# xingyizhou/centernet

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/xingyizhou-centernet).**

7,565 stars · 1,935 forks · Python · MIT

## Links

- GitHub: https://github.com/xingyizhou/CenterNet
- awesome-repositories: https://awesome-repositories.com/repository/xingyizhou-centernet.md

## Description

CenterNet is a center point object detection framework and real-time computer vision pipeline. It identifies objects and poses by predicting center points instead of using anchor boxes.

The system functions as a 3D bounding box estimator, a human pose estimation model, and a tool for real-time object detection. It treats the placement of joints and object locations as center point detection problems to locate entities in images and three-dimensional space.

Capabilities cover 3D object detection, human keypoint estimation, and live video analysis. The pipeline uses a single-stage feedforward inference process to perform continuous analysis on webcams or video files.

## Tags

### Artificial Intelligence & ML

- [Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection.md) — Identifies and locates objects within images using center points and bounding box dimensions. ([source](https://github.com/xingyizhou/centernet#readme))
- [Human](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations/computer-vision-models/pose-estimation-models/human.md) — Identifies human body joints and limbs by treating pose estimation as center point detection. ([source](https://github.com/xingyizhou/centernet#readme))
- [3D Bounding Box Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-detection/3d-bounding-box-generation.md) — Estimates the location, orientation, and size of objects in three-dimensional space. ([source](https://github.com/xingyizhou/centernet#readme))
- [Bounding Box Regression](https://awesome-repositories.com/f/artificial-intelligence-ml/bounding-box-regression.md) — Predicts the dimensions of objects from center points to reconstruct 3D and 2D bounding boxes.
- [Center-Point Localization](https://awesome-repositories.com/f/artificial-intelligence-ml/center-point-localization.md) — Implements an anchor-free architecture that identifies objects by predicting their center points.
- [3D](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection/3d.md) — Locates and classifies objects within three-dimensional space using center point coordinates.
- [Anchor-Free Detection Models](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/object-detection/anchor-free-detection-models.md) — Implements an anchor-free detection framework that regresses objects from center points.
- [Real-Time Object Detection](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-systems/computer-vision/object-detection-tracking/real-time-object-detection.md) — Identifies and tracks objects within live video streams using a fast center-point approach.
- [Keypoint Estimation Models](https://awesome-repositories.com/f/artificial-intelligence-ml/positional-encodings/spatial-coordinate-encodings/heatmap-encodings/keypoint-estimation-models.md) — Predicts human joint locations and object centers using 2D spatial heatmaps.
- [Single-Stage Detectors](https://awesome-repositories.com/f/artificial-intelligence-ml/single-stage-detectors.md) — Processes images through a one-pass convolutional network for high-throughput real-time detection.
- [Computer Vision Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/computer-vision-pipelines.md) — Provides a feedforward vision pipeline for high-speed analysis of live video streams.
- [Local Maximum Pooling](https://awesome-repositories.com/f/artificial-intelligence-ml/local-maximum-pooling.md) — Uses peak-finding algorithms to isolate individual detections from predicted heatmaps.
- [Post-Inference Bounding Box Refinements](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis/machine-learning-evaluation/detection-model-validation/bounding-box-refinement-techniques/post-inference-bounding-box-refinements.md) — Predicts local offsets to correct quantization errors and refine bounding box precision.

### Graphics & Multimedia

- [Live Video Analysis](https://awesome-repositories.com/f/graphics-multimedia/live-video-analysis.md) — Performs continuous object and pose detection from webcams or video files in real time.
- [Real-Time Video Analysis](https://awesome-repositories.com/f/graphics-multimedia/media-processing-analysis/media-manipulation/media-processing-workflows/video-transformation-enhancement/chunked-video-processing/video-processing-apis/video-input-processing/real-time-video-analysis.md) — Provides high-throughput processing of live video frames for immediate object and pose detection. ([source](https://github.com/xingyizhou/centernet#readme))

### Part of an Awesome List

- [3D Detection and Segmentation](https://awesome-repositories.com/f/awesome-lists/ai/3d-detection-and-segmentation.md) — Anchor-free object detection using center points.
- [Computer Vision](https://awesome-repositories.com/f/awesome-lists/ai/computer-vision.md) — Object detection using point-based estimation.
- [Object Detection](https://awesome-repositories.com/f/awesome-lists/ai/object-detection.md) — Object detection approach treating objects as points.
- [CNN](https://awesome-repositories.com/f/awesome-lists/more/cnn.md) — Listed in the “CNN” section of the Ailia Models awesome list.