Deep learning-based dynamic object classification using LiDAR point cloud augmented by layer-based accumulation for intelligent vehicles

Kim, Kyungpyo; Kim, Chan-Soo; Jang, Chang‐Hyun; Sunwoo, Myoungho; Jo, Kichun

doi:10.1016/j.eswa.2020.113861

Cited by 18 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LCDNet estimates the whole six degrees of freedom (DoF) relative transformation between point clouds under driving conditions, which is completely different from previous registration methods and helps to achieve faster convergence in subsequent ICP refinements. This method can also be integrated into the existing Lidar SLAM database (Kim et al, 2021 ).…”

Section: Applicationsmentioning

confidence: 99%

A review of rigid point cloud registration based on deep learning

Chen,

Feng,

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

With the development of 3D scanning devices, point cloud registration is gradually being applied in various fields. Traditional point cloud registration methods face challenges in noise, low overlap, uneven density, and large data scale, which limits the further application of point cloud registration in actual scenes. With the above deficiency, point cloud registration methods based on deep learning technology gradually emerged. This review summarizes the point cloud registration technology based on deep learning. Firstly, point cloud registration based on deep learning can be categorized into two types: complete overlap point cloud registration and partially overlapping point cloud registration. And the characteristics of the two kinds of methods are classified and summarized in detail. The characteristics of the partially overlapping point cloud registration method are introduced and compared with the completely overlapping method to provide further research insight. Secondly, the review delves into network performance improvement summarizes how to accelerate the point cloud registration method of deep learning from the hardware and software. Then, this review discusses point cloud registration applications in various domains. Finally, this review summarizes and outlooks the current challenges and future research directions of deep learning-based point cloud registration.

show abstract

Section: Applicationsmentioning

confidence: 99%

A review of rigid point cloud registration based on deep learning

Chen,

Feng,

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

show abstract

“…This process is particularly challenging due to the variability and complexity of spatial data in real-world environments. Many registration-based methods [4][5][6][7][8] are currently being investigated for aligning multi-frame point clouds to obtain dense point cloud maps. The Iterative Closest Point (ICP) algorithm [9] is a classical point cloud alignment algorithm that optimizes the correspondence between two point clouds by minimizing their differences.…”

Section: Introductionmentioning

confidence: 99%

“…With the development of multi-modality techniques, several studies have proposed utilizing additional information to improve the performance of 3D object detectors. The authors of [7] propose a framework based on an improved ICP method to enhance the performance of deep learning-based classification by incorporating the shape information of the LiDAR point cloud. The authors of [24] explore a motion detection method based on point cloud registration.…”

Section: Introductionmentioning

confidence: 99%

Kalman-Based Scene Flow Estimation for Point Cloud Densification and 3D Object Detection in Dynamic Scenes

Ding,

Zhang,

et al. 2024

Sensors

View full text Add to dashboard Cite

Point cloud densification is essential for understanding the 3D environment. It provides crucial structural and semantic information for downstream tasks such as 3D object detection and tracking. However, existing registration-based methods struggle with dynamic targets due to the incompleteness and deformation of point clouds. To address this challenge, we propose a Kalman-based scene flow estimation method for point cloud densification and 3D object detection in dynamic scenes. Our method effectively tackles the issue of localization errors in scene flow estimation and enhances the accuracy and precision of shape completion. Specifically, we introduce a Kalman filter to correct the dynamic target’s position while estimating long sequence scene flow. This approach helps eliminate the cumulative localization error during the scene flow estimation process. Extended experiments on the KITTI 3D tracking dataset demonstrate that our method significantly improves the performance of LiDAR-only detectors, achieving superior results compared to the baselines.

show abstract

“…In addition, the computational burden of processing and parsing these two kinds of data is also quite heavy. Therefore, finding an effective data fusion method can not only make full use of the advantages of the two sensors, but also avoid their limitations, which is very important for improving the performance and safety of the automatic driving system [4][5]. This study deeply understands the characteristics and challenges of BEV vision and LiDAR data.…”

Section: Introductionmentioning

confidence: 99%

Comparative Study on BEV Vision and LiDAR Point Cloud Data Fusion Methods

Zhou

2023

TCSISR

View full text Add to dashboard Cite

With the gradual maturity of autonomous driving technology, efficient fusion and processing of multimodal sensor data has become an important research direction. This study mainly explores the strategy of integrating BEV (Bird's Eye View) vision with LiDAR point cloud data. We evaluated the performance and applicability of each of the three main data fusion methods through in-depth comparison: early fusion, mid-term fusion, and late fusion. First of all, we summarize the working principle and data characteristics of BEV vision and LiDAR, and emphasize their key roles in auto drive system. Then, the theoretical basis and implementation methods of the three fusion strategies were described in detail. The experimental results show that different fusion strategies exhibit their own advantages in different application scenarios and requirements. For example, early fusion performs well in high-precision tasks, but has a high demand for computing resources. And mid-term fusion is more suitable in scenarios with high real-time requirements. Overall, this study provides in-depth insights and practical suggestions on the fusion of BEV vision and LiDAR data in the field of autonomous driving, laying a solid foundation for future research and applications.

show abstract

Deep learning-based dynamic object classification using LiDAR point cloud augmented by layer-based accumulation for intelligent vehicles

Cited by 18 publications

References 26 publications

A review of rigid point cloud registration based on deep learning

A review of rigid point cloud registration based on deep learning

Kalman-Based Scene Flow Estimation for Point Cloud Densification and 3D Object Detection in Dynamic Scenes

Comparative Study on BEV Vision and LiDAR Point Cloud Data Fusion Methods

Contact Info

Product

Resources

About