This paper presents an intelligent integrated system for fruit detection using multi-UAV imaging and deep learning. The system combines artificial intelligence (AI), deep learning (DL), and unmanned aerial vehicles (UAVs) to achieve real-time fruit detection and counting in orchards. The core innovation is the ability to simultaneously capture and synchronize video frames from multiple UAV cameras, converting them into a cohesive data structure and continuous image. This integration is further enhanced by image quality optimization techniques, ensuring high-resolution and accurate detection of targeted objects during UAV operations. The system's effectiveness is proven by experiments, achieving a high mean average precision rate of 86.8% in fruit detection and counting, surpassing existing technologies. It also maintains low average error rates, with a false positive rate of 14.7% and a false negative rate of 18.3%, even under challenging weather conditions like cloudiness. The practical implications of this multi-UAV imaging and DL-based approach are vast, particularly for real-time fruit recognition in orchards, marking a significant stride forward in digital agriculture aligned with Industry 4.0 objectives. The system includes a new method for dynamic image capture from multiple UAVs, real-time video stream synchronization, a novel DCNN architecture called YOLOv5-v1 for detecting specified structural objects, and an improved method for counting specified structural objects using a group of UAVs. The paper also describes the experimental setup, including the use of a farm orchard, equipment details, and evaluation criteria such as precision, recall, F1-score, and mAP. The results show that the system achieves high accuracy and efficiency in fruit detection and counting, with a mean average precision of 86.8% and a low false positive and false negative rate. The system is designed to be efficient, with a low number of parameters and a small model size, making it suitable for deployment in various hardware setups. The study contributes to the development of intelligent systems for automated fruit detection in orchard environments, addressing the challenges of traditional methods and providing a robust solution for real-time fruit recognition and counting.This paper presents an intelligent integrated system for fruit detection using multi-UAV imaging and deep learning. The system combines artificial intelligence (AI), deep learning (DL), and unmanned aerial vehicles (UAVs) to achieve real-time fruit detection and counting in orchards. The core innovation is the ability to simultaneously capture and synchronize video frames from multiple UAV cameras, converting them into a cohesive data structure and continuous image. This integration is further enhanced by image quality optimization techniques, ensuring high-resolution and accurate detection of targeted objects during UAV operations. The system's effectiveness is proven by experiments, achieving a high mean average precision rate of 86.8% in fruit detection and counting, surpassing existing technologies. It also maintains low average error rates, with a false positive rate of 14.7% and a false negative rate of 18.3%, even under challenging weather conditions like cloudiness. The practical implications of this multi-UAV imaging and DL-based approach are vast, particularly for real-time fruit recognition in orchards, marking a significant stride forward in digital agriculture aligned with Industry 4.0 objectives. The system includes a new method for dynamic image capture from multiple UAVs, real-time video stream synchronization, a novel DCNN architecture called YOLOv5-v1 for detecting specified structural objects, and an improved method for counting specified structural objects using a group of UAVs. The paper also describes the experimental setup, including the use of a farm orchard, equipment details, and evaluation criteria such as precision, recall, F1-score, and mAP. The results show that the system achieves high accuracy and efficiency in fruit detection and counting, with a mean average precision of 86.8% and a low false positive and false negative rate. The system is designed to be efficient, with a low number of parameters and a small model size, making it suitable for deployment in various hardware setups. The study contributes to the development of intelligent systems for automated fruit detection in orchard environments, addressing the challenges of traditional methods and providing a robust solution for real-time fruit recognition and counting.