Application of image sensors to obtain potholes data on road damage

Assessment of road condition can be done by visually assessing the level of road damage and also measuring road deflection. Currently measuring road damage assessment uses a visual method with direct observations in the field. The results of the road damage assessment are calculated from the value of the type of damage. A visual assessment of road damage was used to handle road repairs in the form of road maintenance and road improvements. There are several methods of visually assessing road damage, such as the Bina Marga method and PCI method. Several methods of assessing road damage using the visual manual method so far require the accuracy of surveyors to determine the level and type of road damage. The level of accuracy of each surveyor may vary depending on experience in assessment. In addition, the use of this method takes a long time to assess road damage. Road damage assessment needs to use other better methods. One of them is by using data from image sensors, so that road damage data can be obtained more accurately and quickly. Therefore, it is necessary to propose the use image sensors to help asses road damage. This paper will review several methods of visually manual road damage assesment and plans for using image sensor on vehicle with CNN method based on the TPU with the MobileNet SSD v2. In the application of this image sensor tool, it is found that the level of accuracy is higher when carried out during the day and with a vehicle speed of less than 20 km/hour.