Discrete cosine transform: algorithms, advantages, applications
Discrete cosine transform: algorithms, advantages, applications
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM Computing Surveys (CSUR)
On the Analysis of Accumulative Difference Pictures from Image Sequences of Real World Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
A common method for real time moving object detection in image sequences is background removal, also referred to as background subtraction. The numerous approaches differ in the type of background model used and the procedure used to update the model. This paper discusses modeling each $4 \times 4$ pixel patch of an image through a set of coefficient vectors which are obtained by means of a discrete cosine transform. The amount of vectors used to model a patch is adapted online for each patch separately. In contrast to most other background removal techniques foreground detection and background adaptation procedure also incorporates temporal and spacial characteristics of an object motion. The presented methods was shown to be very robust to arbitrary changes in the observed environment and was successfully tested in several video surveillance scenarios.