Object Detection In Point Clouds Research Articles

POAT-Net: Parallel Offset-Attention Assisted Transformer for 3D Object Detection for Autonomous Driving

3D object detection is playing a key role in the perception process of autonomous driving and industrial robots automation. Inherent characteristics of point cloud raise an enormous challenge to both spatial representation and association analysis. Unordered point cloud spatial data structure and density variations caused by gradually varying distances to LiDAR make accurate and robust 3D object detection even more difficult. In this paper, we present a novel transformer network POAT-Net for 3D point cloud object detection. Transformer is credited with the great success in Natural Language Processing (NLP) and exhibiting inspiring potentials in point cloud processing. Our method POAT-Net is inherently insensitive to element permutations within the unordered point cloud. The associations between local points contribute significantly to 3D object detection or other 3D tasks. Parallel offset-attention is leveraged to highlight and capture subtle associations between local points. To overcome the non-uniform density distribution of different objects, we exploit Normalized multi-resolution Grouping (NMRG) strategy to enhance the non-uniform density adaptive ability for POAT-Net. Quantitative experimental results on KITTI3D dataset demonstrate our method achieves the state-of-the-art performance.

3D point cloud object detection method in view of voxel based on graph convolution network

3D point cloud object detection method in view of voxel based on graph convolution network

Towards a Weakly Supervised Framework for 3D Point Cloud Object Detection and Annotation.

It is quite laborious and costly to manually label LiDAR point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised framework which allows learning 3D detection from a few weakly annotated examples. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under inaccurate and inexact supervision, obtained by our proposed BEV center-click annotation strategy, where only the horizontal object centers are click-annotated in bird's view scenes. Stage-2 learns to predict cuboids and confidence scores in a coarse-to-fine, cascade manner, under incomplete supervision, i.e., only a small portion of object cuboids are precisely annotated. With KITTI dataset, using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves 86-97 percent the performance of current top-leading, fully supervised detectors (which require 3,712 exhaustively annotated scenes with 15,654 instances). More importantly, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, supporting both automatic and active (human-in-the-loop) working modes. The annotations generated by our model can be used to train 3D object detectors, achieving over 95 percent of their original performance (with manually labeled training data). Our experiments also show our model's potential in boosting performance when given more training data. The above designs make our approach highly practical and open-up opportunities for learning 3D detection at reduced annotation cost.

PSANet: Pyramid Splitting and Aggregation Network for 3D Object Detection in Point Cloud.

3D object detection in LiDAR point clouds has been extensively used in autonomous driving, intelligent robotics, and augmented reality. Although the one-stage 3D detector has satisfactory training and inference speed, there are still some performance problems due to insufficient utilization of bird’s eye view (BEV) information. In this paper, a new backbone network is proposed to complete the cross-layer fusion of multi-scale BEV feature maps, which makes full use of various information for detection. Specifically, our proposed backbone network can be divided into a coarse branch and a fine branch. In the coarse branch, we use the pyramidal feature hierarchy (PFH) to generate multi-scale BEV feature maps, which retain the advantages of different levels and serves as the input of the fine branch. In the fine branch, our proposed pyramid splitting and aggregation (PSA) module deeply integrates different levels of multi-scale feature maps, thereby improving the expressive ability of the final features. Extensive experiments on the challenging KITTI-3D benchmark show that our method has better performance in both 3D and BEV object detection compared with some previous state-of-the-art methods. Experimental results with average precision (AP) prove the effectiveness of our network.

TANet: Robust 3D Object Detection from Point Clouds with Triple Attention

In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches. We observe two crucial phenomena: 1) the detection accuracy of the hard objects, e.g., Pedestrians, is unsatisfactory, 2) when adding additional noise points, the performance of existing approaches decreases rapidly. To alleviate these problems, a novel TANet is introduced in this paper, which mainly contains a Triple Attention (TA) module, and a Coarse-to-Fine Regression (CFR) module. By considering the channel-wise, point-wise and voxel-wise attention jointly, the TA module enhances the crucial information of the target while suppresses the unstable cloud points. Besides, the novel stacked TA further exploits the multi-level feature attention. In addition, the CFR module boosts the accuracy of localization without excessive computation cost. Experimental results on the validation set of KITTI dataset demonstrate that, in the challenging noisy cases, i.e., adding additional random noisy points around each object, the presented approach goes far beyond state-of-the-art approaches. Furthermore, for the 3D object detection task of the KITTI benchmark, our approach ranks the first place on Pedestrian class, by using the point clouds as the only input. The running speed is around 29 frames per second.

Three-Dimensional Point Cloud Object Detection Using Scene Appearance Consistency Among Multi-View Projection Directions

Three-dimensional (3D) object detection in point clouds is an important technique for various high-level computer vision tasks. In this study, we propose a method for point-wise detection of regions of objects in a scene. We regard the 3D object detection problem as a series of optimal matching problems between object and scene images, which are obtained by projecting point clouds into multiple viewpoints. The main novelty of this study is treating the 3D object detection problem as the determination of optimal correspondence among image sets. Unlike the existing methods that directly employ individual correspondences between projected image pairs, the simultaneous matching of projected image sets allows the evaluation of the appearance consistency of the target object in multi-viewpoint scene images. The other novelty of the proposed method is using principal component analysis to estimate effective image-projection directions for object point clouds. By projecting object point clouds in directions orthogonal to the first principal component basis, the projected images can include plenty of point clouds information, thus providing highly discriminative features for image matching. We back-project reliable matching results retrieved from the image-set correspondence into 3D space to achieve point-wise object detection. Experiments using public datasets demonstrate the effectiveness and performance of the proposed method.

3-D Point Cloud Object Detection Based on Supervoxel Neighborhood With Hough Forest Framework

Object detection in three-dimensional (3-D) laser scanning point clouds of complex urban environment is a challenging problem. Existing methods are limited by their robustness to complex situations such as occlusion, overlap, and rotation or by their computational efficiency. This paper proposes a high computationally efficient method integrating supervoxel with Hough forest framework for detecting objects from 3-D laser scanning point clouds. First, a point cloud is over-segmented into spatially consistent supervoxels. Each supervoxel together with its first-order neighborhood is grouped into one local patch. All the local patches are described by both structure and reflectance features, and then used in the training stage for learning a random forest classifier as well as the detection stage to vote for the possible location of the object center. Second, local reference frame and circular voting strategies are introduced to achieve the invariance to the azimuth rotation of objects. Finally, objects are detected at the peak points in 3-D Hough voting space. The performance of our proposed method is evaluated on real-world point cloud data collected by the up-to-date mobile laser scanning system. Experimental results demonstrate that our proposed method outperforms state-of-the-art 3-D object detection methods with high computational efficiency.