Open AccessDesign and Implementation of a Multi-scale Object Detection Algorithm on TensorFlow
Author(s) -
Yanbin Chen,
Wenxin Huai,
Han Zhao
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1576/1/012031
Subject(s) - pascal (unit) , computer science , object detection , artificial intelligence , scale (ratio) , algorithm , object (grammar) , object class detection , artificial neural network , process (computing) , pattern recognition (psychology) , data mining , machine learning , computer vision , face detection , facial recognition system , quantum mechanics , programming language , physics , operating system
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%.