dgenerate-ultralytics-headless 8.3.190__py3-none-any.whl → 8.3.191__py3-none-any.whl

ultralytics/solutions/config.py

@@ -1,7 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from dataclasses import dataclass, field
-from typing import Any, List, Optional, Tuple
+from typing import Any
 
 import cv2
 
@@ -60,22 +62,22 @@ class SolutionConfig:
         >>> print(cfg.model)
     """
 
-    source: Optional[str] = None
-    model: Optional[str] = None
-    classes: Optional[List[int]] = None
+    source: str | None = None
+    model: str | None = None
+    classes: list[int] | None = None
     show_conf: bool = True
     show_labels: bool = True
-    region: Optional[List[Tuple[int, int]]] = None
-    colormap: Optional[int] = cv2.COLORMAP_DEEPGREEN
+    region: list[tuple[int, int]] | None = None
+    colormap: int | None = cv2.COLORMAP_DEEPGREEN
     show_in: bool = True
     show_out: bool = True
     up_angle: float = 145.0
     down_angle: int = 90
-    kpts: List[int] = field(default_factory=lambda: [6, 8, 10])
+    kpts: list[int] = field(default_factory=lambda: [6, 8, 10])
     analytics_type: str = "line"
-    figsize: Optional[Tuple[int, int]] = (12.8, 7.2)
+    figsize: tuple[int, int] | None = (12.8, 7.2)
     blur_ratio: float = 0.5
-    vision_point: Tuple[int, int] = (20, 20)
+    vision_point: tuple[int, int] = (20, 20)
     crop_dir: str = "cropped-detections"
     json_file: str = None
     line_width: int = 2
@@ -87,7 +89,7 @@ class SolutionConfig:
     show: bool = False
     iou: float = 0.7
     conf: float = 0.25
-    device: Optional[str] = None
+    device: str | None = None
     max_det: int = 300
     half: bool = False
     tracker: str = "botsort.yaml"

ultralytics/solutions/distance_calculation.py

@@ -1,7 +1,7 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 import math
-from typing import Any, Dict, List
+from typing import Any
 
 import cv2
 
@@ -39,8 +39,8 @@ class DistanceCalculation(BaseSolution):
 
         # Mouse event information
         self.left_mouse_count = 0
-        self.selected_boxes: Dict[int, List[float]] = {}
-        self.centroids: List[List[int]] = []  # Store centroids of selected objects
+        self.selected_boxes: dict[int, list[float]] = {}
+        self.centroids: list[list[int]] = []  # Store centroids of selected objects
 
     def mouse_event_for_distance(self, event: int, x: int, y: int, flags: int, param: Any) -> None:
         """

ultralytics/solutions/heatmap.py

@@ -1,6 +1,8 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-from typing import Any, List
+from __future__ import annotations
+
+from typing import Any
 
 import cv2
 import numpy as np
@@ -50,7 +52,7 @@ class Heatmap(ObjectCounter):
         self.colormap = self.CFG["colormap"]
         self.heatmap = None
 
-    def heatmap_effect(self, box: List[float]) -> None:
+    def heatmap_effect(self, box: list[float]) -> None:
         """
         Efficiently calculate heatmap area and effect location for applying colormap.
 

ultralytics/solutions/object_counter.py

@@ -1,7 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from collections import defaultdict
-from typing import Any, Optional, Tuple
+from typing import Any
 
 from ultralytics.solutions.solutions import BaseSolution, SolutionAnnotator, SolutionResults
 from ultralytics.utils.plotting import colors
@@ -52,9 +54,9 @@ class ObjectCounter(BaseSolution):
 
     def count_objects(
         self,
-        current_centroid: Tuple[float, float],
+        current_centroid: tuple[float, float],
         track_id: int,
-        prev_position: Optional[Tuple[float, float]],
+        prev_position: tuple[float, float] | None,
         cls: int,
     ) -> None:
         """

ultralytics/solutions/parking_management.py

@@ -1,7 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 import json
-from typing import Any, List, Tuple
+from typing import Any
 
 import cv2
 import numpy as np
@@ -141,7 +143,7 @@ class ParkingPtsSelection:
             self.draw_box(self.current_box)
             self.current_box.clear()
 
