The escalating global population, industrialization, and climate change are increasing pressure on agricultural lands. In this context, sustainable agricultural land management is critically important, particularly for high-value crops such as citrus, which plays critical role in economic and food security. Accurate detection and enumeration of citrus trees are essential for ensuring the sustainability and effective monitoring of citrus cultivation. This study employs deep learning methods for object detection of citrus trees in the Tarsus district of Mersin, comparing the performance of Mask R-CNN, YOLOv8, and YOLO11 models using low-resolution satellite imagery. Additionally, the impact of super-resolution (SR) techniques on model accuracy is examined. Results demonstrate that integrating SR techniques significantly improves object detection accuracy, with the YOLO11 model achieving the highest performance. In the raw dataset, the YOLO11 model obtained mAP50 (45.39%) and mAP50-95 (22.15%) values; in the SR applied dataset, these metrics were 85.93% and 67.66%, respectively. This research underscores the potential of deep learning-based approaches to enhance citrus tree monitoring, yield estimation, and agricultural management practices, offering actionable insights for sustainable agriculture.