385 lines
18 KiB
Python
385 lines
18 KiB
Python
|
|
import argparse
|
|
import csv
|
|
import os
|
|
import platform
|
|
import sys
|
|
import paho.mqtt.client as mqtt
|
|
import json
|
|
import time
|
|
from pathlib import Path
|
|
|
|
import torch
|
|
|
|
FILE = Path(__file__).resolve()
|
|
ROOT = FILE.parents[0] # YOLOv5 root directory
|
|
if str(ROOT) not in sys.path:
|
|
sys.path.append(str(ROOT)) # add ROOT to PATH
|
|
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
|
|
|
|
from ultralytics.utils.plotting import Annotator, colors, save_one_box
|
|
|
|
from models.common import DetectMultiBackend
|
|
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams
|
|
from utils.general import (
|
|
LOGGER,
|
|
Profile,
|
|
check_file,
|
|
check_img_size,
|
|
check_imshow,
|
|
check_requirements,
|
|
colorstr,
|
|
cv2,
|
|
increment_path,
|
|
non_max_suppression,
|
|
print_args,
|
|
scale_boxes,
|
|
strip_optimizer,
|
|
xyxy2xywh,
|
|
)
|
|
from utils.torch_utils import select_device, smart_inference_mode
|
|
|
|
MQTT_BROKER = "broker.hivemq.com"
|
|
MQTT_PORT = 1883
|
|
MQTT_TOPIC = "Automation001"
|
|
|
|
def on_connect(client, userdata, flags, rc):
|
|
if rc == 0:
|
|
print("Connected to MQTT broker successfully.")
|
|
else:
|
|
print(f"Failed to connect to MQTT broker, return code {rc}")
|
|
|
|
def on_publish(client, userdata, mid):
|
|
print(f"Message {mid} published.")
|
|
|
|
# Initialize MQTT client
|
|
client = mqtt.Client()
|
|
client.on_connect = on_connect
|
|
client.on_publish = on_publish
|
|
client.connect(MQTT_BROKER, MQTT_PORT, 60) # Connect to the broker
|
|
|
|
# Store detected objects over multiple frames (Sliding Window)
|
|
from collections import deque
|
|
|
|
WINDOW_SIZE = 30
|
|
RECOGNITION_THRESHOLD = 0.7
|
|
|
|
# Buffer to store objects detected over last N frames
|
|
focus_buffer = deque(maxlen=WINDOW_SIZE) # Track objects over last 5 frames
|
|
|
|
def get_focused_object(detections, img_shape):
|
|
"""
|
|
Determines the object the user is focusing on by finding the detection
|
|
closest to the center of the frame and ensuring persistence over frames.
|
|
|
|
:param detections: Tensor of shape (N, 6) containing [x1, y1, x2, y2, confidence, class]
|
|
:param img_shape: Shape of the original image (height, width, channels)
|
|
:return: The most consistently detected object (class ID) or None if no stable focus.
|
|
"""
|
|
if len(detections) == 0:
|
|
return 80 # No objects detected
|
|
|
|
# Step 1: Filter out low-confidence detections
|
|
detections = detections[detections[:, 4] > 0.5] # Keep only confidence > 50%
|
|
|
|
if len(detections) == 0:
|
|
return 80 # No confident detections
|
|
|
|
# Step 2: Calculate object centroids
|
|
image_center = torch.tensor([img_shape[1] / 2, img_shape[0] / 2]) # (x_center, y_center)
|
|
centroids = torch.stack([(detections[:, 0] + detections[:, 2]) / 2,
|
|
(detections[:, 1] + detections[:, 3]) / 2], dim=1)
|
|
|
|
# Step 3: Find the object closest to the center
|
|
distances = torch.norm(centroids - image_center, dim=1) # Euclidean distance
|
|
min_distance_index = torch.argmin(distances) # Index of the closest object
|
|
|
|
focused_object = int(detections[min_distance_index, 5]) # Get class ID of the focused object
|
|
|
|
# Step 4: Maintain a sliding window of detected objects
|
|
focus_buffer.append(focused_object)
|
|
|
|
# Step 5: Determine the most frequently appearing object in buffer
|
|
focus_counts = {obj: focus_buffer.count(obj) for obj in set(focus_buffer)}
|
|
most_frequent_object = max(focus_counts, key=focus_counts.get) # Object appearing most in buffer
|
|
|
|
# Only return if it appears in at least 60% of frames in the buffer
|
|
if focus_counts[most_frequent_object] >= RECOGNITION_THRESHOLD * len(focus_buffer):
|
|
return most_frequent_object
|
|
else:
|
|
return 80 # No stable focus object
|
|
|
|
# 80 class corresponds
|
|
|
|
@smart_inference_mode()
|
|
def run(
|
|
weights=ROOT / "yolov5s.pt", # model path or triton URL
|
|
source=ROOT / "data/images", # file/dir/URL/glob/screen/0(webcam)
|
|
data=ROOT / "data/coco128.yaml", # dataset.yaml path