-    def draw_box(self, box: List[Tuple[int, int]]) -> None:
+    def draw_box(self, box: list[tuple[int, int]]) -> None:
         """Draw a bounding box on the canvas using the provided coordinates."""
         for i in range(4):
             self.canvas.create_line(box[i], box[(i + 1) % 4], fill="blue", width=2)

ultralytics/solutions/region_counter.py

@@ -1,6 +1,8 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-from typing import Any, Dict, List, Tuple
+from __future__ import annotations
+
+from typing import Any
 
 import numpy as np
 
@@ -53,10 +55,10 @@ class RegionCounter(BaseSolution):
     def add_region(
         self,
         name: str,
-        polygon_points: List[Tuple],
-        region_color: Tuple[int, int, int],
-        text_color: Tuple[int, int, int],
-    ) -> Dict[str, Any]:
+        polygon_points: list[tuple],
+        region_color: tuple[int, int, int],
+        text_color: tuple[int, int, int],
+    ) -> dict[str, Any]:
         """
         Add a new region to the counting list based on the provided template with specific attributes.
 

ultralytics/solutions/similarity_search.py

@@ -1,8 +1,10 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 import os
 from pathlib import Path
-from typing import Any, List
+from typing import Any
 
 import numpy as np
 from PIL import Image
@@ -126,7 +128,7 @@ class VisualAISearch:
 
         LOGGER.info(f"Indexed {len(self.image_paths)} images.")
 
-    def search(self, query: str, k: int = 30, similarity_thresh: float = 0.1) -> List[str]:
+    def search(self, query: str, k: int = 30, similarity_thresh: float = 0.1) -> list[str]:
         """
         Return top-k semantically similar images to the given query.
 
@@ -158,7 +160,7 @@ class VisualAISearch:
 
         return [r[0] for r in results]
 
-    def __call__(self, query: str) -> List[str]:
+    def __call__(self, query: str) -> list[str]:
         """Direct call interface for the search function."""
         return self.search(query)
 

ultralytics/solutions/solutions.py

@@ -1,9 +1,11 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 import math
 from collections import Counter, defaultdict
 from functools import lru_cache
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any
 
 import cv2
 import numpy as np
@@ -135,7 +137,7 @@ class BaseSolution:
             ops.Profile(device=self.device),  # solution
         )
 
-    def adjust_box_label(self, cls: int, conf: float, track_id: Optional[int] = None) -> Optional[str]:
+    def adjust_box_label(self, cls: int, conf: float, track_id: int | None = None) -> str | None:
         """
         Generate a formatted label for a bounding box.
 
@@ -302,8 +304,8 @@ class SolutionAnnotator(Annotator):
     def __init__(
         self,
         im: np.ndarray,
-        line_width: Optional[int] = None,
-        font_size: Optional[int] = None,
+        line_width: int | None = None,
+        font_size: int | None = None,
         font: str = "Arial.ttf",
         pil: bool = False,
         example: str = "abc",
@@ -323,8 +325,8 @@ class SolutionAnnotator(Annotator):
 
     def draw_region(
         self,
-        reg_pts: Optional[List[Tuple[int, int]]] = None,
-        color: Tuple[int, int, int] = (0, 255, 0),
+        reg_pts: list[tuple[int, int]] | None = None,
+        color: tuple[int, int, int] = (0, 255, 0),
         thickness: int = 5,
     ):
         """
@@ -344,9 +346,9 @@ class SolutionAnnotator(Annotator):
     def queue_counts_display(
         self,
         label: str,
-        points: Optional[List[Tuple[int, int]]] = None,
-        region_color: Tuple[int, int, int] = (255, 255, 255),
-        txt_color: Tuple[int, int, int] = (0, 0, 0),
+        points: list[tuple[int, int]] | None = None,
+        region_color: tuple[int, int, int] = (255, 255, 255),
+        txt_color: tuple[int, int, int] = (0, 0, 0),
     ):
         """
         Display queue counts on an image centered at the points with customizable font size and colors.
@@ -390,9 +392,9 @@ class SolutionAnnotator(Annotator):
     def display_analytics(
         self,
         im0: np.ndarray,
-        text: Dict[str, Any],
-        txt_color: Tuple[int, int, int],
-        bg_color: Tuple[int, int, int],
+        text: dict[str, Any],
+        txt_color: tuple[int, int, int],
+        bg_color: tuple[int, int, int],
         margin: int,
     ):
         """
@@ -425,7 +427,7 @@ class SolutionAnnotator(Annotator):
 
     @staticmethod
     @lru_cache(maxsize=256)
-    def estimate_pose_angle(a: List[float], b: List[float], c: List[float]) -> float:
+    def estimate_pose_angle(a: list[float], b: list[float], c: list[float]) -> float:
         """
         Calculate the angle between three points for workout monitoring.
 
