Fig 11 - uploaded by A. Z. M. Tahmidul Kabir
Content may be subject to copyright.
A. confidance rate of identifying the vehicle to remove, B.Mask of the car without dilation, C. Output after inpainting using mask without dilation, D. Mask of the vehicle after dilation , E. output after inpating using mask with dilation
Source publication
Data augmentation is a common technique to increase dataset. This study proposes a method that generates image data of empty road dataset. Data-driven approach is a popular approach to training an intelligent model. Various existing researches or new researches that require the empty road to train their data-driven model will be benefited by using...
Citations
... Morphological transformations were also adjusted to the output, and multiple iterations were sometimes required to improve the results. (14) The use of a deep learning algorithm to automatically detect road potholes was proposed by Rohitaa et al. Three deep learning models, namely, CNN, Mask R-CNN, and YOLOv3, were trained and tested using a dataset. ...
