This week, we have looked for related works and made some decisions about which way to follow for our project. We’ve decided to use Google’s Street View since we have found related works in this area which can help us.
Here are some papers:
Accurate Image Localization Based on Google Maps Street View http://crcv.ucf.edu/papers/eccv2010/Zamir_ECCV_2010.pdf
To Know Where We Are: Vision-Based Positioning in Outdoor Environments https://arxiv.org/pdf/1506.05870.pdf
Street View Challenge: Identification of Commercial Entities in Street View Imagery
http://www.cs.stanford.edu/~amirz/index_files/Street_View_Challenge.pdf
Worldwide Pose Estimation using 3D Point Clouds http://landmark.cs.cornell.edu/docs/global_pose.pdf
Also, we’ve found course and lesson webpages which can be very helpful:
Generic 3D Representation via Pose Estimation and Matching http://3drepresentation.stanford.edu/
CS231n: Convolutional Neural Networks for Visual Recognition https://cs231n.github.io/