@@ -443,8 +445,8 @@ class SolutionAnnotator(Annotator):
 
     def draw_specific_kpts(
         self,
-        keypoints: List[List[float]],
-        indices: Optional[List[int]] = None,
+        keypoints: list[list[float]],
+        indices: list[int] | None = None,
         radius: int = 2,
         conf_thresh: float = 0.25,
     ) -> np.ndarray:
@@ -480,9 +482,9 @@ class SolutionAnnotator(Annotator):
     def plot_workout_information(
         self,
         display_text: str,
-        position: Tuple[int, int],
-        color: Tuple[int, int, int] = (104, 31, 17),
-        txt_color: Tuple[int, int, int] = (255, 255, 255),
+        position: tuple[int, int],
+        color: tuple[int, int, int] = (104, 31, 17),
+        txt_color: tuple[int, int, int] = (255, 255, 255),
     ) -> int:
         """
         Draw workout text with a background on the image.
@@ -516,9 +518,9 @@ class SolutionAnnotator(Annotator):
         angle_text: str,
         count_text: str,
         stage_text: str,
-        center_kpt: List[int],
-        color: Tuple[int, int, int] = (104, 31, 17),
-        txt_color: Tuple[int, int, int] = (255, 255, 255),
+        center_kpt: list[int],
+        color: tuple[int, int, int] = (104, 31, 17),
+        txt_color: tuple[int, int, int] = (255, 255, 255),
     ):
         """
         Plot the pose angle, count value, and step stage for workout monitoring.
@@ -548,9 +550,9 @@ class SolutionAnnotator(Annotator):
     def plot_distance_and_line(
         self,
         pixels_distance: float,
-        centroids: List[Tuple[int, int]],
-        line_color: Tuple[int, int, int] = (104, 31, 17),
-        centroid_color: Tuple[int, int, int] = (255, 0, 255),
+        centroids: list[tuple[int, int]],
+        line_color: tuple[int, int, int] = (104, 31, 17),
+        centroid_color: tuple[int, int, int] = (255, 0, 255),
     ):
         """
         Plot the distance and line between two centroids on the frame.
@@ -589,8 +591,8 @@ class SolutionAnnotator(Annotator):
         self,
         im0: np.ndarray,
         text: str,
-        txt_color: Tuple[int, int, int],
-        bg_color: Tuple[int, int, int],
+        txt_color: tuple[int, int, int],
+        bg_color: tuple[int, int, int],
         x_center: float,
         y_center: float,
         margin: int,
@@ -638,9 +640,9 @@ class SolutionAnnotator(Annotator):
         self,
         line_x: int = 0,
         line_y: int = 0,
-        label: Optional[str] = None,
-        color: Tuple[int, int, int] = (221, 0, 186),
-        txt_color: Tuple[int, int, int] = (255, 255, 255),
+        label: str | None = None,
+        color: tuple[int, int, int] = (221, 0, 186),
+        txt_color: tuple[int, int, int] = (255, 255, 255),
     ):
         """
         Draw a sweep annotation line and an optional label.
@@ -677,10 +679,10 @@ class SolutionAnnotator(Annotator):
 
     def visioneye(
         self,
-        box: List[float],
-        center_point: Tuple[int, int],
-        color: Tuple[int, int, int] = (235, 219, 11),
-        pin_color: Tuple[int, int, int] = (255, 0, 255),
+        box: list[float],
+        center_point: tuple[int, int],
+        color: tuple[int, int, int] = (235, 219, 11),
+        pin_color: tuple[int, int, int] = (255, 0, 255),
     ):
         """
         Perform pinpoint human-vision eye mapping and plotting.
@@ -698,10 +700,10 @@ class SolutionAnnotator(Annotator):
 
     def adaptive_label(
         self,
-        box: Tuple[float, float, float, float],
+        box: tuple[float, float, float, float],
         label: str = "",
-        color: Tuple[int, int, int] = (128, 128, 128),
-        txt_color: Tuple[int, int, int] = (255, 255, 255),
+        color: tuple[int, int, int] = (128, 128, 128),
+        txt_color: tuple[int, int, int] = (255, 255, 255),
         shape: str = "rect",
         margin: int = 5,
     ):

ultralytics/solutions/streamlit_inference.py

@@ -2,7 +2,7 @@
 
 import io
 import os
-from typing import Any, List
+from typing import Any
 
 import cv2
 import torch
@@ -72,7 +72,7 @@ class Inference:
         self.org_frame = None  # Container for the original frame display
         self.ann_frame = None  # Container for the annotated frame display
         self.vid_file_name = None  # Video file name or webcam index
-        self.selected_ind: List[int] = []  # List of selected class indices for detection
+        self.selected_ind: list[int] = []  # List of selected class indices for detection
         self.model = None  # YOLO model instance
 
         self.temp_dict = {"model": None, **kwargs}
@@ -91,8 +91,8 @@ class Inference:
         font-family: 'Archivo', sans-serif; margin-bottom:20px;">Ultralytics YOLO Streamlit Application</h1></div>"""
 
