InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

@article{Wang2020InfoFocus3O,
  title={InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling},
  author={Jun Wang and Shiyi Lan and Mingfei Gao and Larry S. Davis},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.08556}
}
Real-time 3D object detection is crucial for autonomous cars. Achieving promising performance with high efficiency, voxel-based approaches have received considerable attention. However, previous methods model the input space with features extracted from equally divided sub-regions without considering that point cloud is generally non-uniformly distributed over the space. To address this issue, we propose a novel 3D object detection framework with dynamic information modeling. The proposed… 
AGO-Net: Association-Guided 3D Point Cloud Object Detection Network.
  • Liang Du, Xiaoqing Ye, +5 authors Jianfeng Feng
  • Medicine
    IEEE transactions on pattern analysis and machine intelligence
  • 2021
TLDR
This work proposes a novel 3D detection framework that associates intact features for objects via domain adaptation through an attention-based re-weighting module that adaptively strengthens the feature adaptation of more informative regions and achieves new state-of-the-art performance on the KITTI3D detection benchmark in both accuracy and speed.
RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation
TLDR
Range-Aware Attention Network (RAANet), which extracts more powerful BEV features and generates superior 3D object detections, and proposes a novel auxiliary loss for density estimation to further enhance the detection accuracy of RAANet for occluded objects.
M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
TLDR
M3DETR is the first approach that unifies multiple point cloud representations, feature scales, as well as models mutual relationships between point clouds simultaneously using transformers, achieving state-of-the-art performance on the KITTI 3D object detection dataset and Waymo Open Dataset.
Design of robust deep learning-based object detection and classification model for autonomous driving applications
Recently, autonomous driving systems have become hot research which allows the drivers in making decisions to enhance safety, decrease traffic accidents, and move nearer toward completely autonomous
Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds.
  • Junbo Yin, Jianbing Shen, Xin Gao, David J. Crandall, Ruigang Yang
  • Medicine
    IEEE transactions on pattern analysis and machine intelligence
  • 2021
TLDR
This paper proposes an Attentive Spatiotemporal Transformer GRU (AST-GRU), which contains a Spatial Transformer Attention (STA) module and a Temporal Trans transformer Attention (TTA) module that enhances the vanilla GRU to focus on small objects and better align the moving objects.
SRDAN: Scale-aware and Range-aware Domain Adaptation Network for Cross-dataset 3D Object Detection
TLDR
This work proposes a new cross-dataset 3D object detection method named Scale-aware and Range-aware Domain Adaptation Network (SRDAN), and takes advantage of the geometric characteristics of 3D data and proposes the scale-aware domain alignment and the range-awaredomain alignment strategies to guide the distribution alignment between two domains.
CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection
  • Ramin Nabati, H. Qi
  • Computer Science
    2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2021
TLDR
This paper proposes a middle-fusion approach to exploit both radar and camera data for 3D object detection and solves the key data association problem using a novel frustum-based method.

References

SHOWING 1-10 OF 34 REFERENCES
Multi-view 3D Object Detection Network for Autonomous Driving
TLDR
This paper proposes Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes and designs a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths.
Joint 3D Proposal Generation and Object Detection from View Aggregation
TLDR
This work presents AVOD, an Aggregate View Object Detection network for autonomous driving scenarios that uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal network (RPN) and a second stage detector network.
SARPNET: Shape attention regional proposal network for liDAR-based 3D object detection
TLDR
A novel 3D object detection network called SARPNET is introduced, which deploys a new low-level feature encoder to remedy the sparsity and inhomogeneity of LiDAR point clouds with an even sample method, and embodies a shape attention mechanism that learns the statistic 3D shape priors of objects and uses them to spatially enhance semantic embeddings.
STD: Sparse-to-Dense 3D Object Detector for Point Cloud
TLDR
This work proposes a two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD), and implements a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance.
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
TLDR
Extensive experiments on the 3D detection benchmark of KITTI dataset show that the proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input.
PointPillars: Fast Encoders for Object Detection From Point Clouds
TLDR
benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds, and proposes a lean downstream network.
SECOND: Sparsely Embedded Convolutional Detection
TLDR
An improved sparse convolution method for Voxel-based 3D convolutional networks is investigated, which significantly increases the speed of both training and inference and introduces a new form of angle loss regression to improve the orientation estimation performance.
Frustum PointNets for 3D Object Detection from RGB-D Data
TLDR
This work directly operates on raw point clouds by popping up RGBD scans and leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects.
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
  • Yin Zhou, Oncel Tuzel
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists.
nuScenes: A Multimodal Dataset for Autonomous Driving
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object
...
1
2
3
4
...