Title :
A real time object tracking system for contrast media injection
Author :
Wang, Zhelong ; Dai, Chuan ; Zhao, Hongyu
Author_Institution :
Shenyang Inst. of Autom., Chinese Acad. of Sci., Shenyang, China
Abstract :
Contrast media is widely used in hospital for a better imaging of CT angiography. However, emergencies (such as needle eruption and capillary hemorrhage) may exist due to the extreme high speed of injection. A video-object-tracking system is implemented in this paper which can keep track of the patient´s progress and sound an alarm in the event of danger. The MeanShift algorithm for real-time object tracking determines the location of the injection site. An area based detection method is presented to check whether the injection site is bleeding. Experiment results show that the video-tracking-and-monitoring system could track the injection site effectively and achieve a high tracking accuracy.
Keywords :
computerised tomography; diagnostic radiography; medical image processing; object detection; target tracking; CT angiography; area based detection method; contrast media injection; hospital; injection site; meanshift algorithm; real time system; video object tracking system; Analytical models; Computational modeling; Computed tomography; Medical services; Monitoring; Robustness; Tracking; Canny operator; Edge; MeanShift algorithm; Tracking; Visual tracking;
Conference_Titel :
Systems Man and Cybernetics (SMC), 2010 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-6586-6
DOI :
10.1109/ICSMC.2010.5641832