nuScenes map expansion pack (#172)

* Initial commit

* Added missing descartes requirement

* Overhauled tutorial

* Renamed map files

* Fix wrong file extension

* Renamed map extension to map expansion

* Fix wrong import, clear outputs

* Fixes for queenstown map

* Overhauled map tutorial

* Fixed wrong output message

* Added detailed information on map origin and size

* Reorganized readme and faq for map expansion pack

* Rewording

* Minor fixes to the map tutorial

* Change order of the getting started bullet points

* Binary map mask api and visualization example (#181)

* rename map_graph to map_api

* wip: rendering

* rendering

* map api done

* visualization example

* Renamed MapAPIExplorer to NuscenesMapExplorer

* Reformatting

* Reformatting

* Undo spacing bug

* Fix missing return statement

* Added n_rows as argument

* Pass on n_rows argument

* Improved tutorial visualization

* Updated naming conventions, first extract raw data then visualize, changed order

* Rename `get_map_patch_mask` to `get_map_mask` and change output format to be a stacked numpy array

* Added instructions for rotated map patches

* Updated typing

* Plot whole map by default

* Typo in the map names

* Round canvas size

* Swapped order of arguments

* Handle case where canvas_size is not given to render_map_mask

* Started on semantic prior check

* Fixed bug with swapped height/width

* More experiments on reconstructing semantic prior

* Removing comparison to semantic_prior

* Delete test.py

README.md

@@ -5,13 +5,13 @@ Welcome to the devkit of the [nuScenes](https://www.nuscenes.org) dataset.
 ## Overview
 - [Changelog](#changelog)
 - [Dataset download](#dataset-download)
+- [Map expansion](#map-expansion)
 - [Devkit setup](#devkit-setup)
-- [Tutorial](#tutorial)
-- [Frequently asked questions](#frequently-asked-questions)
-- [Object detection task](#object-detection-task)
+- [Getting started](#getting-started)
 - [Citation](#citation)
 
 ## Changelog
+- Jul. 1, 2019: Map expansion pack released.
 - Apr. 30, 2019: Devkit v1.0.1: loosen PIP requirements, refine detection challenge, export 2d annotation script. 
 - Mar. 26, 2019: Full dataset, paper, & devkit v1.0.0 released. Support dropped for teaser data.
 - Dec. 20, 2018: Initial evaluation code released. Devkit folders restructured, which breaks backward compatibility.
@@ -30,11 +30,19 @@ Eventually you should have the following folder structure:
 /data/sets/nuscenes
     samples	-	Sensor data for keyframes.
     sweeps	-	Sensor data for intermediate frames.
-    maps	-	Large image files (~500 Gigapixel) that depict the drivable surface and sidewalks in the scene.
+    maps	-	Folder for all map files: rasterized .png images and vectorized .json files.
     v1.0-*	-	JSON tables that include all the meta data and annotations. Each split (trainval, test, mini) is provided in a separate folder.
 ```
 If you want to use another folder, specify the `dataroot` parameter of the NuScenes class (see tutorial).
 
+## Map expansion
+In July 2019 we published a map expansion pack with 11 semantic layers (crosswalk, sidewalk, traffic lights, stop lines, lanes, etc.).
+To install this expansion, please follow these steps:
+- Download the expansion pack from the [Download page](https://www.nuscenes.org/download),
+- Move the four .json files to your nuScenes maps folder (e.g. `/data/sets/nuscenes/maps`).
+- Get the latest version of the nuscenes-devkit.
+- If you already have a previous version of the devkit, update the pip requirements (see [details](https://github.com/nutonomy/nuscenes-devkit/blob/master/setup/installation.md)): `pip install -r setup/requirements.txt`
+
 ## Devkit setup
 The devkit is tested for Python 3.6 and Python 3.7.
 To install Python, please check [here](https://github.com/nutonomy/nuscenes-devkit/blob/master/installation.md#install-python).
@@ -45,20 +53,22 @@ pip install nuscenes-devkit
 ```
 For an advanced installation, see [installation](https://github.com/nutonomy/nuscenes-devkit/blob/master/setup/installation.md) for detailed instructions.
 
