Supervision

- Added [256](https://github.com/roboflow/supervision/pull/256): support for ByteTrack for object tracking with [`sv.ByteTrack`](/0.13.0/tracker/core/#bytetrack).

- Added [222](https://github.com/roboflow/supervision/pull/222): [`sv.Detections.from_ultralytics`](/0.13.0/detection/core/#supervision.detection.core.Detections.from_ultralytics) to enable seamless integration with [Ultralytics](https://github.com/ultralytics/ultralytics) framework. This will enable you to use `supervision` with all [models](https://docs.ultralytics.com/models/) that Ultralytics supports.

!!! failure "Deprecated"

[`sv.Detections.from_yolov8`](/0.13.0/detection/core/supervision.detection.core.Detections.from_yolov8) is now deprecated and will be removed with `supervision-0.15.0` release.

- Added [191](https://github.com/roboflow/supervision/pull/191): [`sv.Detections.from_paddledet`](/0.13.0/detection/core/#supervision.detection.core.Detections.from_paddledet) to enable seamless integration with [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) framework.

- Added [245](https://github.com/roboflow/supervision/pull/245): support for loading PASCAL VOC segmentation datasets with [`sv.DetectionDataset.`](/0.13.0/dataset/core/#supervision.dataset.core.DetectionDataset.from_pascal_voc).

- No removals or deprecations in this release!

- Essential update to the [`LineZone`](https://supervision.roboflow.com/0.25.0/detection/tools/line_zone/): when computing line crossings, detections that jitter might be counted twice (or more). This can now be solved with the `minimum_crossing_threshold` argument. If you set it to `2` or more, extra frames will be used to confirm the crossing, improving the accuracy significantly. ([#1540](https://github.com/roboflow/supervision/pull/1540))

- It is now possible to track objects detected as [`KeyPoints`](https://supervision.roboflow.com/0.25.0/keypoint/core/#supervision.keypoint.core.KeyPoints). See the complete step-by-step guide in the [Object Tracking Guide](https://supervision.roboflow.com/latest/how_to/track_objects/#keypoints). ([1658](https://github.com/roboflow/supervision/pull/1658))

python
import numpy as np
import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8m-pose.pt")
tracker = sv.ByteTrack()
trace_annotator = sv.TraceAnnotator()

def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model(frame)[0]
key_points = sv.KeyPoints.from_ultralytics(results)

detections = key_points.as_detections()
detections = tracker.update_with_detections(detections)

annotated_image = trace_annotator.annotate(frame.copy(), detections)
return annotated_image

sv.process_video(
source_path="input_video.mp4",
target_path="output_video.mp4",
callback=callback
)


- Added `is_empty` method to [`KeyPoints`](https://supervision.roboflow.com/0.25.0/keypoint/core/#supervision.keypoint.core.KeyPoints) to check if there are any keypoints in the object. ([1658](https://github.com/roboflow/supervision/pull/1658))

- Added `as_detections` method to [`KeyPoints`](https://supervision.roboflow.com/0.25.0/keypoint/core/#supervision.keypoint.core.KeyPoints) that converts `KeyPoints` to `Detections`. ([1658](https://github.com/roboflow/supervision/pull/1658))

- Added a new video to `supervision[assets]`. ([1657](https://github.com/roboflow/supervision/pull/1657))

python
from supervision.assets import download_assets, VideoAssets

path_to_video = download_assets(VideoAssets.SKIING)


- Supervision can now be used with [`Python 3.13`](https://docs.python.org/3/whatsnew/3.13.html). The most renowned update is the ability to run Python [without Global Interpreter Lock (GIL)](https://docs.python.org/3/whatsnew/3.13.html#whatsnew313-free-threaded-cpython). We expect support for this among our dependencies to be inconsistent, but if you do attempt it - let us know the results! ([1595](https://github.com/roboflow/supervision/pull/1595))

- Added [`Mean Average Recall`](https://supervision.roboflow.com/latest/metrics/mean_average_recall/) mAR metric, which returns a recall score, averaged over IoU thresholds, detected object classes, and limits imposed on maximum considered detections. ([#1661](https://github.com/roboflow/supervision/pull/1661))

python
import supervision as sv
from supervision.metrics import MeanAverageRecall

predictions = sv.Detections(...)
targets = sv.Detections(...)

map_metric = MeanAverageRecall()
map_result = map_metric.update(predictions, targets).compute()

map_result.plot()


