Rain Noise Cancellation Technique for LiDAR System Using Convolutional Neural Network

LiDAR is a technology that uses laser pulses to measure an object’s distance, an essential technology for Advanced Driver Assistance Systems (ADASs). However, it can be affected by adverse weather environments that may reduce the safety of ADASs. This paper proposes a convolutional neural network that utilizes lightweight network nodes with multiple repetitions instead of the traditional large-scale model. The proposed approach reduces the parameter size, and a consistent pre-processing method is designed to control the input parameters of the network. This process reduces the data size while retaining sufficient features for neural network training. The method was tested on a LiDAR system, demonstrating its ability to run on simple embedded systems and be deployed in heavy rain environments for real-time processing. The proposed convolutional neural Repetitive Lightweight Feature-preserving Network (RLFN) for LiDAR noise filtering demonstrates significant potential for generalization across various adverse weather conditions and environments. This paper discusses the theoretical and practical aspects of the model’s generalization capabilities. By theoretical justification, the design of our model incorporates several key features that enhance its ability to generalize: (1) Adaptive pre-processing—The adaptive pre-processing method standardizes input sizes while preserving essential features. This ensures that the model can handle varying data distributions and noise patterns, making it robust to different types of adverse weather conditions. (2) Inception and residual structures—The use of inception modules and residual connections allows the model to capture multi-scale features and maintain gradient flow, respectively. These structures are known for their robustness and ability to generalize well across different tasks and datasets. (3) Lightweight network design: The lightweight nature of the network, combined with repetitive loops, ensures efficient computation without sacrificing performance. This design is particularly beneficial for deployment on embedded systems, which often have limited computational resources. As verified by testing on a dataset, WADS, the RLFN demonstrated 98.53% accuracy, with a 96.31% F1 score.