Corpus ID: 15190630

Motion Detection for Video Surveillance

  title={Motion Detection for Video Surveillance},
  author={Junaedur Rahman},
This thesis is related to the broad subject of automatic motion detection and analysis in video surveillance image sequence. Besides, proposing the new unique solution, some of the previous algorit ... 
Built background image using correlation method
Motion detection typically is the case for applications using a fixed camera such as video surveillance applications or traffic monitoring applications. This research directed to detect a movementExpand
Shadow Detection and Removal in Video Sequence using Color-Based Method
A new method combining two color spaces (HSV and YCbCr) with background modelling will be proposed to detect and remove cast shadow in indoor and outdoor with humans, vehicles, and motorcycles moving objects. Expand
Abnormal Human Behavior Detection in Video Using Suspicious Object Detection
An approach to find out an abnormal activity based on features of object which is independent of object size, shape and speed is used and also increases accuracy in video surveillance system to detect abnormal activity in real time environment. Expand


View-based detection and analysis of periodic motion
  • Ross Cutler, L. Davis
  • Computer Science, Mathematics
  • Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170)
  • 1998
A technique that detects periodic motion by segmenting moving objects from the background and computing the object's self-similarity as it evolves in time is described. Expand
A System for Video Surveillance and Monitoring
Under the three-year Video Surveillance and Monitoring (VSAM) project (1997‐1999), the Robotics Institute at Carnegie Mellon University (CMU) and the Sarnoff Corporation developed a system forExpand
Understanding Background Mixture Models for Foreground Segmentation
This tutorial paper describes a practical implementation of the Stauffer-Grimson algorithm and provides values for all model parameters and shows what approximations to the theory were made and how to improve the standard algorithm by redefining those approximation. Expand
A Robust Background Subtraction and Shadow Detection
This paper develops a robust and efficiently computed background subtraction algorithm that is able to cope with local illumination change problems, such as shadows and highlights, as well as global illumination changes. Expand
Improved adaptive Gaussian mixture model for background subtraction
An efficient adaptive algorithm using Gaussian mixture probability density is developed using Recursive equations to constantly update the parameters and but also to simultaneously select the appropriate number of components for each pixel. Expand
Moving target classification and tracking from real-time video
An end-to-end method for extracting moving targets from a real-time video stream, classifying them into predefined categories according to image-based properties, and then robustly tracking them is described. Expand
A Pixel Layering Framework For Robust Foreground Detection In Video
This work presents a framework for robust foreground detection that works under difficult conditions such as dynamic background and nominally moving camera. The proposed method includes two mainExpand
Image Segmentation in Video Sequences: A Probabilistic Approach
A mixture-of-Gaussians classification model for each pixel is learned using an unsupervised technique--an efficient, incremental version of EM, which identifies and eliminates shadows much more effectively than other techniques such as thresholding. Expand
Robust techniques for background subtraction in urban traffic video
This paper compares various background subtraction algorithms for detecting moving vehicles and pedestrians in urban traffic video sequences, considering approaches varying from simple techniques such as frame differencing and adaptive median filtering, to more sophisticated probabilistic modeling techniques. Expand
Effective Gaussian mixture learning for video background subtraction
  • Dar-Shyang Lee
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2005
An effective scheme to improve the convergence rate without compromising model stability is proposed by replacing the global, static retention factor with an adaptive learning rate calculated for each Gaussian at every frame. Expand