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.
Keywords
Point cloudLidarComputer scienceArtificial intelligenceInferenceOrientation (vector space)Convolution (computer science)RangingConvolutional neural networkObject detectionComputer visionRGB color modelConvergence (economics)Pattern recognition (psychology)Remote sensingArtificial neural networkMathematics
Affiliated Institutions
Related Publications
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To...
A general framework for object detection
This paper presents a general trainable framework for object detection in static images of cluttered scenes. The detection technique we develop is based on a wavelet representat...
Natural Feature Detection on Mobile Phones with 3D FAST
In this paper, we present a novel feature detection approach designed for mobile devices, showing optimized solutions for both detection and description. It is based on FAST (Fe...
Spatial Priors for Part-Based Recognition Using Statistical Models
We present a class of statistical models for part-based object recognition that are explicitly parameterized according to the degree of spatial structure they can represent. The...
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
Regional dropout strategies have been proposed to enhance performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to atte...
Publication Info
- Year
- 2018
- Type
- article
- Volume
- 18
- Issue
- 10
- Pages
- 3337-3337
- Citations
- 2910
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
2910
OpenAlex
Cite This
Yan Yan,
Yuxing Mao,
Bo Li
(2018).
SECOND: Sparsely Embedded Convolutional Detection.
Sensors
, 18
(10)
, 3337-3337.
https://doi.org/10.3390/s18103337
Identifiers
- DOI
- 10.3390/s18103337