Enhanced YOLOv8n model boosts real-time vehicle detection with attention and efficient convolution

Researchers have developed an improved YOLOv8n model for real-time vehicle detection, incorporating Ghost Modules, CBAM, and DCNv2. This enhanced model aims to boost performance in intelligent transportation systems by reducing feature redundancy and refining feature representation. Tested on the KITTI dataset, the model achieved a 95.4% [email protected], an improvement of nearly 9% over the standard YOLOv8n. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Offers a more accurate and efficient solution for vehicle detection in intelligent transportation systems.

RANK_REASON This is a research paper detailing an improved computer vision model for a specific application.

Read on arXiv cs.CV →

• YOLOv8n
• Ghost Module
• CBAM
• DCNv2
• KITTI dataset

• paper
• other