robosat
robosat copied to clipboard
mapbox
Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds
At the moment we are using pixel-wise loss functions for our segmentation models. These loss functions are great for overall segmentation problems but they fail to capture topology inherent in...
At the moment the `rs extract` handlers are responsible to walk over OpenStreetMap and collect and extract GeoJSON features for the training dataset. Every handler has to start from scratch...
Given the config file, we could randomly produce standard training dataset from the raw dataset. By the way, at present if I want to train my dataset, I must create...
With https://github.com/mapbox/robosat/pull/46 we are changing our model architecture from training the encoder and decoder from scratch to using a pre-trained ResNet for the encoder. The pre-trained ResNet uses three channels...
At the moment we have a parking lot handler tuned with thresholds specifically for zoom level 18: https://github.com/mapbox/robosat/blob/4cc40914a32443c1358ef7b45451b52298302597/robosat/features/parking.py#L11-L103 Instead what we should do is: - generalize thresholds and base them...
While cleaning up datasets, we want to look at just the images and their labels. The current `rs compare` requires at-least one masks directory and this PR makes the masks...
Right now `rs masks` is able to combine multiple slippy map directories with probabilities. The idea is that we can have multiple models and this feature allows us for model...
I see no reason why we can't implement object detection into robosat for specific use-cases. The pre-processing and post-processing needs to be slightly adapted to work with bounding boxes but...
At the moment we are using a pre-trained ResNet as an encoder in our encoder-decoder architecture: https://github.com/mapbox/robosat/blob/8b7566e3b5de3583eb64fbb641ff18b9ff01f901/robosat/unet.py#L94-L100 https://github.com/mapbox/robosat/blob/8b7566e3b5de3583eb64fbb641ff18b9ff01f901/robosat/unet.py#L123-L134 We are currently training the model as is with all layers unfrozen....
Splitting off of https://github.com/mapbox/robosat/issues/12. Eventually we want to implement an object detection architecture in addition to out current semantic segmentation architecture. The RetinaNet (ticketed in #12) is a perfect fit...