- Added [`Precision`](https://supervision.roboflow.com/latest/metrics/precision/) and [`Recall`](https://supervision.roboflow.com/latest/metrics/recall/) metrics, providing a baseline for comparing model outputs to ground truth or another model ([#1609](https://github.com/roboflow/supervision/pull/1609))

python
import supervision as sv
from supervision.metrics import Recall

predictions = sv.Detections(...)
targets = sv.Detections(...)

recall_metric = Recall()
recall_result = recall_metric.update(predictions, targets).compute()

recall_result.plot()


- All Metrics now support Oriented Bounding Boxes (OBB) ([1593](https://github.com/roboflow/supervision/pull/1593))

python
import supervision as sv
from supervision.metrics import F1_Score

predictions = sv.Detections(...)
targets = sv.Detections(...)

f1_metric = MeanAverageRecall(metric_target=sv.MetricTarget.ORIENTED_BOUNDING_BOXES)
f1_result = f1_metric.update(predictions, targets).compute()


- Introducing Smart Labels! When `smart_position` is set for [`LabelAnnotator`](https://supervision.roboflow.com/0.25.0/detection/annotators/#supervision.annotators.core.LabelAnnotator), [`RichLabelAnnotator`](https://supervision.roboflow.com/0.25.0/detection/annotators/#supervision.annotators.core.RichLabelAnnotator) or [`VertexLabelAnnotator`](https://supervision.roboflow.com/0.25.0/detection/annotators/#supervision.annotators.core.RichLabelAnnotator), the labels will move around to avoid overlapping others. ([1625](https://github.com/roboflow/supervision/pull/1625))

python
import supervision as sv
from ultralytics import YOLO

image = cv2.imread("image.jpg")

label_annotator = sv.LabelAnnotator(smart_position=True)

model = YOLO("yolo11m.pt")
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)

annotated_frame = label_annotator.annotate(first_frame.copy(), detections)
sv.plot_image(annotated_frame)


- Added the `metadata` variable to [`Detections`](https://supervision.roboflow.com/0.25.0/detection/core/#supervision.detection.core.Detections). It allows you to store custom data per-image, rather than per-detected-object as was possible with `data` variable. For example, `metadata` could be used to store the source video path, camera model or camera parameters. ([1589](https://github.com/roboflow/supervision/pull/1589))

python
import supervision as sv
from ultralytics import YOLO

model = YOLO("yolov8m")

result = model("image.png")[0]
detections = sv.Detections.from_ultralytics(result)

Items in `data` must match length of detections
object_ids = [num for num in range(len(detections))]
detections.data["object_number"] = object_ids

Items in `metadata` can be of any length.
detections.metadata["camera_model"] = "Luxonis OAK-D"


- Added a `py.typed` type hints metafile. It should provide a stronger signal to type annotators and IDEs that type support is available. ([1586](https://github.com/roboflow/supervision/pull/1586))

- `ByteTrack` no longer requires `detections` to have a `class_id` ([1637](https://github.com/roboflow/supervision/pull/1637))
- `draw_line`, `draw_rectangle`, `draw_filled_rectangle`, `draw_polygon`, `draw_filled_polygon` and `PolygonZoneAnnotator` now comes with a default color ([1591](https://github.com/roboflow/supervision/pull/1591))
- Dataset classes are treated as case-sensitive when merging multiple datasets. ([1643](https://github.com/roboflow/supervision/pull/1643))
- Expanded [metrics documentation](https://supervision.roboflow.com/0.25.0/metrics/f1_score/) with example plots and printed results ([#1660](https://github.com/roboflow/supervision/pull/1660))
- Added usage example for polygon zone ([1608](https://github.com/roboflow/supervision/pull/1608))
- Small improvements to error handling in polygons: ([1602](https://github.com/roboflow/supervision/pull/1602))

- Updated [`ByteTrack`](https://supervision.roboflow.com/0.25.0/trackers/#supervision.tracker.byte_tracker.core.ByteTrack), removing shared variables. Previously, multiple instances of `ByteTrack` would share some date, requiring liberal use of `tracker.reset()`. ([1603](https://github.com/roboflow/supervision/pull/1603)), ([#1528](https://github.com/roboflow/supervision/pull/1528))
- Fixed a bug where `class_agnostic` setting in `MeanAveragePrecision` would not work. ([1577](https://github.com/roboflow/supervision/pull/1577)) hacktoberfest
- Removed welcome workflow from our CI system. ([1596](https://github.com/roboflow/supervision/pull/1596))

