首页|面向恶劣天气的激光雷达目标检测技术研究

面向恶劣天气的激光雷达目标检测技术研究

扫码查看
自动驾驶车辆高度依赖传感器收集环境信息,其中LiDAR传感器因能提供精确的三维空间信息而在该领域广泛应用.然而,恶劣天气条件(例如雾、雪、雨等)会导致LiDAR光束散射与折射,进而降低探测精度并影响目标检测性能.因此,研究如何有效缓解LiDAR在恶劣天气下目标检测性能的下降显得尤为重要.利用恶劣天气条件下的真实数据集,探讨了通过数据增强技术模拟恶劣天气以生成仿真数据集的方法,通过分析这些方法的优势与局限性,指出了未来研究的重点与难点.
Research on LiDAR Target Detection Technology for Inclement Weather
Autonomous driving vehicles rely on sensors to collect surrounding environment information.Li-DAR sensors can provide accurate three-dimensional spatial information of the scene and are widely used in the field of autonomous driving.However,laser beam is scattered and refracted in severe weather condi-tions(such as fog,snow or rain),resulting in a decrease in detection accuracy and changes in target detec-tion performance.Therefore,it is crucial to explore how to mitigate the degradation of LiDAR target detec-tion performance.Utilizing real-world datasets collected under such conditions,methods to simulate ad-verse weather through data augmentation techniques to generate simulation datasets are explored.By analy-zing the advantages and limitations of these methods,the key focuses and challenges for future research are identified.

LiDARadverse weatherreal-world datasetssimulation datasets

杨雪、黄宏成

展开 >

上海交通大学机械与动力工程学院,上海 200240

激光雷达 恶劣天气 真实数据集 仿真数据集

2024

传动技术
上海交通大学

传动技术

影响因子:0.197
ISSN:1006-8244
年,卷(期):2024.38(3)