Small Object Detection with YOLO: A Performance Analysis Across Model Versions and Hardware
This work aids practitioners in deploying YOLO models effectively by providing insights into hardware-specific performance, but it is incremental as it focuses on comparative analysis without introducing new methods.
This paper evaluates YOLO object detection models (v5 to v11) across hardware platforms and optimization libraries, analyzing inference speed, detection accuracy, and sensitivity to object size (1%, 2.5%, and 5% of image area). It identifies trade-offs to guide optimal model selection for real-world deployment.
This paper provides an extensive evaluation of YOLO object detection models (v5, v8, v9, v10, v11) by com- paring their performance across various hardware platforms and optimization libraries. Our study investigates inference speed and detection accuracy on Intel and AMD CPUs using popular libraries such as ONNX and OpenVINO, as well as on GPUs through TensorRT and other GPU-optimized frameworks. Furthermore, we analyze the sensitivity of these YOLO models to object size within the image, examining performance when detecting objects that occupy 1%, 2.5%, and 5% of the total area of the image. By identifying the trade-offs in efficiency, accuracy, and object size adaptability, this paper offers insights for optimal model selection based on specific hardware constraints and detection requirements, aiding practitioners in deploying YOLO models effectively for real-world applications.