- Large refactor of `ByteTrack`: STrack moved to separate class, removed superfluous `BaseTrack` class, removed unused variables ([1603](https://github.com/roboflow/supervision/pull/1603))
- Large refactor of `RichLabelAnnotator`, matching its contents with `LabelAnnotator`. ([1625](https://github.com/roboflow/supervision/pull/1625))

- Added [F1 score](https://supervision.roboflow.com/0.24.0/metrics/f1_score/#supervision.metrics.f1_score.F1Score) as a new metric for detection and segmentation. [1521](https://github.com/roboflow/supervision/pull/1521)

python
import supervision as sv
from supervision.metrics import F1Score

predictions = sv.Detections(...)
targets = sv.Detections(...)

f1_metric = F1Score()
f1_result = f1_metric.update(predictions, targets).compute()

print(f1_result)
print(f1_result.f1_50)
print(f1_result.small_objects.f1_50)


- Added new cookbook: [Small Object Detection with SAHI](https://supervision.roboflow.com/0.24.0/notebooks/small-object-detection-with-sahi/). This cookbook provides a detailed guide on using [`InferenceSlicer`](https://supervision.roboflow.com/0.24.0/detection/tools/inference_slicer/) for small object detection. [#1483](https://github.com/roboflow/supervision/pull/1483)

- Added an [Embedded Workflow](https://roboflow.com/workflows), which allows you to [preview annotators](https://supervision.roboflow.com/0.24.0/detection/annotators/). [#1533](https://github.com/roboflow/supervision/pull/1533)

- Enhanced [`LineZoneAnnotator`](https://supervision.roboflow.com/0.24.0/detection/tools/line_zone/#supervision.detection.line_zone.LineZoneAnnotator), allowing the labels to align with the line, even when it's not horizontal. Also, you can now disable text background, and choose to draw labels off-center which minimizes overlaps for multiple [`LineZone`](https://supervision.roboflow.com/0.24.0/detection/tools/line_zone/#supervision.detection.line_zone.LineZone) labels. [854](https://github.com/roboflow/supervision/pull/854)

python
import supervision as sv
import cv2

image = cv2.imread("<SOURCE_IMAGE_PATH>")

line_zone = sv.LineZone(
start=sv.Point(0, 100),
end=sv.Point(50, 200)
)
line_zone_annotator = sv.LineZoneAnnotator(
text_orient_to_line=True,
display_text_box=False,
text_centered=False
)

annotated_frame = line_zone_annotator.annotate(
frame=image.copy(), line_counter=line_zone
)

sv.plot_image(frame)


- Added per-class counting capabilities to [`LineZone`](https://supervision.roboflow.com/0.24.0/detection/tools/line_zone/#supervision.detection.line_zone.LineZone) and introduced [`LineZoneAnnotatorMulticlass`](https://supervision.roboflow.com/0.24.0/detection/tools/line_zone/#supervision.detection.line_zone.LineZoneAnnotatorMulticlass) for visualizing the counts per class. This feature allows tracking of individual classes crossing a line, enhancing the flexibility of use cases like traffic monitoring or crowd analysis. [1555](https://github.com/roboflow/supervision/pull/1555)

python
import supervision as sv
import cv2

image = cv2.imread("<SOURCE_IMAGE_PATH>")

line_zone = sv.LineZone(
start=sv.Point(0, 100),
end=sv.Point(50, 200)
)
line_zone_annotator = sv.LineZoneAnnotatorMulticlass()

frame = line_zone_annotator.annotate(
frame=frame, line_zones=[line_zone]
)

sv.plot_image(frame)


- Added [`from_easyocr`](https://supervision.roboflow.com/0.24.0/detection/core/#supervision.detection.core.Detections.from_easyocr), allowing integration of OCR results into the supervision framework. [EasyOCR](https://github.com/JaidedAI/EasyOCR) is an open-source optical character recognition (OCR) library that can read text from images. [#1515](https://github.com/roboflow/supervision/pull/1515)

python
import supervision as sv
import easyocr
import cv2

image = cv2.imread("<SOURCE_IMAGE_PATH>")

reader = easyocr.Reader(["en"])
result = reader.readtext("<SOURCE_IMAGE_PATH>", paragraph=True)
detections = sv.Detections.from_easyocr(result)

box_annotator = sv.BoxAnnotator(color_lookup=sv.ColorLookup.INDEX)
label_annotator = sv.LabelAnnotator(color_lookup=sv.ColorLookup.INDEX)

annotated_image = image.copy()
annotated_image = box_annotator.annotate(scene=annotated_image, detections=detections)
annotated_image = label_annotator.annotate(scene=annotated_image, detections=detections)

sv.plot_image(annotated_image)