         # Subtitle of streamlit application
-        sub_title_cfg = """<div><h5 style="color:#042AFF; text-align:center; font-family: 'Archivo', sans-serif; 
-        margin-top:-15px; margin-bottom:50px;">Experience real-time object detection on your webcam, videos, and images 
+        sub_title_cfg = """<div><h5 style="color:#042AFF; text-align:center; font-family: 'Archivo', sans-serif;
+        margin-top:-15px; margin-bottom:50px;">Experience real-time object detection on your webcam, videos, and images
         with the power of Ultralytics YOLO! 🚀</h5></div>"""
 
         # Set html page configuration and append custom HTML
@@ -141,8 +141,9 @@ class Inference:
         elif self.source == "image":
             import tempfile  # scope import
 
-            imgfiles = self.st.sidebar.file_uploader("Upload Image Files", type=IMG_FORMATS, accept_multiple_files=True)
-            if imgfiles:
+            if imgfiles := self.st.sidebar.file_uploader(
+                "Upload Image Files", type=IMG_FORMATS, accept_multiple_files=True
+            ):
                 for imgfile in imgfiles:  # Save each uploaded image to a temporary file
                     with tempfile.NamedTemporaryFile(delete=False, suffix=f".{imgfile.name.split('.')[-1]}") as tf:
                         tf.write(imgfile.read())
@@ -185,7 +186,7 @@ class Inference:
 
     def image_inference(self) -> None:
         """Perform inference on uploaded images."""
-        for idx, img_info in enumerate(self.img_file_names):
+        for img_info in self.img_file_names:
             img_path = img_info["path"]
             image = cv2.imread(img_path)  # Load and display the original image
             if image is not None:

ultralytics/trackers/bot_sort.py

@@ -1,7 +1,9 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 from collections import deque
-from typing import Any, List, Optional
+from typing import Any
 
 import numpy as np
 import torch
@@ -53,7 +55,7 @@ class BOTrack(STrack):
     shared_kalman = KalmanFilterXYWH()
 
     def __init__(
-        self, xywh: np.ndarray, score: float, cls: int, feat: Optional[np.ndarray] = None, feat_history: int = 50
+        self, xywh: np.ndarray, score: float, cls: int, feat: np.ndarray | None = None, feat_history: int = 50
     ):
         """
         Initialize a BOTrack object with temporal parameters, such as feature history, alpha, and current features.
@@ -102,13 +104,13 @@ class BOTrack(STrack):
 
         self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
 
-    def re_activate(self, new_track: "BOTrack", frame_id: int, new_id: bool = False) -> None:
+    def re_activate(self, new_track: BOTrack, frame_id: int, new_id: bool = False) -> None:
         """Reactivate a track with updated features and optionally assign a new ID."""
         if new_track.curr_feat is not None:
             self.update_features(new_track.curr_feat)
         super().re_activate(new_track, frame_id, new_id)
 
-    def update(self, new_track: "BOTrack", frame_id: int) -> None:
+    def update(self, new_track: BOTrack, frame_id: int) -> None:
         """Update the track with new detection information and the current frame ID."""
         if new_track.curr_feat is not None:
             self.update_features(new_track.curr_feat)
@@ -124,7 +126,7 @@ class BOTrack(STrack):
         return ret
 
     @staticmethod
-    def multi_predict(stracks: List["BOTrack"]) -> None:
+    def multi_predict(stracks: list[BOTrack]) -> None:
         """Predict the mean and covariance for multiple object tracks using a shared Kalman filter."""
         if len(stracks) <= 0:
             return
@@ -210,7 +212,7 @@ class BOTSORT(BYTETracker):
         """Return an instance of KalmanFilterXYWH for predicting and updating object states in the tracking process."""
         return KalmanFilterXYWH()
 
