robots to accurately detect livestock based on visual data, enabling them to effectively monitor and manage animals. We discuss various issues that can be addressed using this combination of technologies, including navigation in unknown or changing environments, creating three-dimensional models of the surrounding environment, as well as autonomous control of robots and unmanned vehicles. This article also provides an overview of existing approaches and techniques used to address these issues, evaluating their advantages and limitations. In conclusion, we discuss the prospects for the development of this field and potential directions for future research.