IN2013CH05859AIN5859CH2013AIN2013CH05859AIN 2013CH05859 AIN2013CH05859 AIN 2013CH05859AIN 5859CH2013 AIN5859CH2013 AIN 5859CH2013AIN 2013CH05859 AIN2013CH05859 AIN 2013CH05859A
Authority
IN
India
Prior art keywords
image frames
interest
subject
volume
quality indicator
Prior art date
Application number
Inventor
Chandan Kumar Mallappa Aladahalli
Krishna Seetharam Shriram
Original Assignee
Gen Electric
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Gen ElectricfiledCriticalGen Electric
Priority to IN5859CH2013priorityCriticalpatent/IN2013CH05859A/en
Publication of IN2013CH05859ApublicationCriticalpatent/IN2013CH05859A/en
Methods and systems for imaging a subject are presented. One or more candidate structures corresponding to a target feature and one or more supplementary features in each of a plurality of image frames are identified, where the plurality of image frames corresponds to a volume of interest of the subject. One or more spatial configurations corresponding to each of a plurality of combinations of the candidate structures are determined. Each of the spatial configurations is compared with a spatial reference model corresponding to a determined relative position of the target feature and the supplementary features in the volume of interest. A quality indicator corresponding to each of the plurality of image frames is computed based on the comparison. An optimal image frame is selected from the plurality of image frames based on the computed quality indicator. FIG. 2
Method for acquiring bounding box corresponding to an object in an image by using convolutional neural network including tracking network and computing device using the same