Object Detection through Modified YOLO Neural Network

In the field of object detection, recently, tremendous success is achieved, but still it is a very challenging task to detect and identify objects accurately with fast speed. Human beings can detect and recognize multiple objects in images or videos with ease regardless of the object’s appearance, b...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Scientific programming Ročník 2020; číslo 2020; s. 1 - 10
Hlavní autori: Nazir, Shah, Ahmad, Belal, Yahya, Muhammad, Ma, Yinglong, Ahmad, Tanvir, Haq, Amin Ul
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cairo, Egypt Hindawi Publishing Corporation 2020
Hindawi
John Wiley & Sons, Inc
Predmet:
Accuracy
Back propagation
Classification
Computer simulation
Convolution
Deep learning
Image detection
Machine learning
Methods
Neural networks
Object recognition
Researchers
ISSN:1058-9244, 1875-919X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In the field of object detection, recently, tremendous success is achieved, but still it is a very challenging task to detect and identify objects accurately with fast speed. Human beings can detect and recognize multiple objects in images or videos with ease regardless of the object’s appearance, but for computers it is challenging to identify and distinguish between things. In this paper, a modified YOLOv1 based neural network is proposed for object detection. The new neural network model has been improved in the following ways. Firstly, modification is made to the loss function of the YOLOv1 network. The improved model replaces the margin style with proportion style. Compared to the old loss function, the new is more flexible and more reasonable in optimizing the network error. Secondly, a spatial pyramid pooling layer is added; thirdly, an inception model with a convolution kernel of 1 ∗ 1 is added, which reduced the number of weight parameters of the layers. Extensive experiments on Pascal VOC datasets 2007/2012 showed that the proposed method achieved better performance.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1058-9244
1875-919X
DOI:10.1155/2020/8403262