|
|
imgsz=(640, 640), # inference size (height, width)
|
|
conf_thres=0.25, # confidence threshold
|
|
iou_thres=0.45, # NMS IOU threshold
|
|
max_det=1000, # maximum detections per image
|
|
device="", # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
|
view_img=False, # show results
|
|
save_txt=False, # save results to *.txt
|
|
save_format=0, # save boxes coordinates in YOLO format or Pascal-VOC format (0 for YOLO and 1 for Pascal-VOC)
|
|
save_csv=False, # save results in CSV format
|
|
save_conf=False, # save confidences in --save-txt labels
|
|
save_crop=False, # save cropped prediction boxes
|
|
nosave=False, # do not save images/videos
|
|
classes=None, # filter by class: --class 0, or --class 0 2 3
|
|
agnostic_nms=False, # class-agnostic NMS
|
|
augment=False, # augmented inference
|
|
visualize=False, # visualize features
|
|
update=False, # update all models
|
|
project=ROOT / "runs/detect", # save results to project/name
|
|
name="exp", # save results to project/name
|
|
exist_ok=False, # existing project/name ok, do not increment
|
|
line_thickness=3, # bounding box thickness (pixels)
|
|
hide_labels=False, # hide labels
|
|
hide_conf=False, # hide confidences
|
|
half=False, # use FP16 half-precision inference
|
|
dnn=False, # use OpenCV DNN for ONNX inference
|
|
vid_stride=1, # video frame-rate stride
|
|
):
|
|
|
|
source = str(source)
|
|
save_img = not nosave and not source.endswith(".txt") # save inference images
|
|
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
|
|
is_url = source.lower().startswith(("rtsp://", "rtmp://", "http://", "https://"))
|
|
webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file)
|
|
screenshot = source.lower().startswith("screen")
|
|
if is_url and is_file:
|
|
source = check_file(source) # download
|
|
|
|
# Directories
|
|
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run
|
|
(save_dir / "labels" if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
|
|
|
|
# Load model
|
|
device = select_device(device)
|
|
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half)
|
|
stride, names, pt = model.stride, model.names, model.pt
|
|
names[80] = 'none'
|
|
imgsz = check_img_size(imgsz, s=stride) # check image size
|
|
|
|
# Dataloader
|
|
bs = 1 # batch_size
|
|
if webcam:
|
|
view_img = check_imshow(warn=True)
|
|
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
|
|
bs = len(dataset)
|
|
elif screenshot:
|
|
dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt)
|
|
else:
|
|
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride)
|
|
vid_path, vid_writer = [None] * bs, [None] * bs
|
|
|
|
# Run inference
|
|
model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup
|
|
seen, windows, dt = 0, [], (Profile(device=device), Profile(device=device), Profile(device=device))
|
|
for path, im, im0s, vid_cap, s in dataset:
|
|
with dt[0]:
|
|
im = torch.from_numpy(im).to(model.device)
|
|
im = im.half() if model.fp16 else im.float() # uint8 to fp16/32
|
|
im /= 255 # 0 - 255 to 0.0 - 1.0
|
|
if len(im.shape) == 3:
|
|
im = im[None] # expand for batch dim
|
|
if model.xml and im.shape[0] > 1:
|
|
ims = torch.chunk(im, im.shape[0], 0)
|
|
|
|
# Inference
|
|
with dt[1]:
|
|
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
|
|
if model.xml and im.shape[0] > 1:
|
|
pred = None
|
|
for image in ims:
|
|
if pred is None:
|
|
pred = model(image, augment=augment, visualize=visualize).unsqueeze(0)
|
|
else:
|
|
pred = torch.cat((pred, model(image, augment=augment, visualize=visualize).unsqueeze(0)), dim=0)
|
|
pred = [pred, None]
|
|
else:
|
|
pred = model(im, augment=augment, visualize=visualize)
|
|
# NMS
|
|
with dt[2]:
|
|
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
|
|
|
|
# Second-stage classifier (optional)
|
|
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
|
|
|
|
# Define the path for the CSV file
|
|
csv_path = save_dir / "predictions.csv"
|
|
|
|
# Create or append to the CSV file
|
|
def write_to_csv(image_name, prediction, confidence):
|
|
"""Writes prediction data for an image to a CSV file, appending if the file exists."""
