Aiming at the problems that the traditional Canny operator can not protect the edge pixels of Gaussian filter, the point interference of non-human contours is obvious, and the fixed high and low threshold is limited, an improved Canny operator is proposed for the extraction of human contours. Firstly, bilateral filtering is used to replace Gauss filtering to protect image edge; The foreground and background are segmented by the ROI region to eliminate the interference from the background; Then Otsu method (algorithm) is used to calculate the adaptive threshold, and finally better results are obtained by fine-tuning the threshold value. Through experiments, the average accuracy of the improved Canny operator reaches 91.15% in the extraction of human contours, which is more accurate than the traditional Canny operator.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.