Guidance for Specific Target Doors in Hallway using the Computer Vision for Autonomous Vehicles
Document Type
Conference Proceeding
Publication Date
4-1-2019
Abstract
Computer Vision would complement the autonomous robotics goals of accuracy and precision by adding 'eyes' to the performance of the robot. We will be researching on computer vision techniques and experimenting their benefits with autonomous robotics. We investigated both Arduino MegaTM Controller Board and Raspberry Pi for analyzing the flexibility of chipset for computer vision using the 4-wire dual data bus Pixi Camera (CMU's 5th version). Both C/C++ and Python libraries were implemented to test the vision camera using I2C and USB communication. Pixi camera scans at a rate of 50 frames per second. We investigated the object recognition, object classification and object tracking capabilities using various algorithms for detecting the specific target doors in a hallway. The autonomous robot is going to maneuver in the hall way by avoiding the obstacles and stop precisely at a door-front of the assigned door number. This is possible by associating the door numbers with color codes.
Recommended Citation
McLellan, Nicholas K.; Gokaraju, Balakrishna; Tesiero, Raymond C.; and Bhattacharya, Sambit, "Guidance for Specific Target Doors in Hallway using the Computer Vision for Autonomous Vehicles" (2019). College of Health, Science, and Technology. 836.
https://digitalcommons.uncfsu.edu/college_health_science_technology/836