Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point -- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors. CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with 28.1% AP at 142 FPS, 37.4% AP at 52 FPS, and 45.1% AP with multi-scale testing at 1.4 FPS. We use the same approach to estimate 3D bounding box in the KITTI benchmark and human pose on the COCO keypoint dataset. Our method performs competitively with sophisticated multi-stage methods and runs in real-time.
## Highlights
- **Simple:** One-sentence method summary: use keypoint detection technic to detect the bounding box center point and regress to all other object properties like bounding box size, 3d information, and pose.
- **Versatile:** The same framework works for object detection, 3d bounding box estimation, and multi-person pose estimation with minor modification.
- **Fast:** The whole process in a single network feedforward. No NMS post processing is needed. Our DLA-34 model runs at *52* FPS with *37.4* COCO AP.
- **Strong**: Our best single model achieves *45.1*AP on COCO test-dev.
- **Easy to use:** We provide user friendly testing API and webcam demos.
## Main results
### Object Detection on COCO validation
| Backbone | AP / FPS | Flip AP / FPS| Multi-scale AP / FPS |
We provide example images in `CenterNet_ROOT/images/` (from [Detectron](https://github.com/facebookresearch/Detectron/tree/master/demo)). If set up correctly, the output should look like
`ret` will be a python dict: `{category_id : [[x1, y1, x2, y2, score], ...], }`
## Benchmark Evaluation and Training
After [installation](readme/INSTALL.md), follow the instructions in [DATA.md](readme/DATA.md) to setup the datasets. Then check [GETTING_STARTED.md](readme/GETTING_STARTED.md) to reproduce the results in the paper.
We provide scripts for all the experiments in the [experiments](experiments) folder.
## Develop
If you are interested in training CenterNet in a new dataset, use CenterNet in a new task, or use a new network architecture for CenterNet, please refer to [DEVELOP.md](readme/DEVELOP.md). Also feel free to send us emails for discussions or suggestions.
Portions of the code are borrowed from [human-pose-estimation.pytorch](https://github.com/Microsoft/human-pose-estimation.pytorch) (image transform, resnet), [CornerNet](https://github.com/princeton-vl/CornerNet) (hourglassnet, loss functions), [dla](https://github.com/ucbdrive/dla) (DLA network), [DCNv2](https://github.com/CharlesShang/DCNv2)(deformable convolutions), [tf-faster-rcnn](https://github.com/endernewton/tf-faster-rcnn)(Pascal VOC evaluation) and [kitti_eval](https://github.com/prclibo/kitti_eval) (KITTI dataset evaluation). Please refer to the original License of these projects (See [NOTICE](NOTICE)).
