Method Details
Details for method '3D-GCK'
Method overview
| name | 3D-GCK |
| challenge | 3D vehicle detection |
| details | 3D-GCK is based on the standard SSD 2D object detection framework and lifts the 2D detections to 3D space by predicting additional regression and classification parameters. Hence, the runtime is kept close to pure 2D object detection. The additional parameters are transformed to 3D bounding box keypoints within the network under geometric constraints. 3D-GCK features a full 3D description including all three angles of rotation without supervision by any labeled ground truth data for the object’s orientation, as it focuses on certain keypoints within the image plane. |
| publication | Single-Shot 3D Detection of Vehicles from Monocular RGB Images via Geometry Constrained Keypoints in Real-Time Nils Gählert, Jun-Jun Wan, Nicolas Jourdan, Jan Finkbeiner, Uwe Franke, and Joachim Denzler IV 2020 https://arxiv.org/abs/2006.13084 |
| project page / code | |
| used Cityscapes data | 3D bounding boxes |
| used external data | ImageNet |
| runtime | 0.05 s NVIDIA V100 |
| subsampling | no |
| submission date | October, 2020 |
| previous submissions |
Average results
| Metric | Value |
|---|---|
| Detection Score | 30.4674 |
| AP | 34.2889 |
| Center Distance | 96.538 |
| Size Similarity | 70.9601 |
| Orientation Similarity Yaw | 82.2345 |
| Orientation Similarity Pitch Roll | 99.9749 |
Class results
| Class | Detection Score |
|---|---|
| car | 66.3711 |
| truck | 21.1726 |
| bus | 25.1725 |
| train | 12.697 |
| motorcycle | 25.3173 |
| bicycle | 32.0742 |
Results json
This json can be visualized using the tool csPlot3dDetectionResults,
which is part of the cityscapesScripts found on
Github.