CHANNELS

Aerospace

Automotive

Automated & Autonomous Vehicles

Battery & Electrification Technology

Defense

Drone TV

Electronics

Manufacturing & Prototyping

Materials

Medical

Motion Control

RF & Microwave Technology

Robotics & Automation

Sensors & IoT

Test & Measurement

Aerospace
Automotive
Automated & Autonomous Vehicles
Battery & Electrification Technology
Defense
Drone TV
Electronics
Manufacturing & Prototyping
Materials
Medical
Motion Control
RF & Microwave Technology
Robotics & Automation
Sensors & IoT
Test & Measurement
Aerospace & Defense
Search Results

Firefighting Robotic Scout Creates 3D Thermal Map for Rescuers

University of California, San Diego engineers have developed new image processing techniques for rapid exploration and characterization of fires by small, Segway-like robotic vehicles. The robotic vehicles photograph the interior of burning buildings by using stereo and infrared vision, and use data gathered from various sensors to characterize the state of a fire, including temperatures, volatile gases, and structural integrity. An on-board software system maps the thermal data onto a 3D scene constructed from the images. This 3D thermal map can be provided in near real time to rescuers, who could better assess the structure and plan their firefighting and rescue activities.

Topics:
Automation Cameras Communications Detectors Environmental Monitoring Green Design & Manufacturing Imaging Motion Control Motors & Drives Robotics Sensors Software Visualization Software Wireless

More From SAE Media Group

    Transcript

    00:00:04 the UCSD coordinated robotics lab is focused on the development of semi-autonomous robots to assist with firefighting search and rescue operations and environmental monitoring using stereo and infrared imagery we are able to map Urban environments and detect survivors ffr is a physically robust vehicle designed to drive in a Segway like

    00:00:34 manner the robot also has an actuated Center leg that can raise the body up allowing the robot to climb stairs and overcome large obstacles by using the wheels as reaction fly wheels the robot is able to maintain stability and balance on the center leg as the robot navigates through a structure it captures a sequence of

    00:01:01 images using the infrared and RGB cameras we are able to produce a dense 3D Point cloud from the images using visual structure from motion calibration is used to resolve the parameters of each camera as well as their relative position and orientation with respect to each other in our experiments a planer checkerboard pattern is used as a

    00:01:23 calibration object thermally conductive rubber tape is placed over the checkerboards black squares to produce a large temperature gradient at Each corner when heated its Corners are detected and matched using open CV images captured by the robot are processed by the visual sfm software which uses bundle adjustment to produce a sparse Point cloud with textures it is

    00:01:46 then extrapolated to form a dense Point Cloud each 3D point is projected onto the set of thermal image ples from which it is visible the pixel intensity values at the corresponding coordinates are averaged and assigned to each point in the thermal 3D Cloud thanks for watching