Design and Implementation of a Multi-scale Object Detection Algorithm on TensorFlow

The technology of object detection is a very important subject in computer vision task. It has been widely used in intelligent transportation, face detection, aerospace and medical image equipment. In this paper, a kind of object detection algorithm based on regression and region proposals is studie...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of physics. Conference series Ročník 1576; číslo 1; s. 12031 - 12038
Hlavní autori: Yanbin, Chen, Huai, Wang, Zhuo, Han
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Bristol IOP Publishing 01.06.2020
Predmet:
Accuracy
Algorithms
Computer vision
convolutional neural network
Datasets
deep learning
Face recognition
Feature extraction
Feature maps
Machine learning
Medical equipment
Medical imaging
multi-scale detection
object detection
Object recognition
Physics
Proposals
Regression models
RPN
Training
Two dimensional models
ISSN:1742-6588, 1742-6596
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The technology of object detection is a very important subject in computer vision task. It has been widely used in intelligent transportation, face detection, aerospace and medical image equipment. In this paper, a kind of object detection algorithm based on regression and region proposals is studied. We use a popular deep learning framework-TensorFlow, as the experimental platform. We propose a multi-scale object detection algorithm based on RPN region proposal network, which can extract the features of large and small objects by using the level of feature map. In addition, this paper also improves the classification regression model and proposes a two-dimensional loss function, which makes the region proposals closer to the groundtruth boxes in the final training, which makes the training process of the improved network easier. The experimental data set used in this paper is PASCAL VOC data set, the accuracy and speed of each category in 20 detection objects are calculated and analyzed. A number of experiments have proved that the proposed multi-scale object detection algorithm based on RPN have improved in accuracy and speed. The average detection precision on the PASCAL VOC dataset increased to 74.4%.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1576/1/012031