- Added [`oriented_box_iou_batch`](https://supervision.roboflow.com/0.24.0/detection/utils/#supervision.detection.utils.oriented_box_iou_batch) function to `detection.utils`. This function computes Intersection over Union (IoU) for oriented or rotated bounding boxes (OBB). [1502](https://github.com/roboflow/supervision/pull/1502)

python
import numpy as np

boxes_true = np.array([[[1, 0], [0, 1], [3, 4], [4, 3]]])
boxes_detection = np.array([[[1, 1], [2, 0], [4, 2], [3, 3]]])
ious = sv.oriented_box_iou_batch(boxes_true, boxes_detection)
print("IoU between true and detected boxes:", ious)


- Extended [`PolygonZoneAnnotator`](https://supervision.roboflow.com/0.24.0/detection/tools/polygon_zone/#supervision.detection.tools.polygon_zone.PolygonZoneAnnotator) to allow setting opacity when drawing zones, providing enhanced visualization by filling the zone with adjustable transparency. [1527](https://github.com/roboflow/supervision/pull/1527)

python
import cv2
from ncnn.model_zoo import get_model
import supervision as sv

image = cv2.imread("<SOURCE_IMAGE_PATH>")
model = get_model(
"yolov8s",
target_size=640,
prob_threshold=0.5,
nms_threshold=0.45,
num_threads=4,
use_gpu=True,
)
result = model(image)
detections = sv.Detections.from_ncnn(result)


!!! failure "Removed"

The `frame_resolution_wh` parameter in [`PolygonZone`](https://supervision.roboflow.com/0.24.0/detection/tools/polygon_zone/#supervision.detection.tools.polygon_zone.PolygonZone) has been removed.

!!! failure "Removed"

Supervision installation methods `"headless"` and `"desktop"` were removed, as they are no longer needed. `pip install supervision[headless]` will install the base library and harmlessly warn of non-existent extras.

- Supervision now depends on `opencv-python` rather than `opencv-python-headless`. [1530](https://github.com/roboflow/supervision/pull/1530)

- Fixed the COCO 101 point Average Precision algorithm to correctly interpolate precision, providing a more precise calculation of average precision without averaging out intermediate values. [1500](https://github.com/roboflow/supervision/pull/1500)

- Resolved miscellaneous issues highlighted when building documentation. This mostly includes whitespace adjustments and type inconsistencies. Updated documentation for clarity and fixed formatting issues. Added explicit version for `mkdocstrings-python`. [1549](https://github.com/roboflow/supervision/pull/1549)

- Enabled and fixed Ruff rules for code formatting, including changes like avoiding unnecessary iterable allocations and using Optional for default mutable arguments. [1526](https://github.com/roboflow/supervision/pull/1526)

- Added [930](https://github.com/roboflow/supervision/pull/930): `IconAnnotator`, a [new annotator](https://supervision.roboflow.com/0.23.0/detection/annotators/#supervision.annotators.core.IconAnnotator) that allows drawing icons on each detection. Useful if you want to draw a specific icon for each class.

python
import supervision as sv
from inference import get_model

image = <SOURCE_IMAGE_PATH>
icon_dog = <DOG_PNG_PATH>
icon_cat = <CAT_PNG_PATH>

model = get_model(model_id="yolov8n-640")
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

icon_paths = []
for class_name in detections.data["class_name"]:
if class_name == "dog":
icon_paths.append(icon_dog)
elif class_name == "cat":
icon_paths.append(icon_cat)
else:
icon_paths.append("")

icon_annotator = sv.IconAnnotator()
annotated_frame = icon_annotator.annotate(
scene=image.copy(),
detections=detections,
icon_path=icon_paths
)


- Added [1385](https://github.com/roboflow/supervision/pull/1385): [`BackgroundColorAnnotator`](https://supervision.roboflow.com/0.23.0/detection/annotators/#supervision.annotators.core.BackgroundColorAnnotator), that draws an overlay on the background images of the detections.

python
import supervision as sv
from inference import get_model

image = <SOURCE_IMAGE_PATH>

model = get_model(model_id="yolov8n-640")
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

background_overlay_annotator = sv.BackgroundOverlayAnnotator()
annotated_frame = background_overlay_annotator.annotate(
scene=image.copy(),
detections=detections
)


