TY - GEN
T1 - An overview of object detection and tracking
AU - Zhao, Yi
AU - Shi, Haobin
AU - Chen, Xuanwen
AU - Li, Xuesi
AU - Wang, Cong
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/9/28
Y1 - 2015/9/28
N2 - Over the last couple of years, object detection and tracking reserachers have been developing many new techniques, which has been used widely by others. In this article, we present an extensive overview of object detection and tracking methods. At the same time, we also introduces some related theoretical knowledge (e.g., feature and classification). The reason why the object detection and tracking in summarized together, is because the object detection can be said to be the foundation of the object tracking, and they all need to choose the right features and training effective classification. Due to the application fields and emphasis may be different, the number of features which we can select is large. This paper mainly introduces some common features, such as color, histogram of gradients edges and optical flow. Then classifications are introduced, which are all classical classifications. There are many methods of detection and tracking, but now researchers will mainly consider some of the key factors, which include context, silhouette and background. Finally, we respectively introduced some common methods for object detection and object tracking. And discuss the advantages and disadvantages of principles.
AB - Over the last couple of years, object detection and tracking reserachers have been developing many new techniques, which has been used widely by others. In this article, we present an extensive overview of object detection and tracking methods. At the same time, we also introduces some related theoretical knowledge (e.g., feature and classification). The reason why the object detection and tracking in summarized together, is because the object detection can be said to be the foundation of the object tracking, and they all need to choose the right features and training effective classification. Due to the application fields and emphasis may be different, the number of features which we can select is large. This paper mainly introduces some common features, such as color, histogram of gradients edges and optical flow. Then classifications are introduced, which are all classical classifications. There are many methods of detection and tracking, but now researchers will mainly consider some of the key factors, which include context, silhouette and background. Finally, we respectively introduced some common methods for object detection and object tracking. And discuss the advantages and disadvantages of principles.
KW - background
KW - context
KW - detection
KW - feature
KW - tracking
UR - http://www.scopus.com/inward/record.url?scp=84959899232&partnerID=8YFLogxK
U2 - 10.1109/ICInfA.2015.7279299
DO - 10.1109/ICInfA.2015.7279299
M3 - 会议稿件
AN - SCOPUS:84959899232
T3 - 2015 IEEE International Conference on Information and Automation, ICIA 2015 - In conjunction with 2015 IEEE International Conference on Automation and Logistics
SP - 280
EP - 286
BT - 2015 IEEE International Conference on Information and Automation, ICIA 2015 - In conjunction with 2015 IEEE International Conference on Automation and Logistics
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2015 IEEE International Conference on Information and Automation, ICIA 2015 - In conjunction with 2015 IEEE International Conference on Automation and Logistics
Y2 - 8 August 2015 through 10 August 2015
ER -