Efficient Object Detection with an Optimized YOLOv8x Model

Abstract

This study developed an efficient object detection model for indoor environments, addressing common challenges such as occlusions, varying lighting, and cluttered scenes. We evaluated several YOLOv8 variants—ranging from nano to extra-large—and introduced an optimized YOLOv8x model. Our approach combines structured pruning, quantization-aware training, and advanced data preprocessing techniques, including augmentation and noise reduction, to improve model performance while reducing computational demands. The models were developed and evaluated using a carefully selected indoor object detection dataset featuring ten common categories. Performance was measured through key metrics like precision, recall, and mean average precision (mAP). Among them, the fine-tuned YOLOv8x clearly outshined the baseline models, reaching a training precision of 0.577, a recall of 0.572, and an [email protected] of 0.537. When tested on new data, it demonstrated even better generalization, delivering a precision of 0.502, a recall of 0.528, and an [email protected] of 0.480—proving robustness and reliability in real-world scenarios. These results demonstrate that pruning and quantization can significantly reduce model complexity without sacrificing accuracy, which helps to detect indoor objects. In essence, it is optimized for indoor object detection, offering promising applications in smart environments, surveillance, and robotics.