- Added [1386](https://github.com/roboflow/supervision/pull/1386): Support for Transformers v5 functions in [`sv.Detections.from_transformers`](https://supervision.roboflow.com/0.23.0/detection/core/#supervision.detection.core.Detections.from_transformers). This includes the `DetrImageProcessor` methods `post_process_object_detection`, `post_process_panoptic_segmentation`, `post_process_semantic_segmentation`, and `post_process_instance_segmentation`.

python
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection

processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")

image = Image.open(<SOURCE_IMAGE_PATH>)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
outputs = model(**inputs)

width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label)


- Added [1354](https://github.com/roboflow/supervision/pull/1354): Ultralytics SAM (Segment Anything Model) support in [`sv.Detections.from_ultralytics`](https://supervision.roboflow.com/0.23.0/detection/core/#supervision.detection.core.Detections.from_ultralytics). [SAM2](https://sam2.metademolab.com/) was released during this update, and is already supported via [`sv.Detections.from_sam`](https://supervision.roboflow.com/0.23.0/detection/core/#supervision.detection.core.Detections.from_sam).

python
import supervision as sv
from segment_anything import (
sam_model_registry,
SamAutomaticMaskGenerator
)
sam_model_reg = sam_model_registry[MODEL_TYPE]
sam = sam_model_reg(checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
mask_generator = SamAutomaticMaskGenerator(sam)
sam_result = mask_generator.generate(IMAGE)
detections = sv.Detections.from_sam(sam_result=sam_result)


- Added [1458](https://github.com/roboflow/supervision/pull/1458): `outline_color` options for [`TriangleAnnotator`](https://supervision.roboflow.com/0.23.0/detection/annotators/#supervision.annotators.core.TriangleAnnotator) and [`DotAnnotator`](https://supervision.roboflow.com/0.23.0/detection/annotators/#supervision.annotators.core.DotAnnotator).

- Added [1409](https://github.com/roboflow/supervision/pull/1409): `text_color` option for [`VertexLabelAnnotator`](https://supervision.roboflow.com/0.23.0/keypoint/annotators/#supervision.keypoint.annotators.VertexLabelAnnotator) keypoint annotator.

- Changed [1434](https://github.com/roboflow/supervision/pull/1434): [`InferenceSlicer`](https://supervision.roboflow.com/0.23.0/detection/tools/inference_slicer/) now features an `overlap_wh` parameter, making it easier to compute slice sizes when handling overlapping slices.

- Fix [1448](https://github.com/roboflow/supervision/pull/1448): Various annotator type issues have been resolved, supporting expanded error handling.

- Fix [1348](https://github.com/roboflow/supervision/pull/1348): Introduced a new method for [seeking to a specific video frame](https://supervision.roboflow.com/0.23.0/utils/video/#supervision.utils.video.get_video_frames_generator), addressing cases where traditional seek methods were failing. It can be enabled with `iterative_seek=True`.

python
import supervision as sv

for frame in sv.get_video_frames_generator(
source_path=<SOURCE_VIDEO_PATH>,
start=60,
iterative_seek=True
):
...


- Fix [1424](https://github.com/roboflow/supervision/pull/1424): `plot_image` function now clearly indicates that the size is in inches.

!!! failure "Removed"

The `track_buffer`, `track_thresh`, and `match_thresh` parameters in [`ByteTrack`](trackers.md/supervision.tracker.byte_tracker.core.ByteTrack) are deprecated and were removed as of `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.

!!! failure "Removed"

The `triggering_position` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/supervision.detection.tools.polygon_zone.PolygonZone) was removed as of `supervision-0.23.0`. Use `triggering_anchors` instead.

!!! failure "Deprecated"

`overlap_filter_strategy` in `InferenceSlicer.__init__` is deprecated and will be removed in `supervision-0.27.0`. Use `overlap_strategy` instead.

!!! failure "Deprecated"

`overlap_ratio_wh` in `InferenceSlicer.__init__` is deprecated and will be removed in `supervision-0.27.0`. Use `overlap_wh` instead.

- Added [1326](https://github.com/roboflow/supervision/pull/1326): [`sv.DetectionsDataset`](https://supervision.roboflow.com/0.22.0/datasets/core/#supervision.dataset.core.DetectionDataset) and [`sv.ClassificationDataset`](https://supervision.roboflow.com/0.22.0/datasets/core/#supervision.dataset.core.ClassificationDataset) allowing to load the images into memory only when necessary (lazy loading).

