This is the second DSPS student competition on the application of AI for pavement condition monitoring. The current edition will consist of two main tracks: Tracks 1 and 2.
Track 1 will follow a data-centric model instead of the traditional model-centric approaches. Top-down and dash-cam views of pavement image data containing seven main distress types annotated with bounding boxes will be provided. Participants will systematically change/enhance datasets provided using various data cleaning, annotation, augmentation strategies to improve the accuracy of a predefined model architecture.
Track 2 will be model-centric: Teams are free to use any model architecture of their choice to detect, and estimate the severity of different types of pavement distresses.
Below you will find full competition information
and team registration form.