Statistical motion vector analysis for object tracking in compressed video streams

2008 ◽  
Author(s):  
Marc Leny ◽  
Françoise Prêteux ◽  
Didier Nicholson
Author(s):  
Fernando Bombardelli ◽  
Serhan Gul ◽  
Daniel Becker ◽  
Matthias Schmidt ◽  
Cornelius Hellge

2012 ◽  
Vol 532-533 ◽  
pp. 1219-1224
Author(s):  
Hong Tao Deng

During video transmission over error prone network, compressed video bit-stream is sensitive to channel errors that may degrade the decoded pictures severely. In order to solve this problem, error concealment technique is a useful post-processing tool for recovering the lost information. In these methods, how to estimate the lost motion vector correctly is important for the quality of decoded picture. In order to recover the lost motion vector, an Decoder Motion Vector Estimation (DMVE) criterion was proposed and have well effect for recover the lost blocks. In this paper, we propose an improved error concealment method based on DMVE, which exploits the accurate motion vector by using redundant motion vector information. The experimental results with an H.264 codec show that our method improves both subjective and objective decoder reconstructed video quality, especially for sequences of drastic motion.


2010 ◽  
Author(s):  
Mehrube Mehrubeoglu ◽  
Diego Rojas ◽  
Lifford McLauchlan

2011 ◽  
Vol 58-60 ◽  
pp. 2290-2295 ◽  
Author(s):  
Ruo Hong Huan ◽  
Xiao Mei Tang ◽  
Zhe Hu Wang ◽  
Qing Zhang Chen

A method of abnormal motion detection for intelligent video surveillance is presented, which includes object intrusion detection, object overlong stay detection and object overpopulation detection. Background subtraction algorithm is used to detect moving objects in video streams. Kalman filter is applied for object tracking. By the construction of relation matrix, the tracking process is divided into five statuses for prediction and estimation, which are object disappearing, object separating, new object appearing, object sheltering and object matching. The object parameters and predictive information in the next frame which is used to track moving objects is established by Kalman filter. Then, three types of abnormal motion detection are implemented. The relative position of alarm area or guard line with the rectangle boxes of the moving objects is used to detect whether the object is invading. The existing time of the moving objects in monitor area is counted to detect whether the object is staying too long. Moving objects in the monitor area are classified and counted to detect whether the objects are too much. Alarm will be triggered when abnormal motion detection as defined is detected in the monitor area.


Sign in / Sign up

Export Citation Format

Share Document