Smart City Gnosys
Smart city article details
| Title | Dfa-Sat: Dynamic Feature Abstraction With Self-Attention-Based 3D Object Detection For Autonomous Driving |
|---|---|
| ID_Doc | 19852 |
| Authors | Mushtaq H.; Deng X.; Ali M.; Hayat B.; Raza Sherazi H.H. |
| Year | 2023 |
| Published | Sustainability (Switzerland), 15, 18 |
| DOI | http://dx.doi.org/10.3390/su151813667 |
| Abstract | Autonomous vehicles (AVs) play a crucial role in enhancing urban mobility within the context of a smarter and more connected urban environment. Three-dimensional object detection in AVs is an essential task for comprehending the driving environment to contribute to their safe use in urban environments. Existing 3D LiDAR object detection systems lose many critical point features during the down-sampling process and neglect the crucial interactions between local features, providing insufficient semantic information and leading to subpar detection performance. We propose a dynamic feature abstraction with self-attention (DFA-SAT), which utilizes self-attention to learn semantic features with contextual information by incorporating neighboring data and focusing on vital geometric details. DFA-SAT comprises four modules: object-based down-sampling (OBDS), semantic and contextual feature extraction (SCFE), multi-level feature re-weighting (MLFR), and local and global features aggregation (LGFA). The OBDS module preserves the maximum number of semantic foreground points along with their spatial information. SCFE learns rich semantic and contextual information with respect to spatial dependencies, refining the point features. MLFR decodes all the point features using a channel-wise multi-layered transformer approach. LGFA combines local features with decoding weights for global features using matrix product keys and query embeddings to learn spatial information across each channel. Extensive experiments using the KITTI dataset demonstrate significant improvements over the mainstream methods SECOND and PointPillars, improving the mean average precision (AP) by 6.86% and 6.43%, respectively, on the KITTI test dataset. DFA-SAT yields better and more stable performance for medium and long distances with a limited impact on real-time performance and model parameters, ensuring a transformative shift akin to when automobiles replaced conventional transportation in cities. © 2023 by the authors. |
| Author Keywords | 3D object dejection; self-attention; semantic features leaning; smart cities |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
13435  | 0.872 | Wu H.; Deng J.; Wen C.; Li X.; Wang C.; Li J. | Casa: A Cascade Attention Network For 3-D Object Detection From Lidar Point Clouds | IEEE Transactions on Geoscience and Remote Sensing, 60 (2022) |
| 19752 | 0.864 | Abd Elhamied E.M.; Youssef S.M. | Development Of Smart 3D Object Detection Using Lidar Cloud-Data Collection | Journal of Physics: Conference Series, 2128, 1 (2021) |
| 38523 | 0.852 | Thayalan S.; Muthukumarasamy S. | Multifocus Object Detector For Vehicle Tracking In Smart Cities Using Spatiotemporal Attention Map | Journal of Applied Remote Sensing, 17, 1 (2023) |
| 43636 | 0.852 | Yi H.; Liu Y.; Wang M. | Psnet: Patch-Based Self-Attention Network For 3D Point Cloud Semantic Segmentation | Remote Sensing, 17, 12 (2025) |
| 17074 | 0.851 | Zaboli M.; Rastiveis H.; Hosseiny B.; Shokri D.; Sarasua W.A.; Homayouni S. | D-Net: A Density-Based Convolutional Neural Network For Mobile Lidar Point Clouds Classification In Urban Areas | Remote Sensing, 15, 9 (2023) |