Multiclass objects detection algorithm using DarkNet-53 and DenseNet for intelligent vehicles

Intelligent vehicles should not only be able to detect various obstacles, but also identify their categories so as to take an appropriate protection and intervention. However, the scenarios of object detection are usually complex and changeable, so how to balance the relationship between accuracy an...

Full description

Saved in:
Bibliographic Details
Published inEURASIP journal on advances in signal processing Vol. 2023; no. 1; pp. 85 - 18
Main Authors Yang, Lina, Chen, Gang, Ci, Wenyan
Format Journal Article
LanguageEnglish
Published Cham Springer International Publishing 01.08.2023
Springer
Springer Nature B.V
SpringerOpen
Subjects
Algorithms
Analysis
Convolution
DarkNet-53
DenseNet
Downsampling layers
Engineering
Information flow
Information management
Intelligent vehicles
Loss function
Multiclass objects detection
Multilayers
Object recognition
Occlusion
Quantum Information Technology
Signal,Image and Speech Processing
Spintronics
DenseNet
Loss function
Downsampling layers
DarkNet-53
Multiclass objects detection
Online AccessGet full text

Cover

More Information
Summary:Intelligent vehicles should not only be able to detect various obstacles, but also identify their categories so as to take an appropriate protection and intervention. However, the scenarios of object detection are usually complex and changeable, so how to balance the relationship between accuracy and speed is a difficult task of object detection. This paper proposes a multi-object detection algorithm using DarkNet-53 and dense convolution network (DenseNet) to further ensure maximum information flow between layers. Three 8-layer dense blocks are used to replace the last three downsampling layers in DarkNet-53 structure, so that the network can make full use of multi-layer convolution features before prediction. The loss function of coordinate prediction error in YOLOv3 is further improved to improve the detection accuracy. Extensive experiments are conducted on the public KITTI and Pascal VOC datasets, and the results demonstrate that the proposed algorithm has better robustness, and the network model is more suitable for the traffic scene in the real driving environment and has better adaptability to the objects with long distance, small size and partial occlusion.
ISSN:1687-6180
1687-6172
1687-6180
DOI:10.1186/s13634-023-01045-8