I am currently working on integrating an object tracking algorithm of my own making into the Mission Planner. The algorithm combines Lucas-Kanade and SURF and attempts to learn negative and positive reinforcement values as it runs. Right now it is in the early stages of development, but I hope to have something fully functional within a few months.
My hope is to use this to aid in automatic centering of the tracked object by sending commands to the APM to move the camera gimbal based on the distance of the tracked object from the center of the frame. In the videos below you will see two demonstrations of this tracking algorithm. In both cases it seems to perform well with background noise.
NOTE: I apologize for the terrible frame rate of the videos. I don't have very good screen capture software. The second video is a little higher quality.
Comments
looks like a dead thread. dang it
anyone out there
Adam.
Wondering how your project is going. I have not seen or at least found a recent update so wondering how its going. I ask because this is exactly the type of thing I am looking for. I have a project I call the military drone clone project and that I am just starting on and the first component is the EO/IR system. I have a 16X zoom day night camera and a .0001 lux night camera I can going to integrate into a gimbal arrangement but thought it would be even cooler to have ground based object tracking and so far have found no one that has that working. Until I stumble across your post.
how to integrate mission planner with Matlab. im using matlab for target tracking. but wonder to send a command to the apm to move toward the target detected.
Adam, Congratulations too, i know you will be busy now ! all the best..
Thanks Chuck! It has been amazing.
I am looking forward to getting something up here for you guys.
Congrats!
I suppose it HAS been a few months. My wife and I just welcomed our first child into the world this week so things have been a bit hectic. I am concurrently working on this and the automatic PID tuning from my other blog post. I will be testing the automatic PID tuning today or tomorrow. After I confirm that is working well I should be able to get back to this.
Hi Adam, any new info or video you would like to share with us :-)
Yusuf: I am getting closer. I have been super swamped at work lately, but I have found time to improve the tracking accuracy. I will likely get to the hardware tests and post a video by mid December.