Efficiently determining the density of crops and weeds is essential for precision agriculture, enabling optimal resource utilization and enhanced crop management strategies. This paper introduces an innovative approach to classify and estimate the population densities of crops and weeds within agricultural fields using the You Only Look Once (YOLO) object detection algorithm. By integrating the YOLOv8 model with the quadrat sampling technique, the method achieves accurate identification and classification while providing a detailed spatial analysis of plant populations. The YOLO model is meticulously trained and tested on annotated datasets, ensuring robust performance across diverse agricultural scenarios. Experimental results demonstrate that the proposed approach significantly enhances the accuracy of density estimation compared to traditional methods. The YOLO-based detection technique enables swift and reliable identification of plant species and facilitates thorough frequency analysis within specified quadrats. This method supports the precise extrapolation of plant population data to larger field areas, aiding the development of targeted fertilization and pest control strategies. These findings underscore the potential of advanced object detection technologies to revolutionize agricultural practices, promoting efficient and sustainable land management.