-    def init_track(self, results, img: Optional[np.ndarray] = None) -> List[BOTrack]:
+    def init_track(self, results, img: np.ndarray | None = None) -> list[BOTrack]:
         """Initialize object tracks using detection bounding boxes, scores, class labels, and optional ReID features."""
         if len(results) == 0:
             return []
@@ -222,7 +224,7 @@ class BOTSORT(BYTETracker):
         else:
             return [BOTrack(xywh, s, c) for (xywh, s, c) in zip(bboxes, results.conf, results.cls)]
 
-    def get_dists(self, tracks: List[BOTrack], detections: List[BOTrack]) -> np.ndarray:
+    def get_dists(self, tracks: list[BOTrack], detections: list[BOTrack]) -> np.ndarray:
         """Calculate distances between tracks and detections using IoU and optionally ReID embeddings."""
         dists = matching.iou_distance(tracks, detections)
         dists_mask = dists > (1 - self.proximity_thresh)
@@ -237,7 +239,7 @@ class BOTSORT(BYTETracker):
             dists = np.minimum(dists, emb_dists)
         return dists
 
-    def multi_predict(self, tracks: List[BOTrack]) -> None:
+    def multi_predict(self, tracks: list[BOTrack]) -> None:
         """Predict the mean and covariance of multiple object tracks using a shared Kalman filter."""
         BOTrack.multi_predict(tracks)
 
@@ -262,7 +264,7 @@ class ReID:
         self.model = YOLO(model)
         self.model(embed=[len(self.model.model.model) - 2 if ".pt" in model else -1], verbose=False, save=False)  # init
 
-    def __call__(self, img: np.ndarray, dets: np.ndarray) -> List[np.ndarray]:
+    def __call__(self, img: np.ndarray, dets: np.ndarray) -> list[np.ndarray]:
         """Extract embeddings for detected objects."""
         feats = self.model.predictor(
             [save_one_box(det, img, save=False) for det in xywh2xyxy(torch.from_numpy(dets[:, :4]))]

ultralytics/trackers/byte_tracker.py

@@ -1,6 +1,8 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-from typing import Any, List, Optional, Tuple
+from __future__ import annotations
+
+from typing import Any
 
 import numpy as np
 
@@ -51,7 +53,7 @@ class STrack(BaseTrack):
 
     shared_kalman = KalmanFilterXYAH()
 
-    def __init__(self, xywh: List[float], score: float, cls: Any):
+    def __init__(self, xywh: list[float], score: float, cls: Any):
         """
         Initialize a new STrack instance.
 
@@ -89,7 +91,7 @@ class STrack(BaseTrack):
         self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
 
     @staticmethod
-    def multi_predict(stracks: List["STrack"]):
+    def multi_predict(stracks: list[STrack]):
         """Perform multi-object predictive tracking using Kalman filter for the provided list of STrack instances."""
         if len(stracks) <= 0:
             return
@@ -104,9 +106,9 @@ class STrack(BaseTrack):
             stracks[i].covariance = cov
 
     @staticmethod
-    def multi_gmc(stracks: List["STrack"], H: np.ndarray = np.eye(2, 3)):
+    def multi_gmc(stracks: list[STrack], H: np.ndarray = np.eye(2, 3)):
         """Update state tracks positions and covariances using a homography matrix for multiple tracks."""
-        if len(stracks) > 0:
+        if stracks:
             multi_mean = np.asarray([st.mean.copy() for st in stracks])
             multi_covariance = np.asarray([st.covariance for st in stracks])
 
@@ -135,7 +137,7 @@ class STrack(BaseTrack):
         self.frame_id = frame_id
         self.start_frame = frame_id
 
-    def re_activate(self, new_track: "STrack", frame_id: int, new_id: bool = False):
+    def re_activate(self, new_track: STrack, frame_id: int, new_id: bool = False):
         """Reactivate a previously lost track using new detection data and update its state and attributes."""
         self.mean, self.covariance = self.kalman_filter.update(
             self.mean, self.covariance, self.convert_coords(new_track.tlwh)
@@ -151,7 +153,7 @@ class STrack(BaseTrack):
         self.angle = new_track.angle
         self.idx = new_track.idx
 
-    def update(self, new_track: "STrack", frame_id: int):
+    def update(self, new_track: STrack, frame_id: int):
         """
         Update the state of a matched track.
 
