The advent of computer vision systems has revolutionized numerous industries, enabling real-time object detection and measurement for applications such as manufacturing, logistics, and healthcare. However, existing solutions often focus on either detection or measurement, lacking an integrated approach that ensures both real-time performance and measurement accuracy. This research presents the Realtime Autonomous Object Detection and Measurement System (Real-AODM), which bridges this gap by integrating the YOLO model for object detection with ArUco marker-based technique for dimension measurement. By combining these two advanced techniques, Real-AODM provides an integrated prototype that enables object detection and measurement in real time. The system was trained and validated on objects of diverse shapes and sizes, ensuring its adaptability and accuracy in real-world applications. Experimental results demonstrate that the system achieves highly accurate detection and precise measurements, underscoring its robustness and efficiency. The implementation of adaptive algorithms for dynamic lighting conditions, shadow removal and various camera positions further enhances the system’s versatility for diverse applications. The results highlight the potential for Real-AODM to enhance real-time object analysis capabilities, providing a comprehensive, practical and smart solution for autonomous detection and measurement in various industry environments.