Dihang Deng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dihang Deng has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Fan Ren
Changan Software Technology Company, Changan Automobile Corp, Chongqing, China
1 shared publication - Guangxia Yang
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China
1 shared publication - Panliang Tang
School of Integrated Circuit Science and Engineering, University of Electronic Science and Technology of China, No. 2006, Xiyuan Avenu, West Hi-Tech Zone, Chengdu 611731, China
1 shared publication - Yuanhong Zhong
Chongqing University
1 shared publication
Latest Publications
- Open Access
- 28 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 15 (5) , 1-8
Mask-SL RCNN: Feature-Enhanced 3D Object Detection Network for Point Clouds
At present, with the original point cloud as input, most of the object detectors use Pointnet++ to extract features of the point cloud based on the Farthest Point Sampling (FPS). However, affected by FPS, feature extraction is incomplete and unstable. Moreover, high-level semantic features lack the internal vertex properties of Regions of Interest (RoI). In order to solve the above problems, we propose the MaskSL RCNN (Mask-Spherical-neighborhood-global-feature-Layer Region-CNN), a feature-enhanced 3D object detection network. It improves sampling of the farthest point through point-level feature enhancement. In addition, we propose Spherical neighborhood global feature Layer (SL) to supplement the global features and improve the learning ability of network. At last, based on semantic-level feature enhancement, we design grid pooling layer based on vertex attention, which fully explores the boundary characteristics of RoI and increases ability to learn advanced features in RoI. Our network improves detection precision of small objects such as pedestrians. Compared with PointRCNN, it has improved the mAP of simple, medium, and difficult object detection in the KITTI dataset by 2.66%, 1.69%, and 0.67%, respectively.
- 28 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 15 (5) , 1-8
Open AccessMask-SL RCNN: Feature-Enhanced 3D Object Detection Network for Point Clouds
At present, with the original point cloud as input, most of the object detectors use Pointnet++ to extract features of the point cloud based on the Farthest Point Sampling (FPS). However, affected by FPS, feature extraction is incomplete and unstable. Moreover, high-level semantic features lack the internal vertex properties of Regions of Interest (RoI). In order to solve the above problems, we propose the MaskSL RCNN (Mask-Spherical-neighborhood-global-feature-Layer Region-CNN), a feature-enhanced 3D object detection network. It improves sampling of the farthest point through point-level feature enhancement. In addition, we propose Spherical neighborhood global feature Layer (SL) to supplement the global features and improve the learning ability of network. At last, based on semantic-level feature enhancement, we design grid pooling layer based on vertex attention, which fully explores the boundary characteristics of RoI and increases ability to learn advanced features in RoI. Our network improves detection precision of small objects such as pedestrians. Compared with PointRCNN, it has improved the mAP of simple, medium, and difficult object detection in the KITTI dataset by 2.66%, 1.69%, and 0.67%, respectively.