@@ -225,7 +227,7 @@ class STrack(BaseTrack):
         return np.concatenate([self.xywh, self.angle[None]])
 
     @property
-    def result(self) -> List[float]:
+    def result(self) -> list[float]:
         """Get the current tracking results in the appropriate bounding box format."""
         coords = self.xyxy if self.angle is None else self.xywha
         return coords.tolist() + [self.track_id, self.score, self.cls, self.idx]
@@ -294,7 +296,7 @@ class BYTETracker:
         self.kalman_filter = self.get_kalmanfilter()
         self.reset_id()
 
-    def update(self, results, img: Optional[np.ndarray] = None, feats: Optional[np.ndarray] = None) -> np.ndarray:
+    def update(self, results, img: np.ndarray | None = None, feats: np.ndarray | None = None) -> np.ndarray:
         """Update the tracker with new detections and return the current list of tracked objects."""
         self.frame_id += 1
         activated_stracks = []
@@ -411,7 +413,7 @@ class BYTETracker:
         """Return a Kalman filter object for tracking bounding boxes using KalmanFilterXYAH."""
         return KalmanFilterXYAH()
 
-    def init_track(self, results, img: Optional[np.ndarray] = None) -> List[STrack]:
+    def init_track(self, results, img: np.ndarray | None = None) -> list[STrack]:
         """Initialize object tracking with given detections, scores, and class labels using the STrack algorithm."""
         if len(results) == 0:
             return []
@@ -419,14 +421,14 @@ class BYTETracker:
         bboxes = np.concatenate([bboxes, np.arange(len(bboxes)).reshape(-1, 1)], axis=-1)
         return [STrack(xywh, s, c) for (xywh, s, c) in zip(bboxes, results.conf, results.cls)]
 
-    def get_dists(self, tracks: List[STrack], detections: List[STrack]) -> np.ndarray:
+    def get_dists(self, tracks: list[STrack], detections: list[STrack]) -> np.ndarray:
         """Calculate the distance between tracks and detections using IoU and optionally fuse scores."""
         dists = matching.iou_distance(tracks, detections)
         if self.args.fuse_score:
             dists = matching.fuse_score(dists, detections)
         return dists
 
-    def multi_predict(self, tracks: List[STrack]):
+    def multi_predict(self, tracks: list[STrack]):
         """Predict the next states for multiple tracks using Kalman filter."""
         STrack.multi_predict(tracks)
 
@@ -445,7 +447,7 @@ class BYTETracker:
         self.reset_id()
 
     @staticmethod
-    def joint_stracks(tlista: List[STrack], tlistb: List[STrack]) -> List[STrack]:
+    def joint_stracks(tlista: list[STrack], tlistb: list[STrack]) -> list[STrack]:
         """Combine two lists of STrack objects into a single list, ensuring no duplicates based on track IDs."""
         exists = {}
         res = []
@@ -460,13 +462,13 @@ class BYTETracker:
         return res
 
     @staticmethod
-    def sub_stracks(tlista: List[STrack], tlistb: List[STrack]) -> List[STrack]:
+    def sub_stracks(tlista: list[STrack], tlistb: list[STrack]) -> list[STrack]:
         """Filter out the stracks present in the second list from the first list."""
         track_ids_b = {t.track_id for t in tlistb}
         return [t for t in tlista if t.track_id not in track_ids_b]
 
     @staticmethod
-    def remove_duplicate_stracks(stracksa: List[STrack], stracksb: List[STrack]) -> Tuple[List[STrack], List[STrack]]:
+    def remove_duplicate_stracks(stracksa: list[STrack], stracksb: list[STrack]) -> tuple[list[STrack], list[STrack]]:
         """Remove duplicate stracks from two lists based on Intersection over Union (IoU) distance."""
         pdist = matching.iou_distance(stracksa, stracksb)
         pairs = np.where(pdist < 0.15)

ultralytics/trackers/utils/gmc.py

@@ -1,7 +1,8 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from __future__ import annotations
+
 import copy
-from typing import List, Optional
 
 import cv2
 import numpy as np
@@ -89,7 +90,7 @@ class GMC:
         self.prevDescriptors = None
         self.initializedFirstFrame = False
 
-    def apply(self, raw_frame: np.ndarray, detections: Optional[List] = None) -> np.ndarray:
+    def apply(self, raw_frame: np.ndarray, detections: list | None = None) -> np.ndarray:
         """
         Apply object detection on a raw frame using the specified method.
 
@@ -156,7 +157,7 @@ class GMC:
 
         return H
 
-    def apply_features(self, raw_frame: np.ndarray, detections: Optional[List] = None) -> np.ndarray:
+    def apply_features(self, raw_frame: np.ndarray, detections: list | None = None) -> np.ndarray:
         """
         Apply feature-based methods like ORB or SIFT to a raw frame.