When you're driving, how important is it to be able to quickly tell the difference between a person vs. a stop sign? It's a hugely important, but typically very simple, distinction that you would make reflexively. Autonomous vehicles are not able to do this quite as effortlessly. 

This challenge, hosted by the 2018 CVPR workshop on autonomous driving ([WAD][1]), asks you to help give autonomously driven vehicles the same edge. Using an unprecedented dataset, you're asked to segment movable objects, such as cars and pedestrians, at instance level within image frames.

![Segmented image][2]

By participating in this competition, you'll be helping to further our understand of the current status of computer vision algorithms in solving environmental perception problems for autonomous driving.

This challenge is a truly unique opportunity to work on a tremendously high value and high profile problem. The dataset presented here contains over 10 times more fine-labeled images than the largest public dataset of its type.

## Acknowledgements ##
This competition is hosted by the 2018 CVPR workshop on autonomous driving (WAD), with dataset and evaluation metric contributed by Baidu Inc.

 


  [1]: http://www.wad.ai/
  [2]: https://storage.googleapis.com/kaggle-media/competitions/cvpr/image_example.jpg