Improved small-object detection using YOLOv8: A comparative study

Abstract

In the last decade or so, deep neural networks have evolved at a rapid pace, where computer vision has been constantly refreshing its best performance and has been integrated into our lives. In the field of target detection, YOLO model is a popular real-time target detection algorithm model that is fast, efficient, and accurate. This research aims to optimize the latest YOLOv8 model to improve its detection of small objects and compare it with another different version of YOLO models. To achieve this goal, we used the classical deep learning algorithm YOLOv8 as a benchmark and made several improvements and optimizations. We optimized the definition of the detection head, narrowed its perceptual field, and increased its number, allowing the model to better focus on the detailed information of small objects. We compared the optimized YOLOv8 model with other classical YOLO models, including YOLOv3 and YOLOv5n. The experimental results show that our optimized model improves small object detection with higher accuracy. This research provides an effective solution for small object detection with good application prospects. With the continuous development and improvement of the technology, we believe that the YOLO algorithm will continue to play an essential role in object detection and provide a reliable solution for various real-time applications.

An Advanced Approach to Object Detection and Tracking in Robotics and Autonomous Vehicles Using YOLOv8 and LiDAR Data Fusion

“…The corners' coordinates for the bounding box of Car2 are as in (25). The length, width, and height of the truck bounding box are 1.31 m, 0.54 m, and 0.97 m. The dimensions of the 3D bounding boxes closely match the dimensions of the objects detected by the 3D LiDAR.…”

“…It balances speed and accuracy effectively, making it a popular choice in many practical applications. Compared with earlier YOLO versions [22][23][24], YOLOv8 is faster, more accurate, and more flexible [25,26]. These advantages make YOLOv8 particularly suitable for fusion with LiDAR data, providing a powerful solution for real-time object detection and tracking in complex dynamic environments.…”