Surveillance Robot using Neural Net

Surveillance Robot is supposed to inspect buildings for any structural damages and then identify the damage and make further decisions.

AdityaPrakash23

Following Follow project

Liked Like project

Become a Hackaday.io member

Just one more thing

To make the experience fit your profile, pick a username and tell us what interests you.

OK, I'm done! Skip

Similar projects worth following

306 views

0 comments

5 followers

2 likes

Description
Details
Files 0
Components 3
- View all
Logs 1
- View all
Instructions 0
Discussion 0

Description

The Surveillance robot is designed to conduct inspection rounds or emergency inspections of a structure. It keeps taking pics of the structure and feeds it to a trained neural net based image classifier. Once the classifier finds a structural damage, the robot identifies the damage and then reports it to a central system(a server or cloud based web app).

Components

1 × Gazebo Simulator Robotics simulator
1 × ROS Robot programming software
1 × Beaglebone Conroller for robot and image classifier platform

Project Logs

Collapse

Research
AdityaPrakash23 • 10/15/2017 at 05:33 • 0 comments

I have just started with the project. I am presently working on the image classifier and at the same time on Gazebo Simulator. I am first designing the robot in the simulator. The robot is going to be controlled using the Beaglebone Black.