Review: „Multiple Target Detection and Tracking with Guaranteed Framerates on Mobile Phones“

The described related work tracks motion using optical flow algorithms. It seems that those produce satisfying results but not yet cover the full potential of a AR tracking system. Others use interest-point based algorithms which are commonly known as very computational expensive. SIFT descriptors are probably the most used ones although they might belong the… Continue reading Review: „Multiple Target Detection and Tracking with Guaranteed Framerates on Mobile Phones“

javacv

JavaCV is a wrapper for a couple of libraries, including OpenCV. They also provide a pre-compiled OpenCV for Android. Looks promising. Will take a look at it. Wonder if this slows down the application somehow, because they are some more method calls because of the wrapper stuff I guess. But if it speeds up the… Continue reading javacv

OpenCV-Android

At github I found an optimized version of OpenCV for Android. Different to the original Android version this one can be compiled with the Android NDK (except with those creepy work-arounds described at opencv/AndroidTrunk). Unfortunately, the build process took like hours: because some variables needed by the linker aren't set on Windows (but obviously on… Continue reading OpenCV-Android

Sum of Squared Differences

The Sum of Squared Differences (SSD) is a way of determining the correlation between two image regions. It is usually involved when motion compensation needs to be done. SSD is defined as followed: There are some variations of SSD. Like the Zero-mean Sum of Squared Differences (ZSSD): See also: http://siddhantahuja.wordpress.com/2010/04/11/correlation-based-similarity-measures-summary