Object tracking is a well-studied problem within the the area of image processing. The ability to track objects has improved drastically during the last decades, however, it is still considered a complex problem to solve. The importance of object tracking is reflected by the broad area of applications such as video surveillance, human-computer interaction, and robot navigation. The purpose of this study was to examine, evaluate, and make a summary of the most common object tracking methods. In this paper a thorough review of the object tracking process is presented. This includes selection of object representation, object features, methods for object detection, and methods for tracking the object over succeeding frames. A summary of the object tracking methods covered in this paper is presented in the result section, including advantages, disadvantages, and for which context each method is suitable for.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:umu-136153 |
| Date | January 2017 |
| Creators | Ågren, Sanna |
| Publisher | Umeå universitet, Institutionen för datavetenskap |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | UMNAD ; 1100 |
Page generated in 0.0021 seconds