Wrap yolov3 submodule in a package, have the package use catkin python
setup to provide the module to scripts and other catkin packages
Paste camera demo with imports corrected

…/uw_common into brian/object_detection

…is a wrapper usage

1. subscribes to image from sim
2. predicts object bounding boxes
3. publishes prediction

Includes a copy of Xinyu Wang's TensorRT implementation of the Ultralytics YOLOv3 implementation
Some headers headers shuffled out into the include directory so things build in a ROS environment
A bit of CMake setup to make sure things only attempt to build when there's CUDA on the machine

Change demo node to use plain model
Add readme with usage notes

Not touching the copy pasted code to make future diffing easier
Add clang files

Fix whitespace, disable roslint

Use TensorRTs plugin options struct to pass in the number. Also copied
over some boilerplate for making other parameters configurable this way but
didn't hook them up fully
Tweak plugin registration point to match an update in upstream