Place Recognition with ConvNet Landmarks
An object proposal techniques to identify potential landmarks within an image for place recognition. We use the astonishing power of convolutional neural network features to identify matching landmark proposals between images to perform place recognition over extreme appearance and viewpoint variations.
Algorithm
- landmark proposal extraction from the current image
- calculation of a ConvNet feature for each proposal
- projection of the features into a lower dimensional space
- calculation of a matching score for each previously seen image
- calculation of the best match
Notes
- Used https://github.com/pdollar/edges.git edge-box object detection tool-box
- Used https://pdollar.github.io/toolbox/ pdollar-toolbox