Voting for Voting in Online Point Cloud Object Detection

@inproceedings{Wang2015VotingFV,
  title={Voting for Voting in Online Point Cloud Object Detection},
  author={Dominic Zeng Wang and Ingmar Posner},
  booktitle={Robotics: Science and Systems},
  year={2015}
}
This paper proposes an efficient and effective scheme to applying the sliding window approach popular in computer vision to 3D data. [...] Key Result For the object classes car, pedestrian and bicyclist the resulting detector achieves best-in-class detection and timing performance relative to prior art on the KITTI dataset as well as compared to another existing 3D object detection approach.Expand
SPOT: Selective Point Cloud Voting for Better Proposal in Point Cloud Object Detection
TLDR
Baselines enhanced by the Selective Point clOud voTing module can stably improve results in agreement by a large margin and achieve new stateor-the-art detection, especially under more strict evaluation metric that adopts larger IoU threshold, implying the module is the key leading to high-quality object detection in point clouds. Expand
3D Object Detection Using Scale Invariant and Feature Reweighting Networks
TLDR
A new network architecture which focuses on utilizing the front view images and frustum point clouds to generate 3D detection results and achieves better performance than the state-of-the-art methods especially when point clouds are highly sparse. Expand
Density-Based Clustering for 3D Object Detection in Point Clouds
TLDR
This work introduces a novel approach for 3D object detection that is significant in two main aspects: a cascaded modular approach that focuses the receptive field of each module on specific points in the point cloud, for improved feature learning and a class agnostic instance segmentation module that is initiated using unsupervised clustering. Expand
Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks
TLDR
This paper proposes a computationally efficient approach to detecting objects natively in 3D point clouds using convolutional neural networks (CNNs) by leveraging a feature-centric voting scheme to implement novel convolutionan layers which explicitly exploit the sparsity encountered in the input. Expand
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. Expand
EPN: Edge-Aware PointNet for Object Recognition from Multi-View 2.5D Point Clouds
TLDR
A novel architecture coined as Edge-Aware PointNet, that incorporates geometric shape priors as binary maps, integrated in parallel with the PointNet++ framework, through convolutional neural networks (CNNs). Expand
3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection
TLDR
This paper employs a convolutional neural net that exploits context and depth information to jointly regress to 3D bounding box coordinates and object pose and outperforms all existing results in object detection and orientation estimation tasks for all three KITTI object classes. Expand
Recognition of Point Sets Objects in Realistic Scenes
TLDR
The experimental results show that the network structure in this paper can accurately identify and classify point cloud objects in realistic scenes and maintain a certain accuracy when the number of point clouds is small, which is very robust. Expand
PIXOR: Real-time 3D Object Detection from Point Clouds
TLDR
PIXOR is proposed, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions that surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at 10 FPS. Expand
SCNet: Subdivision Coding Network for Object Detection Based on 3D Point Cloud
TLDR
A more efficient representation of 3D point clouds is proposed and SCNet, a single-stage, end-to-end 3D subdivision coding network that learns finer feature representations for vertical grids is proposed. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
Towards 3D object recognition via classification of arbitrary object tracks
TLDR
This paper presents a new track classification method, based on a mathematically principled method of combining log odds estimators, that is fast enough for real time use, is non-specific to object class, and performs well on the task of classifying correctly-tracked, well-segmented objects into car, pedestrian, bicyclist, and background classes. Expand
Sliding Shapes for 3D Object Detection in Depth Images
TLDR
This paper proposes to use depth maps for object detection and design a 3D detector to overcome the major difficulties for recognition, namely the variations of texture, illumination, shape, viewpoint, clutter, occlusion, self-occlusion and sensor noises. Expand
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection
TLDR
This paper addresses the task of efficient object class detection by means of the Hough transform by demonstrating PRISM’s flexibility by two complementary implementations: a generatively trained Gaussian Mixture Model as well as a discriminatively trained histogram approach. Expand
Sparse distance learning for object recognition combining RGB and depth information
TLDR
This work defines a view-to-object distance where a novel view is compared simultaneously to all views of a previous object, and shows that this measure leads to superior classification performance on object category and instance recognition. Expand
What could move? Finding cars, pedestrians and bicyclists in 3D laser data
TLDR
The aim is to provide the layout of an end-to-end pipeline which, when fed by a raw stream of 3D data, produces distinct groups of points which can be fed to downstream classifiers for categorisation. Expand
3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model
TLDR
This paper proposes a novel approach that extends the well-acclaimed deformable part-based model to reason in 3D, and represents an object class as a deformable 3D cuboid composed of faces and parts, which are both allowed to deform with respect to their anchors on the 3D box. Expand
Pedestrian detection combining RGB and dense LIDAR data
TLDR
A state-of-the-art deformable parts detector is trained using different configurations of optical images and their associated 3D point clouds, in conjunction and independently, leveraging upon the recently released KITTI dataset to propose novel strategies for depth upsampling and contextual fusion that together lead to detection performance which exceeds that of the RGB-only systems. Expand
Vision meets robotics: The KITTI dataset
TLDR
A novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research, using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras and a high-precision GPS/IMU inertial navigation system. Expand
Object Detection with Discriminatively Trained Part Based Models
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results inExpand
Histograms of oriented gradients for human detection
  • N. Dalal, B. Triggs
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied. Expand
...
1
2
3
...