背景减法
计算机科学
人工智能
计算机视觉
目标检测
建筑
运动估计
对象(语法)
深度学习
运动(物理)
卷积神经网络
计算机图形学(图像)
运动检测
光流
分割
模式识别(心理学)
像素
地理
考古
作者
Byeongho Heo,Kimin Yun,Jin Young Choi
出处
期刊:International Conference on Image Processing
日期:2017-09-01
被引量:16
标识
DOI:10.1109/icip.2017.8296597
摘要
Background subtraction from the given image is a widely used method for moving object detection. However, this method is vulnerable to dynamic background in a moving camera video. In this paper, we propose a novel moving object detection approach using deep learning to achieve a robust performance even in a dynamic background. The proposed approach considers appearance features as well as motion features. To this end, we design a deep learning architecture composed of two networks: an appearance network and a motion network. The two networks are combined to detect moving object robustly to the background motion by utilizing the appearance of the target object in addition to the motion difference. In the experiment, it is shown that the proposed method achieves 50 fps speed in GPU and outperforms state-of-the-art methods for various moving camera videos.
科研通智能强力驱动
Strongly Powered by AbleSci AI