Multi-feature Fusion VoteNet for 3D Object Detection

Wang, Zhoutao; Xie, Qian; Wei, Mingqiang; Long, Kun; Wang, Jun

doi:10.1145/3462219

Cited by 18 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most importantly, the advantages of the proposed n-sigmoid CSA-VoteNet stems from two significant facts: on the one hand, it assigns different relevance weights to different elements of the input data during the voting process; on the other hand, the attention map enables the network to emphasize important features and suppress irrelevant or noisy ones. COG [34] 2D-driven [35] F-PointNet [36] VoteNet [12] MLCVNet [37] DeMF [38] CSA-VoteNet A-SCN [39] Point-attention [40] CAA [31] Point-transformer [32] Offset-attention [41] CSA A-SCN [39] Point-attention [40] CAA [31] Pointtransformer [32] Offset-attention [41] CSA…”

Section: Methods In Comparisonmentioning

confidence: 99%

An Innovative n-Shifted Sigmoid Channel and Spatial Attention Module for Efficient 3D Scene Object Detection

Du,

Burume,

Liu

2024

Preprint

View full text Add to dashboard Cite

Recently, attention mechanisms have developed into an important tool for performance improvement of deep neural networks. In computer vision, attention mechanisms are generally divided into two main branches: spatial and channel attention. Both attention categories have their own advantages. The fusion of both attentions achieves higher performance, on the cost of the computational load. This paper introduces an innovative and lighter n-shifted sigmoid channel and spatial attention (CSA) module to reduce the computational cost and to improve the 3D scene relevant features selection. To validate the proposed attention module, 3D scene object detection in the deep Hough voting point sets is considered as the testing application. The proposed attention module with its piecewise n-shifted sigmoid activation function improves the network’s learning and generalization capacity which effectively predict bounding box parameters directly from 3D scenes and detect objects more accurately. This advantage is achieved by selectively attending to more relevant features of the input data. When used in the deep Hough voting point sets, the proposed attention module outperforms state-of-the-art 3D detection methods on the sizable SUNRGBD dataset. Experiments conducted showed an increase of 12.02 mean accuracy precision (mAP) when compared to the celebrated VoteNet (without attention). It also got 9.92 mAP higher compared to the MLVCNet, and 10.32 mAP higher than the Point Transformer. The proposed model not only decreases the sigmoid vanishing gradient problem but also brings out valuable features by fusing channel-wise and spatial information while improving accuracy results in 3D object detection.

show abstract

Section: Methods In Comparisonmentioning

confidence: 99%

An Innovative n-Shifted Sigmoid Channel and Spatial Attention Module for Efficient 3D Scene Object Detection

Du,

Burume,

Liu

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The current mainstream solution for autonomous driving is to use Lidar and vision cameras for fusion [3], Lidar (Light Detection And Ranging) which is short for Lidar. The main Lidar ranging principles are: time-offlight (TOF) method [4], laser triangulation [5], and continuous wave frequency modulation (FMCW) [6], which is a noncontact active ranging sensor [7] [8]. Vision cameras can be further divided into monocular cameras, binocular cameras [39], and depth cameras [10].…”

Section: Introductionmentioning

confidence: 99%

LIDAR and camera fusion method based on detection frame overlap

Wu,

Ding

2023

International Conference on Automation Control, Algorithm, and Intelligent Bionics (ACAIB 2023)

View full text Add to dashboard Cite

The target detection by fusion of LiDAR and camera can effectively improve the accuracy of target detection and recognition. The current fusion algorithm mainly stays in feature-level fusion, and the real-time performance is poor to be deployed in mobile, this paper proposes a target-level fusion scheme to fuse the target frames detected by two sensors based on the overlap, and the experiments show that the method can effectively improve the detection rate and classification correct rate.

show abstract

“…The primary goal of three-dimensional (3D) object detection in autonomous driving scenarios is to locate and identify items in road scenes. This task has drawn significant attention from industries 1 , 2 and academia 3 , 4 . Lidar is frequently utilized in the field of autonomous driving and is capable of precisely sensing 3D spatial information.…”

Section: Introductionmentioning

confidence: 99%

“…This task has drawn significant attention from industries 1,2 and academia. 3,4 Lidar is frequently utilized in the field of autonomous driving and is capable of precisely sensing 3D spatial information. Lidar-based 3D object detection has attracted more attention recently as deep learning has advanced.…”

Section: Introductionmentioning

confidence: 99%

Three-dimensional object detection with spatial-semantic features of point clouds

Chen,

Han

2023

J. Electron. Imag.

View full text Add to dashboard Cite

.Three-dimensional (3D) object detection is crucial for accurate recognition of autonomous driving roads, and the distribution of point clouds in 3D scenes becomes sparse with increasing distance, thus seriously affecting the sensor’s perception precision. To address this problem, we propose a two-stage 3D object detection network based on point and voxel feature fusion. In the first stage, a spatial semantic feature fusion module is designed to effectively fuse low-level spatial features and high-level semantic features to generate high-quality proposals. Then, an attention mechanism-based residual module is constructed to expand the receptive field and adaptively aggregate the voxel features in the 3D scene. At the same time, the sampled key points and voxel features are fused to extract the key information in the 3D scene. In the second stage, the graph network pooling module is introduced to construct local graphs on 3D proposals using key point features as nodes to estimate the confidence and location of objects more accurately. Experimental results on the KITTI dataset show that the detection precision is improved significantly in easy, moderate, and hard tasks.

show abstract

Multi-feature Fusion VoteNet for 3D Object Detection

Cited by 18 publications

References 50 publications

An Innovative n-Shifted Sigmoid Channel and Spatial Attention Module for Efficient 3D Scene Object Detection

An Innovative n-Shifted Sigmoid Channel and Spatial Attention Module for Efficient 3D Scene Object Detection

LIDAR and camera fusion method based on detection frame overlap

Three-dimensional object detection with spatial-semantic features of point clouds

Contact Info

Product

Resources

About