apollack11 / advanced-computer-vision Goto Github PK

Hi,
I try to run project.launch file. Everything looks fine and in my opinion flow node is waiting for the image from "/usb_cam/image_raw/compressed" topic. But when I publish my images to that topic, flow node is still doing nothing. Can you tell me what I am doing wrong?

How would I go about calculating the homography perspective matrix? In flow.cpp, it is on line 153:

double H_data[9] = {0.0002347417933653588, -9.613823951336309e-20, -0.07500000298023225, -7.422126200315807e-19, -0.0002818370786240783, 0.5159999728202818, 1.683477982667922e-19, 5.30242624981192e-18, 1};

Using my own data, I am accumulating lots of drift (robots pose veers to the right), and when the robot takes a u-turn, it underestimates the change in heading. Please let me know, thanks!

Really awesome job on the source code. It is well documented and easy to understand!

When the fram moves too fast or there are not enough features in the surrounding space , the node crashes .

Can i know where i should perhaps put a try catch-exception to get over this issue ?

When I compile this package using catkin_make within my workspace I get the following compile error:

/usr/include/opencv2/core/operations.hpp:1850:51: note: template argument deduction/substitution failed:
/home/stagiair/catkin_ws_2/src/advanced-computer-vision-master/src/flow.cpp:559:58: note: cannot convert ‘((FlowCalculator*)this)->FlowCalculator::H’ (type ‘cv::Matx33d {aka cv::Matx<double, 3, 3>}’) to type ‘double’
motion_avg += Point3f((H * Mat(*it2) - H * Mat(*it1)) / N); // you can tell it's the average by the way that it is!

Is this a known problem? And if so, is there a solution available?

Thanks in advance!

Hi,

I want know what license is applied for this project.

Thanks.