Visual tracking based on convolutional neural network

被引：0

作者：

Li, Xiuzhi ^{[1
,2
]}

Jiang, Kai ^{[1
,2
]}

Jia, Songmin ^{[1
,2
]}

Zhang, Xiangyin ^{[1
,2
]}

Sun, Yanjun ^{[1
]}

机构：

[1] Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China

[2] Beijing Key Lab Computat Intelligence & Intellige, Beijing, Peoples R China

来源：

2018 CHINESE AUTOMATION CONGRESS (CAC) | 2018年

关键词：

object tracking; neural networks; Kalman; deep learning;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The tracking object is one of the important research directions in the field of computer vision and plays an important role in intelligent video monitoring. In this paper, a visual tracking method based on deep learning object detection is proposed. There are many functions required in human object tracking tasks, including the drive of hight-definition panoramic camera, real-time video streaming protocol of RTSP, object detection based on deep convolution neural network, ROI selection of interest area, dynamic object tracking of KF, and online video distribution of human coordinates through SOCKET communication.

引用

页码：4061 / 4066

页数：6