Add Ultralytics YOLO pose detector and update documentation.

This commit is contained in:
jaykin-jmsc-aiml
2025-09-24 16:03:52 +05:30
parent 7e2f5a3017
commit e57ed4e8a2
8 changed files with 297 additions and 9 deletions
+22 -1
View File
@@ -58,7 +58,7 @@ This does not affect using hardware for accelerating other tasks such as [semant
# Officially Supported Detectors
Frigate provides the following builtin detector types: `cpu`, `edgetpu`, `hailo8l`, `memryx`, `onnx`, `openvino`, `rknn`, and `tensorrt`. By default, Frigate will use a single CPU detector. Other detectors may require additional configuration as described below. When using multiple detectors they will run in dedicated processes, but pull from a common queue of detection requests from across all cameras.
Frigate provides the following builtin detector types: `cpu`, `edgetpu`, `hailo8l`, `memryx`, `onnx`, `openvino`, `rknn`, `tensorrt`, and `ultralytics_pose`. By default, Frigate will use a single CPU detector. Other detectors may require additional configuration as described below. When using multiple detectors they will run in dedicated processes, but pull from a common queue of detection requests from across all cameras.
## Edge TPU Detector
@@ -141,6 +141,27 @@ detectors:
---
## Ultralytics Pose Detector
The Ultralytics Pose detector runs a YOLO pose model and depends on the `ultralytics` package. To configure an Ultralytics Pose detector, set the `"type"` attribute to `"ultralytics_pose"`.
:::note
The `model_type` must be set to `yolo-pose` for this detector to work correctly.
:::
### Configuration
```yaml
detectors:
pose:
type: ultralytics_pose
device: cpu # or cuda for nvidia gpus
half_precision: False # optional, runs the model in half precision (GPU only)
max_detections: 20 # optional, maximum number of detections to return
```
---
## Hailo-8
This detector is available for use with both Hailo-8 and Hailo-8L AI Acceleration Modules. The integration automatically detects your hardware architecture via the Hailo CLI and selects the appropriate default model if no custom model is specified.