!!! failure "Deprecated"

Constructing `DetectionDataset` with parameter `images` as `Dict[str, np.ndarray]` is deprecated and will be removed in `supervision-0.26.0`. Please pass a list of paths `List[str]` instead.

!!! failure "Deprecated"

The `DetectionDataset.images` property is deprecated and will be removed in `supervision-0.26.0`. Please loop over images with `for path, image, annotation in dataset:`, as that does not require loading all images into memory.

python
import roboflow
from roboflow import Roboflow
import supervision as sv

roboflow.login()
rf = Roboflow()

project = rf.workspace(<WORKSPACE_ID>).project(<PROJECT_ID>)
dataset = project.version(<PROJECT_VERSION>).download("coco")

ds_train = sv.DetectionDataset.from_coco(
images_directory_path=f"{dataset.location}/train",
annotations_path=f"{dataset.location}/train/_annotations.coco.json",
)

path, image, annotation = ds_train[0]
loads image on demand

for path, image, annotation in ds_train:
loads image on demand


- Added [1296](https://github.com/roboflow/supervision/pull/1296): [`sv.Detections.from_lmm`](https://supervision.roboflow.com/0.22.0/detection/core/#supervision.detection.core.Detections.from_lmm) now supports parsing results from the [Florence 2](https://huggingface.co/microsoft/Florence-2-large) model, extending the capability to handle outputs from this Large Multimodal Model (LMM). This includes detailed object detection, OCR with region proposals, segmentation, and more. Find out more in our [Colab notebook](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-florence-2-on-detection-dataset.ipynb).

- Added [1232](https://github.com/roboflow/supervision/pull/1232) to support keypoint detection with Mediapipe. Both [legacy](https://colab.research.google.com/github/googlesamples/mediapipe/blob/main/examples/pose_landmarker/python/%5BMediaPipe_Python_Tasks%5D_Pose_Landmarker.ipynb) and [modern](https://ai.google.dev/edge/mediapipe/solutions/vision/pose_landmarker/python) pipelines are supported. See [`sv.KeyPoints.from_mediapipe`](https://supervision.roboflow.com/0.22.0/keypoint/core/#supervision.keypoint.core.KeyPoints.from_mediapipe) for more.

- Added [1316](https://github.com/roboflow/supervision/pull/1316): [`sv.KeyPoints.from_mediapipe`](https://supervision.roboflow.com/0.22.0/keypoint/core/#supervision.keypoint.core.KeyPoints.from_mediapipe) extended to support FaceMesh from Mediapipe. This enhancement allows for processing both face landmarks from `FaceLandmarker`, and legacy results from `FaceMesh`.

- Added [1310](https://github.com/roboflow/supervision/pull/1310): [`sv.KeyPoints.from_detectron2`](https://supervision.roboflow.com/0.22.0/keypoint/core/#supervision.keypoint.core.KeyPoints.from_detectron2) is a new `KeyPoints` method, adding support for extracting keypoints from the popular [Detectron 2](https://github.com/facebookresearch/detectron2) platform.

- Added [1300](https://github.com/roboflow/supervision/pull/1300): [`sv.Detections.from_detectron2`](https://supervision.roboflow.com/0.22.0/detection/core/#supervision.detection.core.Detections.from_detectron2) now supports segmentation models detectron2. The resulting masks can be used with [`sv.MaskAnnotator`](https://supervision.roboflow.com/0.22.0/detection/annotators/#supervision.annotators.core.MaskAnnotator) for displaying annotations.

python
import supervision as sv
from detectron2 import model_zoo
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
import cv2

image = cv2.imread(<SOURCE_IMAGE_PATH>)
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
predictor = DefaultPredictor(cfg)

result = predictor(image)
detections = sv.Detections.from_detectron2(result)

mask_annotator = sv.MaskAnnotator()
annotated_frame = mask_annotator.annotate(scene=image.copy(), detections=detections)


- Added [1277](https://github.com/roboflow/supervision/pull/1277): if you provide a font that supports symbols of a language, [`sv.RichLabelAnnotator`](https://supervision.roboflow.com/0.22.0/detection/annotators/#supervision.annotators.core.LabelAnnotator.annotate) will draw them on your images.
- Various other annotators have been revised to ensure proper in-place functionality when used with `numpy` arrays. Additionally, we fixed a bug where `sv.ColorAnnotator` was filling boxes with solid color when used in-place.

python
import cv2
import supervision as sv
import

image = cv2.imread(<SOURCE_IMAGE_PATH>)

model = get_model(model_id="yolov8n-640")
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)

rich_label_annotator = sv.RichLabelAnnotator(font_path=<TTF_FONT_PATH>)
annotated_image = rich_label_annotator.annotate(scene=image.copy(), detections=detections)


