• S. Uma Maheswari
• Frankline Owino
• A. Anirudh
• VS praganesh

The purpose of this study is to explore the different methods used to detect concrete cracks. it reviews the non-destructive crack detection methods, their strengths and weaknesses. The goal is to analyze their application and feasibility to find the most optimal and practical methodology that will be most optimal for implementation. Crack detection has been manually over a long period of time, this presents major security risks and it is also time consuming. other implementations require using of dedicated hardware which in turn may be expensive to acquire. Using a readily available device which is our smartphone, we can implement the detection system by processing the video stream, even a low-cost smartphone has all the sensors we can use for the system making it is more accessible for usage by many people. Due to the smartphone compactness we have them in lighter weights and smaller form factors, by tapping into readily available devices such as drones and small remote-controlled cars we could attach our smartphone and reach places we could not analyze before such as high walls, dam walls and underground tunnels and get precise location at the cracks

image processing, convolutional neural networks, small unmanned vehicles, concrete crack detection, supervised learning, transfer learning

"Concrete crack detection using convolutional Neural Networks ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.28-32, March-2019, Available :http://www.jetir.org/papers/JETIR1903B05.pdf

"Concrete crack detection using convolutional Neural Networks ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp28-32, March-2019, Available at : http://www.jetir.org/papers/JETIR1903B05.pdf