2020
DOI: 10.3390/s21010136
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: 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. Specific… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
13
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 16 publications
(13 citation statements)
references
References 32 publications
0
13
0
Order By: Relevance
“…The CSP network structure reduces the amount of model calculation while maintaining accuracy. The activation function in CSPDarknet53 is the Mish activation function, as given by Equation (7).…”
Section: Traffic Cone Detection With Colour Imagesmentioning
confidence: 99%
See 1 more Smart Citation
“…The CSP network structure reduces the amount of model calculation while maintaining accuracy. The activation function in CSPDarknet53 is the Mish activation function, as given by Equation (7).…”
Section: Traffic Cone Detection With Colour Imagesmentioning
confidence: 99%
“…Long-range detection sensors, like LiDAR etc., can accurately measure 3D positions throughout the whole day, but object detection based on LiDAR point clouds is challenging. Due to the sparse reflection detection, point clouds lose the colour and whole outline features of objects, and they cannot sufficiently detect small targets at long distances [7]. However, as a cost-effective solution, machine vision technology can solve these issues because images provide rich colour and texture information.…”
Section: Introductionmentioning
confidence: 99%
“…Since LiDAR sensors function well even in adverse lighting conditions, they are crucial to many applications. In these applications, 3D object detection is an important task [ 22 , 23 , 24 , 25 , 26 ]. However, for those objects without spatial volumes, such as road signs on the ground, they cannot be detected using the point cloud data.…”
Section: Related Workmentioning
confidence: 99%
“…Since then, there have been some improved methods for small-target detection in the field of deep learning, such as multiscale fusion, scale invariance, and so on. Feature Pyramid Networks (FPNs) [16,17] use low-level location information with high-level semantic information by propagating the high-level features down. e problem of small-target detection results in part from deep learning target detection algorithms only using top-level feature mapping for classification and prediction and ignoring the location information of low-level features.…”
Section: Introductionmentioning
confidence: 99%