人工智能
判别式
计算机科学
分割
计算机视觉
跟踪(教育)
视频跟踪
深度学习
光学(聚焦)
机器学习
特征提取
强化学习
对象(语法)
特征(语言学)
目标检测
模式识别(心理学)
光学
哲学
物理
心理学
语言学
教育学
作者
Zahra Soleimanitaleb,Mohammad Ali Keyvanrad,Ali Jafari
出处
期刊:International Conference on Computer and Knowledge Engineering
日期:2019-10-01
被引量:13
标识
DOI:10.1109/iccke48569.2019.8964761
摘要
Object tracking is one of the most important tasks in computer vision that has many practical applications such as traffic monitoring, robotics, autonomous vehicle tracking, and so on. Different researches have been done in recent years, but because of different challenges such as occlusion, illumination variations, fast motion, etc. researches in this area continues. In this paper, various methods of tracking objects are examined and a comprehensive classification is presented that classified tracking methods into four main categories of feature-based, segmentation-based, estimation-based, and learning-based methods that each of which has its own sub-categories. The main focus of this paper is on learning-based methods, which are classified into three categories of generative methods, discriminative methods, and reinforcement learning. One of the sub-categories of the discriminative model is deep learning. Because of high-performance, deep learning has recently been very much considered.
科研通智能强力驱动
Strongly Powered by AbleSci AI