MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion

Zhang, Zehan; Shen, Yuxi; Li, Hao; Zhao, Xian; Yang, Meifeng; Wang, Tan; Pu, ShiLiang; Mao, Hui

doi:10.1109/itsc55140.2022.9922104

Cited by 12 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the effectiveness of our APIDFF-Net, we compared it against 12 state-of-the-art methods, including SECOND [39], F-Convnet [36], PointPillars [14], PointR-CNN [29], TANet [19], Associate-3D [7], PI-RCNN [37], MAFF [44], PointPainting [33], CLOCs [23], 3D-CVF [42], RangeRCNN [16], HVPR [21], VoxelNet [48], F-PointPillars [22] and MLF [45]. By comparing our method with these existing approaches, we can better understand the strengths and limitations of our approach.…”

Section: Evaluation Metric and Comparative Methodsmentioning

confidence: 99%

Adaptive learning point cloud and image diversity feature fusion network for 3D object detection

Yan,

Liu,

Liu

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

Abstract3D object detection is a critical task in the fields of virtual reality and autonomous driving. Given that each sensor has its own strengths and limitations, multi-sensor-based 3D object detection has gained popularity. However, most existing methods extract high-level image semantic features and fuse them with point cloud features, focusing solely on consistent information from both sensors while ignoring their complementary information. In this paper, we present a novel two-stage multi-sensor deep neural network, called the adaptive learning point cloud and image diversity feature fusion network (APIDFF-Net), for 3D object detection. Our approach employs the fine-grained image information to complement the point cloud information by combining low-level image features with high-level point cloud features. Specifically, we design a shallow image feature extraction module to learn fine-grained information from images, instead of relying on deep layer features with coarse-grained information. Furthermore, we design a diversity feature fusion (DFF) module that transforms low-level image features into point-wise image features and explores their complementary features through an attention mechanism, ensuring an effective combination of fine-grained image features and point cloud features. Experiments on the KITTI benchmark show that the proposed method outperforms state-of-the-art methods.

show abstract

Section: Evaluation Metric and Comparative Methodsmentioning

confidence: 99%

Adaptive learning point cloud and image diversity feature fusion network for 3D object detection

Yan,

Liu,

Liu

et al. 2023

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…The advantages of multi-perspective point cloud segmentation [18][19][20] are primarily manifested in its ability to provide a more comprehensive spatial understanding than a single perspective. In multi-perspective point cloud segmentation, data from different angles are fused to form more complete three-dimensional representations of target objects or environments.…”

Section: Multi-perspective Fusionmentioning

confidence: 99%

PVI-Net: Point–Voxel–Image Fusion for Semantic Segmentation of Point Clouds in Large-Scale Autonomous Driving Scenarios

Wang,

Li,

et al. 2024

Information

View full text Add to dashboard Cite

In this study, we introduce a novel framework for the semantic segmentation of point clouds in autonomous driving scenarios, termed PVI-Net. This framework uniquely integrates three different data perspectives—point clouds, voxels, and distance maps—executing feature extraction through three parallel branches. Throughout this process, we ingeniously design a point cloud–voxel cross-attention mechanism and a multi-perspective feature fusion strategy for point images. These strategies facilitate information interaction across different feature dimensions of perspectives, thereby optimizing the fusion of information from various viewpoints and significantly enhancing the overall performance of the model. The network employs a U-Net structure and residual connections, effectively merging and encoding information to improve the precision and efficiency of semantic segmentation. We validated the performance of PVI-Net on the SemanticKITTI and nuScenes datasets. The results demonstrate that PVI-Net surpasses most of the previous methods in various performance metrics.

show abstract

“…According to their results, their objective was attained and the method achieved up to 9.87% better class-wise performance than the LiDAR-only detector. In [27], two end-to-end trainable feature fusion techniques were proposed to combine RGB and point-cloud features. Their experiments showed that their methods can improve significantly the filtering of false positive from data.…”

Section: Related Workmentioning

confidence: 99%

Reducing Overconfidence Predictions in Autonomous Driving Perception

Melotti,

Premebida,

Bird

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Object recognition is a crucial step in perception systems for autonomous and intelligent vehicles, as evidenced by the numerous research works in the topic. In this paper, object recognition is explored by using multisensory and multimodality approaches, with the intention of reducing the false positive rate (FPR). The reduction of the FPR becomes increasingly important in perception systems since the misclassification of an object can, depending on the circumstances, potentially cause accidents. In particular, this work presents a strategy through Bayesian inference to reduce the FPR considering the likelihood function as a cumulative distribution function from Gaussian kernel density estimations, and the prior probabilities as cumulative functions of normalized histograms. The validation of the proposed methodology is performed on the KITTI dataset using deep networks (DenseNet, NasNet, and EfficientNet), and recent 3D point cloud networks (PointNet, and PointNet++), by considering three object-categories (cars, cyclists, pedestrians) and the RGB and LiDAR sensor modalities.

show abstract

MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion

Cited by 12 publications

References 38 publications

Adaptive learning point cloud and image diversity feature fusion network for 3D object detection

Adaptive learning point cloud and image diversity feature fusion network for 3D object detection

PVI-Net: Point–Voxel–Image Fusion for Semantic Segmentation of Point Clouds in Large-Scale Autonomous Driving Scenarios

Reducing Overconfidence Predictions in Autonomous Driving Perception

Contact Info

Product

Resources

About