-## Tutorial
-To get started with the nuScenes devkit, please run the tutorial as an IPython notebook:
+## Getting started
+Please follow these steps to make yourself familiar with the nuScenes dataset:
+- Read the [dataset description](https://www.nuscenes.org/overview).
+- [Explore](https://www.nuscenes.org/explore/scene-0011/0) the lidar viewer and videos.
+- [Download](https://www.nuscenes.org/download) the dataset. 
+- Get the [nuscenes-devkit code](https://github.com/nutonomy/nuscenes-devkit).
+- Read the [online tutorial](https://www.nuscenes.org/tutorial) or run it yourself using:
 ```
 jupyter notebook $HOME/nuscenes-devkit/python-sdk/tutorial.ipynb
 ```
-In case you want to avoid downloading and setting up the data, you can also take a look at the [rendered notebook on nuScenes.org](https://www.nuscenes.org/tutorial).
-To learn more about the dataset, go to [nuScenes.org](https://www.nuscenes.org) or take a look at the [database schema](https://github.com/nutonomy/nuscenes-devkit/blob/master/schema.md) and [annotator instructions](https://github.com/nutonomy/nuscenes-devkit/blob/master/instructions.md).
-The [nuScenes paper](https://arxiv.org/abs/1903.11027) provides detailed analysis of the dataset.
-
-## Frequently asked questions
-See [FAQs](https://github.com/nutonomy/nuscenes-devkit/blob/master/faqs.md).
-
-## Object detection task
-For instructions related to the object detection task (results format, classes and evaluation metrics), please refer to [this readme](https://github.com/nutonomy/nuscenes-devkit/blob/master/python-sdk/nuscenes/eval/detection/README.md).
+- Read the [nuScenes paper](https://www.nuscenes.org/publications) for a detailed analysis of the dataset.
+- Run the [map expansion tutorial](https://github.com/nutonomy/nuscenes-devkit/blob/master/python-sdk/nuscenes/map_expansion/map_demo.ipynb).
+- Take a look at the [experimental scripts](https://github.com/nutonomy/nuscenes-devkit/tree/master/python-sdk/nuscenes/scripts).
+- For instructions related to the object detection task (results format, classes and evaluation metrics), please refer to [this readme](https://github.com/nutonomy/nuscenes-devkit/blob/master/python-sdk/nuscenes/eval/detection/README.md).
+- See the [database schema](https://github.com/nutonomy/nuscenes-devkit/blob/master/schema.md) and [annotator instructions](https://github.com/nutonomy/nuscenes-devkit/blob/master/instructions.md).
+- See the [FAQs](https://github.com/nutonomy/nuscenes-devkit/blob/master/faqs.md).
 
 ## Citation
 Please use the following citation when referencing [nuScenes](https://arxiv.org/abs/1903.11027):

faqs.md

@@ -6,15 +6,6 @@ On this page we try to answer questions frequently asked by our users.
     - For issues and bugs *with the devkit*, file an issue on [Github](https://github.com/nutonomy/nuscenes-devkit/issues).
     - For any other questions, please post in the [nuScenes user forum](https://forum.nuscenes.org/).
 
-- How can I get started?
-    - Read the [dataset description](https://www.nuscenes.org/overview).
-    - [Explore](https://www.nuscenes.org/explore/scene-0011/0) the lidar viewer and videos.
-    - Read the [tutorial](https://www.nuscenes.org/tutorial).
-    - Read our [publications](https://www.nuscenes.org/publications).
-    - [Download](https://www.nuscenes.org/download) the dataset. 
-    - Get the [nuscenes-devkit code](https://github.com/nutonomy/nuscenes-devkit).
-    - Take a look at the [experimental scripts](https://github.com/nutonomy/nuscenes-devkit/tree/master/python-sdk/nuscenes/scripts).
-
 - Can I use nuScenes for free?
     - For non-commercial use [nuScenes is free](https://www.nuscenes.org/terms-of-use), e.g. for educational use and some research use.
     - For commercial use please contact [[email protected]](mailto:[email protected]). To allow startups to use our dataset, we adjust the pricing terms to the use case and company size.
@@ -24,13 +15,12 @@ On this page we try to answer questions frequently asked by our users.
     - See the overview site for the [tracking challenge](https://www.nuscenes.org/tracking).
 
 - What's next for nuScenes?
-    - A map expansion kit with 20+ different semantic layers (e.g. lanes, stop lines, traffic lights).
     - Raw IMU & GPS data.
     - Object detection, tracking and other challenges (see above).
 
 - How can I get more information on the sensors used?
     - Read the [Data collection](https://www.nuscenes.org/data-collection) page.
-    - Note that we do not give away the vendor name and model to avoid endorsing a particular vendor. All sensors are publicly available from third-party vendors.
+    - Note that we do not *publicly* reveal the vendor name and model to avoid endorsing a particular vendor. All sensors are publicly available from third-party vendors.
     - For more information, please contact [[email protected]](mailto:[email protected]).
 
 - Can I use nuScenes for 2d object detection?
@@ -39,4 +29,4 @@ On this page we try to answer questions frequently asked by our users.
 
 - How can I share my new dataset / paper for Autonomous Driving?
     - Please contact [[email protected]](mailto:[email protected]) to discuss possible collaborations and listing your work on the [Publications](https://www.nuscenes.org/publications) page.
-    - To discuss it with the community, please post in the [nuScenes user forum](https://forum.nuscenes.org/).
+    - To discuss it with the community, please post in the [nuScenes user forum](https://forum.nuscenes.org/). 

python-sdk/nuscenes/eval/detection/data_classes.py

@@ -98,7 +98,7 @@ def __init__(self,
         assert not np.any(np.isnan(rotation)), 'Error: Rotation may not be NaN!'
 
         # Velocity can be NaN from our database for certain annotations.
-        assert len(velocity) == 2, 'Error: Rotation must have 2 elements!'
+        assert len(velocity) == 2, 'Error: Velocity must have 2 elements!'
 
         assert detection_name is not None, 'Error: detection_name cannot be empty!'
         assert detection_name in DETECTION_NAMES, 'Error: Unknown detection_name %s' % detection_name