3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation
In autonomous driving, LiDAR (light detection and ranging) data are acquired over time. Most existing 3D object detection algorithms propose the object bounding box by processing each frame of data independently, which ignores the temporal sequence information. However, the temporal sequence informa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/12/2986 |
| _version_ | 1797592818245435392 |
|---|---|
| author | Guangda Xie Yang Li Yanping Wang Ziyi Li Hongquan Qu |
| author_facet | Guangda Xie Yang Li Yanping Wang Ziyi Li Hongquan Qu |
| author_sort | Guangda Xie |
| collection | DOAJ |
| description | In autonomous driving, LiDAR (light detection and ranging) data are acquired over time. Most existing 3D object detection algorithms propose the object bounding box by processing each frame of data independently, which ignores the temporal sequence information. However, the temporal sequence information is usually helpful to detect the object with missing shape information due to long distance or occlusion. To address this problem, we propose a temporal sequence information fusion 3D point cloud object detection algorithm based on the Ada-GRU (adaptive gated recurrent unit). In this method, the feature of each frame for the LiDAR point cloud is extracted through the backbone network and is fed to the Ada-GRU together with the hidden features of the previous frames. Compared to the traditional GRU, the Ada-GRU can adjust the gating mechanism adaptively during the training process by introducing the adaptive activation function. The Ada-GRU outputs the temporal sequence fusion features to predict the 3D object in the current frame and transmits the hidden features of the current frame to the next frame. At the same time, the label uncertainty of the distant and occluded objects affects the training effect of the model. For this problem, this paper proposes a probability distribution model of 3D bounding box coordinates based on the Gaussian distribution function and designs the corresponding bounding box loss function to enable the model to learn and estimate the uncertainty of the positioning of the bounding box coordinates, so as to remove the bounding box with large positioning uncertainty in the post-processing stage to reduce the false positive rate. Finally, the experiments show that the methods proposed in this paper improve the accuracy of the object detection without significantly increasing the complexity of the algorithm. |
| first_indexed | 2024-03-11T01:59:29Z |
| format | Article |
| id | doaj.art-f7b0df136aea4d1baa1b32adf1a463c4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T01:59:29Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f7b0df136aea4d1baa1b32adf1a463c42023-11-18T12:24:43ZengMDPI AGRemote Sensing2072-42922023-06-011512298610.3390/rs151229863D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty EstimationGuangda Xie0Yang Li1Yanping Wang2Ziyi Li3Hongquan Qu4College of Electrical and Control Engineering, North China University of Technology, Beijing 100144, ChinaCollege of Information, North China University of Technology, Beijing 100144, ChinaCollege of Information, North China University of Technology, Beijing 100144, ChinaCollege of Electrical and Control Engineering, North China University of Technology, Beijing 100144, ChinaCollege of Information, North China University of Technology, Beijing 100144, ChinaIn autonomous driving, LiDAR (light detection and ranging) data are acquired over time. Most existing 3D object detection algorithms propose the object bounding box by processing each frame of data independently, which ignores the temporal sequence information. However, the temporal sequence information is usually helpful to detect the object with missing shape information due to long distance or occlusion. To address this problem, we propose a temporal sequence information fusion 3D point cloud object detection algorithm based on the Ada-GRU (adaptive gated recurrent unit). In this method, the feature of each frame for the LiDAR point cloud is extracted through the backbone network and is fed to the Ada-GRU together with the hidden features of the previous frames. Compared to the traditional GRU, the Ada-GRU can adjust the gating mechanism adaptively during the training process by introducing the adaptive activation function. The Ada-GRU outputs the temporal sequence fusion features to predict the 3D object in the current frame and transmits the hidden features of the current frame to the next frame. At the same time, the label uncertainty of the distant and occluded objects affects the training effect of the model. For this problem, this paper proposes a probability distribution model of 3D bounding box coordinates based on the Gaussian distribution function and designs the corresponding bounding box loss function to enable the model to learn and estimate the uncertainty of the positioning of the bounding box coordinates, so as to remove the bounding box with large positioning uncertainty in the post-processing stage to reduce the false positive rate. Finally, the experiments show that the methods proposed in this paper improve the accuracy of the object detection without significantly increasing the complexity of the algorithm.https://www.mdpi.com/2072-4292/15/12/2986point cloud3D object detectionGRUpositioning uncertainty |
| spellingShingle | Guangda Xie Yang Li Yanping Wang Ziyi Li Hongquan Qu 3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation Remote Sensing point cloud 3D object detection GRU positioning uncertainty |
| title | 3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation |
| title_full | 3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation |
| title_fullStr | 3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation |
| title_full_unstemmed | 3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation |
| title_short | 3D Point Cloud Object Detection Algorithm Based on Temporal Information Fusion and Uncertainty Estimation |
| title_sort | 3d point cloud object detection algorithm based on temporal information fusion and uncertainty estimation |
| topic | point cloud 3D object detection GRU positioning uncertainty |
| url | https://www.mdpi.com/2072-4292/15/12/2986 |
| work_keys_str_mv | AT guangdaxie 3dpointcloudobjectdetectionalgorithmbasedontemporalinformationfusionanduncertaintyestimation AT yangli 3dpointcloudobjectdetectionalgorithmbasedontemporalinformationfusionanduncertaintyestimation AT yanpingwang 3dpointcloudobjectdetectionalgorithmbasedontemporalinformationfusionanduncertaintyestimation AT ziyili 3dpointcloudobjectdetectionalgorithmbasedontemporalinformationfusionanduncertaintyestimation AT hongquanqu 3dpointcloudobjectdetectionalgorithmbasedontemporalinformationfusionanduncertaintyestimation |