摘要：With the continuous advancement of autonomous vehicle technology, the recognition of buildings becomes increasingly crucial. It enables autonomous vehicles to better comprehend their surrounding environment, facilitating safer navigation and decision-making processes. Therefore, it is significant to improve detection efficiency on edge devices. However, building recognition faces problems such as severe occlusion and large size of detection models that cannot be deployed on edge devices. To solve these problems, a lightweight building recognition model based on YOLOv5s is proposed in this study. We first collected a building dataset from real scenes and the internet, and applied an improved GridMask data augmentation method to expand the dataset and reduce the impact of occlusion. To make the model lightweight, we pruned the model by the channel pruning method, which decreases the computational costs of the model. Furthermore, we used Mish as the activation function to help the model converge better in sparse training. Finally, comparing it to YOLOv5s (baseline), the experiments show that the improved model reduces the model size by 9.595 MB, and the mAP@0.5 reaches 82.3%. This study will offer insights into lightweight building detection, demonstrating its significance in environmental perception, monitoring, and detection, particularly in the field of autonomous driving.

关键字：building detection; data augmentation; YOLOv5; lightweight model

ISSN号： 2079-9292

卷、期、页：卷13期11

发表日期：2024-06-01

影响因子：0.000000

期刊分区（SCI为中科院分区）：三区

收录情况：SCI（科学引文索引印刷版）,SCIE（科学引文索引网络版）

发表期刊名称：ELECTRONICS

通讯作者：赵京翼,李一帆,曹靖,谷雨泰,吴远泽

第一作者：陈冲,王莹莹

论文类型：期刊论文

论文概要：赵京翼,李一帆,曹靖,谷雨泰,吴远泽,陈冲,王莹莹，An Improved YOLOv5s Model for Building Detection，ELECTRONICS，2024，卷13期11

论文题目：An Improved YOLOv5s Model for Building Detection