FIGURE 4 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Source publication
Light detection and ranging (LiDAR) sensors can create high-quality scans of an environment. However, LiDAR point clouds are affected by harsh weather conditions since airborne particles are easily detected. In literature, conventional filtering and artificial intelligence (AI) filtering methods have been used to detect, and remove, airborne partic...
Context in source publication
Context 1
... graphical representation of the proposed CNN structure can be seen in Fig. 4, where the dimension of the tensors is highlighted at each layer. The first convolutional layer has 32 3 x 3 filters, the second convolutional layer has 128 3 x 3 filters, and the third convolutional layer has 256 3 x 3 filters. Each 2D max pooling layer has a pool size of 2 x 2. The proposed CNN model was assembled using the Python ...
Citations
... The first focuses on point cloud segmentation and object detection and recognition using LiDAR. The second area aims to establish the robustness of LiDAR point clouds against weather and external environmental factors [4,5]. ...
... These techniques utilize the geometry and light intensity of the point cloud to effectively eliminate outlier points that resemble airborne particles. However, a drawback of the method is that it removes object points, which can lead to slower algorithm performance when attempting to restore the point clouds using conventional methods [5]. ...
The paper presents a novel method for real-time detection of off-road drivable regions in LiDAR point clouds without relying on deep learning. Our method directly distinguishes drivable regions while accounting for noise caused by snow and fog. By focusing on the scanning characteristics of rotating LiDAR, our PIIC approach achieves robust performance in challenging off-road environments. The proposed technique divides the space into sections and segments drivable areas by counting points in each section. It allows noise influence to be countable using a simple probabilistic model. The developed solution offers significant advancements in autonomous driving in off-road environments since the method offers drivability in real-time with noise immunity. Experimental results demonstrate the efficiency of the proposed method in hazardous situations such as heavy snow, fog, and crosstalk from other LiDAR signals. Importantly, the low computational load enables real-time operation and provides promising opportunities for fusion with other recognition methods.
Although Light Detection and Ranging (LiDAR) is a sensor type for autonomous vehicles, it is recognized as an essential tool in various fields, such as drones, Unmanned Surface Vehicles (USVs), Unmanned Ground Vehicles (UGVs), and surveillance facilities. This is because LiDAR has advantages including a high resolution, 360-degree sensing capabilities, and consistent performance during the day and at night. However, LiDAR has the fatal disadvantage of performing poorly in snow, rain, and fog. Therefore, studies are attempting to remove noise points caused by snow, rain, and fog to ensure that LiDAR performs well even under extreme weather conditions. These studies began in approximately 2020, coinciding with accelerated research on autonomous driving, and they are still being actively pursued today. In particular, with the development of artificial intelligence technology in addition to the existing conventional methods, various approaches are being developed, but papers that thoroughly analyze and organize this research have not yet been published. Accordingly, in this study, we aim to comprehensively review the studies that have attempted to remove LiDAR sensor noise under extreme weather conditions through various methods. This review discusses the latest LiDAR denoising algorithms, with a particular focus on techniques implemented under snowy conditions. These algorithms can be categorized into five types: distance-based, intensity-based, fusion-based, learning-based, and other methods. In addition, this paper covers extreme weather datasets and related perception studies.
