0

i am using pioneer 3dx with rosaria library where sonar publishes obstacles position from where i can extract ranges from obstacles. i mounted intel realsense D435i on pioneer and installed all the libraries required for camera. now the question is what data should i extract from camera for fusing both data so that they complement each other.

i used yolov3 algorithm on realsense camera and try to detect objects ,bounding box and x min,y min,x max, y max and depth info from objects detected. so which info should i use from vast topics that camera is giving to fuse it with sonar range data so to improve obstacle detection fo avoidance i am attaching sonar range data and camera publishes topics below

sonar ranges from 8 sonar rings:

1

pointcloud of sonar:

3

camera published topics:

2

Christoph Rackwitz
  • 11,317
  • 4
  • 27
  • 36
busireddy harshavardhanreddy
  • 1
  • 1
    welcome. [tour], [ask], [mre], [help/on-topic]. remove the photos. insert text when something is text. use graphics only for graphics. – Christoph Rackwitz Feb 16 '23 at 12:11
  • Also, when you need a screen capture, use a screen capture. Not a photograph. – Guilherme Taffarel Bergamin Feb 16 '23 at 21:40
  • What do you mean by "sensor fusion" what kind of output do you expect? Improved pointcloud? Improved costmap_2d? Or just that obstacles gets marked in costmap by sonar and camera? In my experience sonars have wide beam and noisy range with false detections if camera sees same location as sonar I would just turn of sonar and probably get better performance. Of course in close proximity etc sonars are good extra protection – Combinacijus Mar 13 '23 at 05:46

0 Answers0