185 lines
6.3 KiB
Python
185 lines
6.3 KiB
Python
import json
|
|
from pathlib import Path
|
|
import logging
|
|
import torch
|
|
from ultralytics import YOLO
|
|
import cv2
|
|
from dodgeballtracker.helper import iter_frames
|
|
from dodgeballtracker.video_writer import create_video_writer, VideoWriter
|
|
import matplotlib
|
|
import numpy as np
|
|
from boxmot import DeepOcSort as DeepOCSORT
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
Color = tuple[int, int, int]
|
|
|
|
|
|
def get_best_available_torch_device() -> torch.device:
|
|
if torch.cuda.is_available():
|
|
logger.debug("Using the cuda (gpu) torch device.")
|
|
return torch.device('cuda:0')
|
|
if torch.backends.mps.is_available():
|
|
logger.debug("Using the mps (apple silicon) torch device.")
|
|
return torch.device('mps')
|
|
logger.debug("Default to cpu (no apple silicon or cuda) torch device.")
|
|
return torch.device('cpu')
|
|
|
|
|
|
class DetectedObjectBox:
|
|
def __init__(self, min_threshold: float, color: Color):
|
|
self.min_threshold = min_threshold
|
|
self.color = color
|
|
|
|
def __lt__(self, other):
|
|
return self.min_threshold < other.min_threshold
|
|
|
|
@classmethod
|
|
def from_viridis(cls, min_threshold):
|
|
cm = matplotlib.colormaps['viridis']
|
|
color: Color = tuple((int(255 * cm(min_threshold)[i]) for i in range(3)))
|
|
return cls(min_threshold, color)
|
|
|
|
|
|
def get_court_perspective_transform():
|
|
"""
|
|
"""
|
|
empirical_top_left = np.float32([416, 175])
|
|
empirical_top_right = np.float32([905, 173])
|
|
empirical_bottom_left = np.float32([51, 702])
|
|
empirical_bottom_right = np.float32([1188, 695])
|
|
|
|
court_top_left = np.float32([0, 0])
|
|
court_top_right = np.float32([9, 0])
|
|
court_bottom_left = np.float32([0, 18])
|
|
court_bottom_right = np.float32([9, 18])
|
|
|
|
empirical_source = np.float32([empirical_top_left,
|
|
empirical_top_right,
|
|
empirical_bottom_left,
|
|
empirical_bottom_right])
|
|
pixel_per_meter = 50
|
|
empirical_target = np.float32([court_top_left,
|
|
court_top_right,
|
|
court_bottom_left,
|
|
court_bottom_right]) * pixel_per_meter
|
|
return cv2.getPerspectiveTransform(empirical_source, empirical_target)
|
|
|
|
|
|
|
|
|
|
|
|
class DodgeballTracker:
|
|
|
|
def __init__(self,
|
|
input_file: Path,
|
|
output_file: Path,
|
|
video_writer: VideoWriter,
|
|
detected_box_objects: list[DetectedObjectBox],
|
|
transformation_matrix):
|
|
self.input_path = input_file
|
|
self.output_path = output_file
|
|
self.output_json_path = output_file.with_suffix(".json")
|
|
self.video_writer = video_writer
|
|
self.detected_box_objects = sorted(detected_box_objects, reverse=True)
|
|
self.transformation_matrix = transformation_matrix
|
|
self.points = []
|
|
|
|
def write_frame(self, writer, frame) -> None:
|
|
cv2.imshow("Frame", frame)
|
|
writer.write(frame)
|
|
|
|
def extract_box(self, data) -> tuple[int, int, int, int]:
|
|
return int(data[0]), int(data[1]), int(data[2]), int(data[3])
|
|
|
|
def print_box(self, data, frame_idx, frame_ts):
|
|
xmin, ymin, xmax, ymax = self.extract_box(data)
|
|
xavg = (xmax + xmin) / 2
|
|
v = np.array([xavg, ymax, 1])
|
|
ret = self.transformation_matrix @ v
|
|
x, y = ret[0] / ret[2], ret[1] / ret[2]
|
|
object_id = data[-1]
|
|
self.points.append({"x": x,
|
|
"y": y,
|
|
"frameIndex": frame_idx,
|
|
"frameTimestamp": frame_ts,
|
|
"objectId": int(object_id)
|
|
})
|
|
|
|
def print_tracker_data(self, tracker_data, frame_idx, frame_ts):
|
|
for d in tracker_data:
|
|
self.print_box(d, frame_idx, frame_ts)
|
|
|
|
def plot_box_to_frame(self, data, frame):
|
|
confidence = float(data[4])
|
|
for detected_box_object in self.detected_box_objects:
|
|
|
|
if detected_box_object.min_threshold < confidence:
|
|
xmin, ymin, xmax, ymax = self.extract_box(data)
|
|
cv2.rectangle(frame, (xmin, ymin), (xmax, ymax), detected_box_object.color, 2)
|
|
return True
|
|
return False
|
|
|
|
def run_model_on_frame(self, model, frame):
|
|
return model(frame)[0]
|
|
|
|
def crazy_experiment(self, frame):
|
|
cv2.putText(frame,
|
|
"Hello world",
|
|
(50, 50),
|
|
cv2.FONT_HERSHEY_SIMPLEX,
|
|
2,
|
|
(0, 255, 0), 8)
|
|
cv2.line(frame, (0, 0), (511, 511), (255, 0, 0), 5)
|
|
pts = np.array([[50, 50], [500, 50], [500, 500], [50, 500], [50, 50]], np.int32)
|
|
pts = pts.reshape((-1, 1, 2))
|
|
|
|
cv2.polylines(frame, pts, True, (0, 255, 255), 8)
|
|
|
|
def persist_points(self):
|
|
with open(self.output_json_path, "wt") as file_:
|
|
json.dump({"points": self.points}, file_, indent=4)
|
|
|
|
def _get_tracker(self):
|
|
return DeepOCSORT(
|
|
Path('lmbn_n_cuhk03_d.pt'), # which ReID model to use
|
|
get_best_available_torch_device(), # torch.cuda.get_device_name(0), #torch.device(get_best_available_torch_device()),
|
|
True,
|
|
)
|
|
|
|
def _get_detection_model(self):
|
|
"""
|
|
load the pre-trained YOLOv8n model
|
|
"""
|
|
return YOLO("yolo11n.pt", verbose=True)
|
|
|
|
def main(self):
|
|
# define some constants
|
|
video_cap = cv2.VideoCapture(str(self.input_path))
|
|
# writer = create_video_writer(video_cap, self.output_path)
|
|
tracker = self._get_tracker()
|
|
|
|
# load the pre-trained YOLOv8n model
|
|
model = self._get_detection_model()
|
|
|
|
for i, (frame, ts) in enumerate(iter_frames(video_cap)):
|
|
# run the YOLO model on the frame
|
|
res = []
|
|
detections = self.run_model_on_frame(model, frame)
|
|
for data in detections.boxes.data.tolist():
|
|
is_good_box = self.plot_box_to_frame(data, frame)
|
|
if is_good_box:
|
|
res.append(data)
|
|
|
|
data_ = tracker.update(np.array(res), frame)
|
|
self.print_tracker_data(data_, i, ts)
|
|
|
|
self.video_writer.write_frame(frame)
|
|
|
|
if cv2.waitKey(1) == ord("q"):
|
|
break
|
|
|
|
video_cap.release()
|
|
self.persist_points()
|