-
The field of autonomous driving has moved towards bird's eye view (BEV) and 3D perception in recent times e.g: [BEVFormer](https://arxiv.org/abs/2203.17270), [SimpleBEV](https://arxiv.org/abs/2206.079…
-
I hope to add `3D Ground Truth` sensor to collect data for 3D object detection(LiDAR).
In this case, should the `transform` of `3D Ground Truth` sensor be the same as `transform` of Lidar sensor?
ht…
-
Hi @vasgaowei, thanks for meticulously maintaining this informative repository!
To further enhance the comprehensiveness of this repository, I would like to recommend the following papers under the…
-
As there exists the message [`sensor_msgs/RegionOfInterest`](http://docs.ros.org/melodic/api/sensor_msgs/html/msg/RegionOfInterest.html), we should remove our `mas_perception_msgs/BoundingBox2D` in fa…
-
Thanks for your great work!
In the docs, 3D map data is provided in the 1.4.2 version Perception dataset, but how can I load it from tfrecord files? I've tried frames[i].map_features, but len(frames[…
-
In the CNN in the perception module, there exists a category_score and confidence_score. The category_score is used with the objectness_thresh to determine if something is an object and the confidenc…
-
- dynamic following
- point to point navigation #56
- perception processing #55 (2D, 3D camera, dynamic, radar, sonar, 3D lidar, etc)
- planners
- controllers
- custom BT nodes + BT navigator lo…
-
Hi @Gofinge thanks for releasing the code!
The main datasets that PTv3 has been trained on are quite large in scale (Waymo or room-level datasets). Would you recommend any hyperparameters or best p…
-
## What
Add support of loading `PerceptionEvaluationConfig` from scenario file in yaml format.
As a first step, we start from support of the scenario file like as below.
```yaml
ScenarioFormat…
-
For example, the figure of the network structure is missing at this link:
https://github.com/ApolloAuto/apollo/blob/master/docs/specs/images/3d_obstacle_perception/camera_network.png