- Added [1227](https://github.com/roboflow/supervision/pull/1227): Added support for loading Oriented Bounding Boxes dataset in YOLO format.

python
import supervision as sv

train_ds = sv.DetectionDataset.from_yolo(
images_directory_path="/content/dataset/train/images",
annotations_directory_path="/content/dataset/train/labels",
data_yaml_path="/content/dataset/data.yaml",
is_obb=True,
)

_, image, detections in train_ds[0]

obb_annotator = OrientedBoxAnnotator()
annotated_image = obb_annotator.annotate(scene=image.copy(), detections=detections)


- Fixed [1312](https://github.com/roboflow/supervision/pull/1312): Fixed [`CropAnnotator`](https://supervision.roboflow.com/0.22.0/detection/annotators/#supervision.annotators.core.TraceAnnotator.annotate).

!!! failure "Removed"

`BoxAnnotator` was removed, however `BoundingBoxAnnotator` has been renamed to `BoxAnnotator`. Use a combination of [`BoxAnnotator`](https://supervision.roboflow.com/0.22.0/detection/annotators/#supervision.annotators.core.BoxAnnotator) and [`LabelAnnotator`](https://supervision.roboflow.com/0.22.0/detection/annotators/#supervision.annotators.core.LabelAnnotator) to simulate old `BoundingBox` behavior.

!!! failure "Deprecated"

The name `BoundingBoxAnnotator` has been deprecated and will be removed in `supervision-0.26.0`. It has been renamed to [`BoxAnnotator`](https://supervision.roboflow.com/0.22.0/detection/annotators/#supervision.annotators.core.BoxAnnotator).

- Added [975](https://github.com/roboflow/supervision/pull/975) 📝 New Cookbooks: serialize detections into [json](https://github.com/roboflow/supervision/blob/de896189b83a1f9434c0a37dd9192ee00d2a1283/docs/notebooks/serialise-detections-to-json.ipynb) and [csv](https://github.com/roboflow/supervision/blob/de896189b83a1f9434c0a37dd9192ee00d2a1283/docs/notebooks/serialise-detections-to-csv.ipynb).

- Added [1290](https://github.com/roboflow/supervision/pull/1290): Mostly an internal change, our file utility function now support both `str` and `pathlib` paths.

- Added [1340](https://github.com/roboflow/supervision/pull/1340): Two new methods for converting between bounding box formats - [`xywh_to_xyxy`](https://supervision.roboflow.com/0.22.0/detection/utils/#supervision.detection.utils.xywh_to_xyxy) and [`xcycwh_to_xyxy`](https://supervision.roboflow.com/0.22.0/detection/utils/#supervision.detection.utils.xcycwh_to_xyxy)

!!! failure "Removed"

`from_roboflow` method has been removed due to deprecation. Use [from_inference](https://supervision.roboflow.com/0.22.0/detection/core/#supervision.detection.core.Detections.from_inference) instead.

!!! failure "Removed"

`Color.white()` has been removed due to deprecation. Use `color.WHITE` instead.

!!! failure "Removed"

`Color.black()` has been removed due to deprecation. Use `color.BLACK` instead.

!!! failure "Removed"

`Color.red()` has been removed due to deprecation. Use `color.RED` instead.

!!! failure "Removed"

`Color.green()` has been removed due to deprecation. Use `color.GREEN` instead.

!!! failure "Removed"

`Color.blue()` has been removed due to deprecation. Use `color.BLUE` instead.

!!! failure "Removed"

`ColorPalette.default()` has been removed due to deprecation. Use [ColorPalette.DEFAULT](https://supervision.roboflow.com/0.22.0/utils/draw/#supervision.draw.color.ColorPalette.DEFAULT) instead.

!!! failure "Removed"

`FPSMonitor.__call__` has been removed due to deprecation. Use the attribute [FPSMonitor.fps](https://supervision.roboflow.com/0.22.0/utils/video/#supervision.utils.video.FPSMonitor.fps) instead.

- Added [500](https://github.com/roboflow/supervision/pull/500): [`sv.Detections.with_nmm`](https://supervision.roboflow.com/0.21.0/detection/core/#supervision.detection.core.Detections.with_nmm) to perform non-maximum merging on the current set of object detections.

