LiDAR Translation Based on Empirical Approach between Sunny and Foggy for Driving Simulation

Lee, Jinho; Shiotsuka, Daiki; Nishimori, Toshiaki; Nakao, Kenta; Kamijo, Shunsuke

doi:10.1109/wpmc55625.2022.10014784

Cited by 3 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the JARI data set as our data set, which was employed in our previous research on LiDAR translation [ 17 , 18 ] that considered environmental factors. The JARI data set is a reliable data set, to the extent that it was submitted to this journal as part of the LiDAR translation [ 17 ] research last year.…”

Section: Experimental Resultsmentioning

confidence: 99%

“…The BEV generated using LiDAR data typically represents a projection of a three-dimensional environment, which is changed into a two-dimensional perspective viewed from above. Recent investigations have begun to address this limitation by considering weather changes and height information into LiDAR translation, as evidenced in [ 17 , 18 ]. Despite image and LiDAR data dominating the translation research landscape, radar data have received comparatively less attention.…”

Section: Related Workmentioning

confidence: 99%

“…GANs [ 10 ] have made significant contributions, not only to data augmentation but also to image translation, resulting in a variety of derivative research proposals [ 11 , 12 , 13 , 14 , 15 ] in this field. Some studies [ 16 , 17 , 18 ] have proposed GAN-based methods for LiDAR data augmentation. However, these studies have primarily remained limited to image and LiDAR data and have not extended to augmenting radar data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LiDAR-to-Radar Translation Based on Voxel Feature Extraction Module for Radar Data Augmentation

Lee,

Bang,

Shimizu

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

In autonomous vehicles, the LiDAR and radar sensors are indispensable components for measuring distances to objects. While deep-learning-based algorithms for LiDAR sensors have been extensively proposed, the same cannot be said for radar sensors. LiDAR and radar share the commonality of measuring distances, but they are used in different environments. LiDAR tends to produce less noisy data and provides precise distance measurements, but it is highly affected by environmental factors like rain and fog. In contrast, radar is less impacted by environmental conditions but tends to generate noisier data. To reduce noise in radar data and enhance radar data augmentation, we propose a LiDAR-to-Radar translation method with a voxel feature extraction module, leveraging the fact that both sensors acquire data in a point-based manner. Because of the translation of high-quality LiDAR data into radar data, this becomes achievable. We demonstrate the superiority of our proposed method by acquiring and using data from both LiDAR and radar sensors in the same environment for validation.

show abstract

Section: Experimental Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LiDAR-to-Radar Translation Based on Voxel Feature Extraction Module for Radar Data Augmentation

Lee,

Bang,

Shimizu

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to this, several research works have explored denoising and translating LiDAR point clouds using CNNs, GANs, and statistical filters [27], [28]. Recent studies have started considering weather changes and height information in LiDAR translation, as demonstrated in [29], [30]. While image and LiDAR data have been the subject of numerous translation research, radar data has received less attention.…”

Section: A Deep Learning Based Translation Methodsmentioning

confidence: 99%

“…This process is not required for images since they maintain the same range of RGB values. For LiDAR translation [29], [30], the above process improves the learning results.…”

Section: ) Jari Dataset For Radar Translationmentioning

confidence: 97%

Radar Translation Network Between Sunny and Rainy Domains by Combination of KP-Convolution and CycleGAN

Lee,

Bang,

Nishimori

et al. 2023

IEEE Open J. Intell. Transp. Syst.

Self Cite

View full text Add to dashboard Cite

Recently, research on autonomous driving has focused on the advent of various deep learning algorithms. The main sensors for autonomous driving include cameras, LiDAR, and radar, but these algorithms primarily focus on image and LiDAR data. This is because radar data is limited compared to image and LiDAR data. To address the lack of data problem, GAN-based translation methods have been proposed. However, these methods also focus only on image and LiDAR data, such as day-to-night translation or sunny-to-adverse weather translation. Since radar data differs depending on radar sensors and radar points are too sparse to learn patterns compared to LiDAR, translation with radar data is a challenging task. Radar is usually utilized as a sensor that is nearly unaffected by the weather. However, it has been confirmed through JARI data collected by us that rain has a negative effect. CycleGAN is useful for data translation in traffic scenes where pair data is difficult to acquire, since CycleGAN is a network specialized in style translation. KP-Convolution is a module specialized in feature extraction of points while maintaining location information. Therefore, we propose a radar translation network between sunny and rainy domains by combining KP-Convolution and CycleGAN. In this process, we address the adverse effects of radar data by rain, establishing the training format of radar data, KP-Convolution which can learn patterns despite a small number of points, and CycleGAN which is the basis of the translation method.

show abstract

3DR-DIFF: Blind Diffusion Inpainting for 3D Point Cloud Reconstruction and Segmentation

Yasas Mahima,

Perera,

Anavatti

et al. 2024

2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

LiDAR Translation Based on Empirical Approach between Sunny and Foggy for Driving Simulation

Cited by 3 publications

References 21 publications

LiDAR-to-Radar Translation Based on Voxel Feature Extraction Module for Radar Data Augmentation

LiDAR-to-Radar Translation Based on Voxel Feature Extraction Module for Radar Data Augmentation

Radar Translation Network Between Sunny and Rainy Domains by Combination of KP-Convolution and CycleGAN

3DR-DIFF: Blind Diffusion Inpainting for 3D Point Cloud Reconstruction and Segmentation

Contact Info

Product

Resources

About