Abstract
Few object detection methods exist which can resolve small objects (<20 pixels) from complex static backgrounds without significant computational expense. A framework capable of meeting these needs which reverses the steps in classic edge detection methods using the Canny filter for edge detection is presented here. Sample images taken from sequential frames of video footage were processed by subtraction, thresholding, Sobel edge detection, Gaussian blurring, and Zhang–Suen edge thinning to identify objects which have moved between the two frames. The results of this method show distinct contours applicable to object tracking algorithms with minimal “false positive” noise. This framework may be used with other edge detection methods to produce robust, low-overhead object tracking methods.
Highlights
As image capturing hardware and storage capabilities improve, more and more digital imagery is being captured as video
As an alternative we offer a naive approach suitable for detecting moving objects that employs computationally inexpensive methods based on a reversal of classic edge detection techniques
We demonstrate edge detection reversal using the general steps from a single edge detection scheme, the Canny edge detector, and compare the results to simple object detection by image difference
Summary
As image capturing hardware and storage capabilities improve, more and more digital imagery is being captured as video. Classic methods of edge detection based on first and second-derivative kernel operations, such as the Roberts [1], Sobel [2,3], Marr-Hildreth [4], and Haralick [5] techniques are still frequently used as the basis for modern static image edge detection due to the speed and quality of the output [6]. Perhaps one of the the most well-known and actively used techniques in the field of edge detection in computer vision is the Canny edge detector [7]. This classic method detects edges by taking a denoised grayscale image, finding the gradient intensities, suppressing spurious non-maxima, finding the dual-threshold of the result, and edge tracking by hysteresis. As an alternative we offer a naive approach suitable for detecting moving objects that employs computationally inexpensive methods based on a reversal of classic edge detection techniques
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