- Added [1221](https://github.com/roboflow/supervision/pull/1221): [`sv.Detections.from_lmm`](https://supervision.roboflow.com/0.21.0/detection/core/#supervision.detection.core.Detections.from_lmm) allowing to parse Large Multimodal Model (LMM) text result into [`sv.Detections`](https://supervision.roboflow.com/0.21.0/detection/core/) object. For now `from_lmm` supports only [PaliGemma](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma-on-detection-dataset.ipynb) result parsing.

python
import supervision as sv

paligemma_result = "<loc0256><loc0256><loc0768><loc0768> cat"
detections = sv.Detections.from_lmm(
sv.LMM.PALIGEMMA,
paligemma_result,
resolution_wh=(1000, 1000),
classes=["cat", "dog"],
)
detections.xyxy
array([[250., 250., 750., 750.]])

detections.class_id
array([0])


- Added [1236](https://github.com/roboflow/supervision/pull/1236): [`sv.VertexLabelAnnotator`](https://supervision.roboflow.com/0.21.0/keypoint/annotators/#supervision.keypoint.annotators.EdgeAnnotator.annotate) allowing to annotate every vertex of a keypoint skeleton with custom text and color.

python
import supervision as sv

image = ...
key_points = sv.KeyPoints(...)

edge_annotator = sv.EdgeAnnotator(
color=sv.Color.GREEN,
thickness=5
)
annotated_frame = edge_annotator.annotate(
scene=image.copy(),
key_points=key_points
)


- Added [1147](https://github.com/roboflow/supervision/pull/1147): [`sv.KeyPoints.from_inference`](https://supervision.roboflow.com/0.21.0/keypoint/core/#supervision.keypoint.core.KeyPoints.from_inference) allowing to create [`sv.KeyPoints`](https://supervision.roboflow.com/0.21.0/keypoint/core/#supervision.keypoint.core.KeyPoints) from [Inference](https://github.com/roboflow/inference) result.

- Added [1138](https://github.com/roboflow/supervision/pull/1138): [`sv.KeyPoints.from_yolo_nas`](https://supervision.roboflow.com/0.21.0/keypoint/core/#supervision.keypoint.core.KeyPoints.from_yolo_nas) allowing to create [`sv.KeyPoints`](https://supervision.roboflow.com/0.21.0/keypoint/core/#supervision.keypoint.core.KeyPoints) from [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) result.

- Added [1163](https://github.com/roboflow/supervision/pull/1163): [`sv.mask_to_rle`](https://supervision.roboflow.com/0.21.0/datasets/utils/#supervision.dataset.utils.rle_to_mask) and [`sv.rle_to_mask`](https://supervision.roboflow.com/0.21.0/datasets/utils/#supervision.dataset.utils.rle_to_mask) allowing for easy conversion between mask and rle formats.

- Changed [1236](https://github.com/roboflow/supervision/pull/1236): [`sv.InferenceSlicer`](https://supervision.roboflow.com/0.21.0/detection/tools/inference_slicer/) allowing to select overlap filtering strategy (`NONE`, `NON_MAX_SUPPRESSION` and `NON_MAX_MERGE`).

- Changed [1178](https://github.com/roboflow/supervision/pull/1178): [`sv.InferenceSlicer`](https://supervision.roboflow.com/0.21.0/detection/tools/inference_slicer/) adding instance segmentation model support.

python
import cv2
import numpy as np
import supervision as sv
from inference import get_model

model = get_model(model_id="yolov8x-seg-640")
image = cv2.imread(<SOURCE_IMAGE_PATH>)

def callback(image_slice: np.ndarray) -> sv.Detections:
results = model.infer(image_slice)[0]
return sv.Detections.from_inference(results)

slicer = sv.InferenceSlicer(callback = callback)
detections = slicer(image)

mask_annotator = sv.MaskAnnotator()
label_annotator = sv.LabelAnnotator()

annotated_image = mask_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)


- Changed [1228](https://github.com/roboflow/supervision/pull/1228): [`sv.LineZone`](https://supervision.roboflow.com/0.21.0/detection/tools/line_zone/) making it 10-20 times faster, depending on the use case.

- Changed [1163](https://github.com/roboflow/supervision/pull/1163): [`sv.DetectionDataset.from_coco`](https://supervision.roboflow.com/0.21.0/datasets/core/#supervision.dataset.core.DetectionDataset.from_coco) and [`sv.DetectionDataset.as_coco`](https://supervision.roboflow.com/0.21.0/datasets/core/#supervision.dataset.core.DetectionDataset.as_coco) adding support for run-length encoding (RLE) mask format.