Spaces:
Sleeping
Sleeping
File size: 6,334 Bytes
53ad959 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
# Ultralytics YOLO 🚀, AGPL-3.0 license
import math
import cv2
from ultralytics.utils.checks import check_imshow
from ultralytics.utils.plotting import Annotator, colors
class DistanceCalculation:
"""A class to calculate distance between two objects in real-time video stream based on their tracks."""
def __init__(self):
"""Initializes the distance calculation class with default values for Visual, Image, track and distance
parameters.
"""
# Visual & im0 information
self.im0 = None
self.annotator = None
self.view_img = False
self.line_color = (255, 255, 0)
self.centroid_color = (255, 0, 255)
# Predict/track information
self.clss = None
self.names = None
self.boxes = None
self.line_thickness = 2
self.trk_ids = None
# Distance calculation information
self.centroids = []
self.pixel_per_meter = 10
# Mouse event
self.left_mouse_count = 0
self.selected_boxes = {}
# Check if environment support imshow
self.env_check = check_imshow(warn=True)
def set_args(
self,
names,
pixels_per_meter=10,
view_img=False,
line_thickness=2,
line_color=(255, 255, 0),
centroid_color=(255, 0, 255),
):
"""
Configures the distance calculation and display parameters.
Args:
names (dict): object detection classes names
pixels_per_meter (int): Number of pixels in meter
view_img (bool): Flag indicating frame display
line_thickness (int): Line thickness for bounding boxes.
line_color (RGB): color of centroids line
centroid_color (RGB): colors of bbox centroids
"""
self.names = names
self.pixel_per_meter = pixels_per_meter
self.view_img = view_img
self.line_thickness = line_thickness
self.line_color = line_color
self.centroid_color = centroid_color
def mouse_event_for_distance(self, event, x, y, flags, param):
"""
This function is designed to move region with mouse events in a real-time video stream.
Args:
event (int): The type of mouse event (e.g., cv2.EVENT_MOUSEMOVE, cv2.EVENT_LBUTTONDOWN, etc.).
x (int): The x-coordinate of the mouse pointer.
y (int): The y-coordinate of the mouse pointer.
flags (int): Any flags associated with the event (e.g., cv2.EVENT_FLAG_CTRLKEY,
cv2.EVENT_FLAG_SHIFTKEY, etc.).
param (dict): Additional parameters you may want to pass to the function.
"""
global selected_boxes
global left_mouse_count
if event == cv2.EVENT_LBUTTONDOWN:
self.left_mouse_count += 1
if self.left_mouse_count <= 2:
for box, track_id in zip(self.boxes, self.trk_ids):
if box[0] < x < box[2] and box[1] < y < box[3] and track_id not in self.selected_boxes:
self.selected_boxes[track_id] = []
self.selected_boxes[track_id] = box
if event == cv2.EVENT_RBUTTONDOWN:
self.selected_boxes = {}
self.left_mouse_count = 0
def extract_tracks(self, tracks):
"""
Extracts results from the provided data.
Args:
tracks (list): List of tracks obtained from the object tracking process.
"""
self.boxes = tracks[0].boxes.xyxy.cpu()
self.clss = tracks[0].boxes.cls.cpu().tolist()
self.trk_ids = tracks[0].boxes.id.int().cpu().tolist()
def calculate_centroid(self, box):
"""
Calculate the centroid of bounding box.
Args:
box (list): Bounding box data
"""
return int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2)
def calculate_distance(self, centroid1, centroid2):
"""
Calculate distance between two centroids.
Args:
centroid1 (point): First bounding box data
centroid2 (point): Second bounding box data
"""
pixel_distance = math.sqrt((centroid1[0] - centroid2[0]) ** 2 + (centroid1[1] - centroid2[1]) ** 2)
return pixel_distance / self.pixel_per_meter, (pixel_distance / self.pixel_per_meter) * 1000
def start_process(self, im0, tracks):
"""
Calculate distance between two bounding boxes based on tracking data.
Args:
im0 (nd array): Image
tracks (list): List of tracks obtained from the object tracking process.
"""
self.im0 = im0
if tracks[0].boxes.id is None:
if self.view_img:
self.display_frames()
return
self.extract_tracks(tracks)
self.annotator = Annotator(self.im0, line_width=2)
for box, cls, track_id in zip(self.boxes, self.clss, self.trk_ids):
self.annotator.box_label(box, color=colors(int(cls), True), label=self.names[int(cls)])
if len(self.selected_boxes) == 2:
for trk_id, _ in self.selected_boxes.items():
if trk_id == track_id:
self.selected_boxes[track_id] = box
if len(self.selected_boxes) == 2:
for trk_id, box in self.selected_boxes.items():
centroid = self.calculate_centroid(self.selected_boxes[trk_id])
self.centroids.append(centroid)
distance_m, distance_mm = self.calculate_distance(self.centroids[0], self.centroids[1])
self.annotator.plot_distance_and_line(
distance_m, distance_mm, self.centroids, self.line_color, self.centroid_color
)
self.centroids = []
if self.view_img and self.env_check:
self.display_frames()
return im0
def display_frames(self):
"""Display frame."""
cv2.namedWindow("Ultralytics Distance Estimation")
cv2.setMouseCallback("Ultralytics Distance Estimation", self.mouse_event_for_distance)
cv2.imshow("Ultralytics Distance Estimation", self.im0)
if cv2.waitKey(1) & 0xFF == ord("q"):
return
if __name__ == "__main__":
DistanceCalculation()
|