A lightweight distance estimation method using pinhole camera geometry model

Abstract Accurate distance estimation using a monocular camera remains a significant challenge in computer vision, especially in achieving a balance between computational efficiency and precision. Traditional sensor-based methods often lack robustness under varying conditions and tend to be more expensive compared to other approaches. On the other hand, modern deep learning methods can be computationally demanding and may not be suitable for real-time applications on resource-constrained devices. To address these gaps, we propose a lightweight and efficient distance estimation model that integrates the pinhole camera geometry with YOLOv8, a state-of-the-art object detection model. Our approach leverages the geometric simplicity of the pinhole model while benefiting from YOLOv8’s superior object detection capabilities. Experimental results demonstrate the effectiveness of our method, achieving a mean absolute error of 0.085 m and a mean absolute percentage error of 1.94% over distances ranging from 1.1 m to 7.5 m. Furthermore, the method achieves 98.61% accuracy within its effective range (1.1–5.5 m). These findings highlight the practical impact of our model, offering a cost-effective and computationally efficient solution for distance estimation tasks in robotics, autonomous systems, and similar real-world applications.