A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data
In recent years, following the development of sensor and computer techniques, it is favored by many fields, i.e. automatic drive, intelligent home, etc., which the deep learning based semantic segmentation method for point cloud data collected by LiDAR. This type method can automatic extract feature...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10343142/ |
| _version_ | 1827376452878729216 |
|---|---|
| author | Tong Zheng Jialun Chen Wenbin Feng Chongchong Yu |
| author_facet | Tong Zheng Jialun Chen Wenbin Feng Chongchong Yu |
| author_sort | Tong Zheng |
| collection | DOAJ |
| description | In recent years, following the development of sensor and computer techniques, it is favored by many fields, i.e. automatic drive, intelligent home, etc., which the deep learning based semantic segmentation method for point cloud data collected by LiDAR. This type method can automatic extract features of point cloud, helping label semantic categories. However, compared to 2D images, 3D point cloud data is more expensive to acquire. Hence, to save research and production costs, the low-thread LiDAR is a good choice. For one observation scenario, following the decrease of the line, the point cloud becomes sparse, which may cause the information loss. To balance the cost and the segmentation effect, we provide a point cloud completion auxiliary semantic segmentation method. Here, the baseline of the proposed method is Bilateral Augmentation and Adaptive Fusion (BAAF) model. It is the main contribution that a completion module introduction in feature extraction part of BAAF. Under the premise of using low-thread LiDAR sensor to collect data, the semantic segmentation effect of 3D field point cloud is improved as much as possible. It provides theoretical basis for cost saving in practical industrial application. The feature extraction of completion module consists of Graph Aggregation Convolution (GAC) and attention mechanism. Then, we use shuffle transform to upsampling data. In addition, to analyze the effectiveness of the proposed method, we make a new dataset with sparse point cloud data, i.e. Sparse-SemanticKITTI dataset, based on public SemanticKITTI dataset. Furthermore, in experiment part, we prove the research significance. Moreover, we compare the segmentation results between classical methods to the proposed one based on point cloud data in SemanticKITTI, Sparse-SemanticKITTI and Semantic3D dataset, respectively. The effectiveness of the proposed one is obvious. Finally, the model complexity is analyzed. In sum, we provide a sparse point cloud semantic segmentation method to balance the cost and the effect. |
| first_indexed | 2024-03-08T12:10:06Z |
| format | Article |
| id | doaj.art-db69f7f507944d2483aebfce3a7eebe0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T12:10:06Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-db69f7f507944d2483aebfce3a7eebe02024-01-23T00:05:03ZengIEEEIEEE Access2169-35362024-01-0112104591046910.1109/ACCESS.2023.333965710343142A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud DataTong Zheng0https://orcid.org/0000-0003-2251-6844Jialun Chen1Wenbin Feng2Chongchong Yu3https://orcid.org/0000-0003-4234-1260School of Artificial Intelligence, Beijing Technology and Business University, Beijing, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing, ChinaChina Coal Technology and Engineering Group, Shenyang Research Institute, Fushun, ChinaSchool of Artificial Intelligence, Beijing Technology and Business University, Beijing, ChinaIn recent years, following the development of sensor and computer techniques, it is favored by many fields, i.e. automatic drive, intelligent home, etc., which the deep learning based semantic segmentation method for point cloud data collected by LiDAR. This type method can automatic extract features of point cloud, helping label semantic categories. However, compared to 2D images, 3D point cloud data is more expensive to acquire. Hence, to save research and production costs, the low-thread LiDAR is a good choice. For one observation scenario, following the decrease of the line, the point cloud becomes sparse, which may cause the information loss. To balance the cost and the segmentation effect, we provide a point cloud completion auxiliary semantic segmentation method. Here, the baseline of the proposed method is Bilateral Augmentation and Adaptive Fusion (BAAF) model. It is the main contribution that a completion module introduction in feature extraction part of BAAF. Under the premise of using low-thread LiDAR sensor to collect data, the semantic segmentation effect of 3D field point cloud is improved as much as possible. It provides theoretical basis for cost saving in practical industrial application. The feature extraction of completion module consists of Graph Aggregation Convolution (GAC) and attention mechanism. Then, we use shuffle transform to upsampling data. In addition, to analyze the effectiveness of the proposed method, we make a new dataset with sparse point cloud data, i.e. Sparse-SemanticKITTI dataset, based on public SemanticKITTI dataset. Furthermore, in experiment part, we prove the research significance. Moreover, we compare the segmentation results between classical methods to the proposed one based on point cloud data in SemanticKITTI, Sparse-SemanticKITTI and Semantic3D dataset, respectively. The effectiveness of the proposed one is obvious. Finally, the model complexity is analyzed. In sum, we provide a sparse point cloud semantic segmentation method to balance the cost and the effect.https://ieeexplore.ieee.org/document/10343142/Point cloud semantic segmentationLidarbilateral augmentation and adaptive fusion (BAAF)point cloud completiongraph aggregation convolution |
| spellingShingle | Tong Zheng Jialun Chen Wenbin Feng Chongchong Yu A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data IEEE Access Point cloud semantic segmentation Lidar bilateral augmentation and adaptive fusion (BAAF) point cloud completion graph aggregation convolution |
| title | A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data |
| title_full | A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data |
| title_fullStr | A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data |
| title_full_unstemmed | A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data |
| title_short | A Graph Aggregation Convolution and Attention Mechanism Based Semantic Segmentation Method for Sparse Lidar Point Cloud Data |
| title_sort | graph aggregation convolution and attention mechanism based semantic segmentation method for sparse lidar point cloud data |
| topic | Point cloud semantic segmentation Lidar bilateral augmentation and adaptive fusion (BAAF) point cloud completion graph aggregation convolution |
| url | https://ieeexplore.ieee.org/document/10343142/ |
| work_keys_str_mv | AT tongzheng agraphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata AT jialunchen agraphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata AT wenbinfeng agraphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata AT chongchongyu agraphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata AT tongzheng graphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata AT jialunchen graphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata AT wenbinfeng graphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata AT chongchongyu graphaggregationconvolutionandattentionmechanismbasedsemanticsegmentationmethodforsparselidarpointclouddata |