SECOND: Sparsely Embedded Convolutional Detection
Yan Yan,Yuxing Mao,Bo Li +2 more
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.Abstract:
LiDAR-based or RGB-D-based object detection is used in numerous applications, ranging from autonomous driving to robot vision. Voxel-based 3D convolutional networks have been used for some time to enhance the retention of information when processing point cloud LiDAR data. However, problems remain, including a slow inference speed and low orientation estimation performance. We therefore investigate an improved sparse convolution method for such networks, which significantly increases the speed of both training and inference. We also introduce a new form of angle loss regression to improve the orientation estimation performance and a new data augmentation approach that can enhance the convergence speed and performance. The proposed network produces state-of-the-art results on the KITTI 3D object detection benchmarks while maintaining a fast inference speed.read more
Citations
More filters
Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector
Р Ю Чуйков,Д А Юдин +1 more
Posted Content
PointPillars: Fast Encoders for Object Detection from Point Clouds
TL;DR: PointPillars as mentioned in this paper utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars), which can be used with any standard 2D convolutional detection architecture.
Proceedings ArticleDOI
PointPillars: Fast Encoders for Object Detection From Point Clouds
TL;DR: benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds, and proposes a lean downstream network.
Posted Content
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
TL;DR: 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.
Journal ArticleDOI
Deep Learning for 3D Point Clouds: A Survey
TL;DR: This paper presents a comprehensive review of recent progress in deep learning methods for point clouds, covering three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation.
References
More filters
Proceedings ArticleDOI
You Only Look Once: Unified, Real-Time Object Detection
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Posted Content
Fast R-CNN
TL;DR: This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection that builds on previous work to efficiently classify object proposals using deep convolutional networks.
Posted Content
Rich feature hierarchies for accurate object detection and semantic segmentation
TL;DR: This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Book ChapterDOI
SSD: Single Shot MultiBox Detector
Wei Liu,Dragomir Anguelov,Dumitru Erhan,Christian Szegedy,Scott Reed,Cheng-Yang Fu,Alexander C. Berg +6 more
TL;DR: SSD as mentioned in this paper discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, and combines predictions from multiple feature maps with different resolutions to naturally handle objects of various sizes.
Proceedings Article
Mask R-CNN
TL;DR: This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners.