Join GitHub today
GitHub is home to over 20 million developers working together to host and review code, manage projects, and build software together.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
|Failed to load latest commit information.|
******************** * SIFT BASED DSMAC * ******************** README: This code is a SIFT based trackers for UAV applications. The tracker is meant for DMSAC purposes DSMAC: Digital Scene Matcher and Area Co-relator What it tries to do is to match a given input from a UAV and match it to a large map. Since the input object is highly scaled out in the map scene. It is necessary to use PryDown functions to make it easier for them to match. Certain other boosts in the SIFT codes makes the performance in this DMSAC to around 30ms. The upgrades are already pulled into the new OpenCV 2.4.2 (For reference, this pulls involved changes in the Lehviestien distance measurement and the feature calculations) REQUIREMENTS: OpenCV 2.4.2 CMake 2.8 BUILDIING FROM SOURCE: 1. USE CMAKE mkdir build cd build cmake .. make This should make the required files and the executable as well RUNNING THE CODE: ./SIFT_descriptor <Object image> <Scene Image> <resize parameter in power of two> <number of matches to be considered> img1 : Object Image (This will be the zoomed in version) img2 : Scene Image (This will be the Map version, scaled out as compared to the object image) resize parameter : This parameter will scale the image. and float value k will change the image size k times. In most cases k < 0 (In an UAV, this parameter will be a function of height of the UAV) number of matches to be considered : This parameter defines the number of matches to be used for the purpose of homography calculations. AUTHORS: Abhinav Gupta CONSTRBUTORS: Ritesh Ranjan