|
|
data = {"Image Name": image_name, "Prediction": prediction, "Confidence": confidence}
|
|
file_exists = os.path.isfile(csv_path)
|
|
with open(csv_path, mode="a", newline="") as f:
|
|
writer = csv.DictWriter(f, fieldnames=data.keys())
|
|
if not file_exists:
|
|
writer.writeheader()
|
|
writer.writerow(data)
|
|
|
|
# Process predictions
|
|
for i, det in enumerate(pred): # per image
|
|
|
|
seen += 1
|
|
if webcam: # batch_size >= 1
|
|
p, im0, frame = path[i], im0s[i].copy(), dataset.count
|
|
s += f"{i}: "
|
|
else:
|
|
p, im0, frame = path, im0s.copy(), getattr(dataset, "frame", 0)
|
|
|
|
p = Path(p) # to Path
|
|
save_path = str(save_dir / p.name) # im.jpg
|
|
txt_path = str(save_dir / "labels" / p.stem) + ("" if dataset.mode == "image" else f"_{frame}") # im.txt
|
|
s += "{:g}x{:g} ".format(*im.shape[2:]) # print string
|
|
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
|
|
imc = im0.copy() if save_crop else im0 # for save_crop
|
|
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
|
|
if len(det):
|
|
# Rescale boxes from img_size to im0 size
|
|
det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
|
|
|
|
# Print results
|
|
for c in det[:, 5].unique():
|
|
n = (det[:, 5] == c).sum() # detections per class
|
|
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
|
|
|
|
# Write results
|
|
for *xyxy, conf, cls in reversed(det):
|
|
c = get_focused_object(det, im0.shape) # integer class
|
|
label = names[c] if hide_conf else f"{names[c]}"
|
|
confidence = float(conf)
|
|
confidence_str = f"{confidence:.2f}"
|
|
|
|
if confidence > 0.50:
|
|
msg = f"{label}"
|
|
# client.publish(MQTT_TOPIC, msg, retain=True)
|
|
print(f"data sent to mqtt: {msg}")
|
|
|
|
if save_csv:
|
|
write_to_csv(p.name, label, confidence_str)
|
|
|
|
if save_txt: # Write to file
|
|
if save_format == 0:
|
|
coords = (
|
|
(xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()
|
|
) # normalized xywh
|
|
else:
|
|
coords = (torch.tensor(xyxy).view(1, 4) / gn).view(-1).tolist() # xyxy
|
|
line = (cls, *coords, conf) if save_conf else (cls, *coords) # label format
|
|
with open(f"{txt_path}.txt", "a") as f:
|
|
f.write(("%g " * len(line)).rstrip() % line + "\n")
|
|
|
|
if save_img or save_crop or view_img: # Add bbox to image
|
|
c = int(cls) # integer class
|
|
label = None if hide_labels else (names[c] if hide_conf else f"{names[c]} {conf:.2f}")
|
|
annotator.box_label(xyxy, label, color=colors(c, True))
|
|
if save_crop:
|
|
save_one_box(xyxy, imc, file=save_dir / "crops" / names[c] / f"{p.stem}.jpg", BGR=True)
|
|
|
|
# Stream results
|
|
im0 = annotator.result()
|
|
if view_img:
|
|
if platform.system() == "Linux" and p not in windows:
|
|
windows.append(p)
|
|
cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux)
|
|
cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
|
|
cv2.imshow(str(p), im0)
|
|
cv2.waitKey(1) # 1 millisecond
|
|
|
|
# Save results (image with detections)
|
|
if save_img:
|
|
if dataset.mode == "image":
|
|
cv2.imwrite(save_path, im0)
|
|
else: # 'video' or 'stream'
|
|
if vid_path[i] != save_path: # new video
|
|
vid_path[i] = save_path
|
|
if isinstance(vid_writer[i], cv2.VideoWriter):
|
|
vid_writer[i].release() # release previous video writer
|
|
if vid_cap: # video
|
|
fps = vid_cap.get(cv2.CAP_PROP_FPS)
|
|
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
|
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
|
else: # stream
|
|
fps, w, h = 30, im0.shape[1], im0.shape[0]
|
|
save_path = str(Path(save_path).with_suffix(".mp4")) # force *.mp4 suffix on results videos
|
|
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h))
|
|
vid_writer[i].write(im0)
|
|
|
|
|
|
# Print time (inference-only)
|
|
LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1e3:.1f}ms")
|
|
|
|
if cv2.waitKey(1) == ord('q'):
|
|
cv2.destroyAllWindows
|
|
# raise StopIteration
|
|
break
|
|
|
|
# Print results
|
|
t = tuple(x.t / seen * 1e3 for x in dt) # speeds per image
|
|
LOGGER.info(f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}" % t)
|
|
if save_txt or save_img:
|
|
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ""
|
|
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
|
|
if update:
|
|
strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning)
|
|
|
|
|
|
def parse_opt():
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "yolov5s.pt", help="model path or triton URL")
|
|
parser.add_argument("--source", type=str, default=ROOT / "data/images", help="file/dir/URL/glob/screen/0(webcam)")
|
|
parser.add_argument("--data", type=str, default=ROOT / "data/coco128.yaml", help="(optional) dataset.yaml path")
|
|
parser.add_argument("--imgsz", "--img", "--img-size", nargs="+", type=int, default=[640], help="inference size h,w")
|
|
parser.add_argument("--conf-thres", type=float, default=0.25, help="confidence threshold")
|
|
parser.add_argument("--iou-thres", type=float, default=0.45, help="NMS IoU threshold")
|
|
parser.add_argument("--max-det", type=int, default=1000, help="maximum detections per image")
|
|
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
|
|
parser.add_argument("--view-img", action="store_true", help="show results")
|
|
parser.add_argument("--save-txt", action="store_true", help="save results to *.txt")
|
|
parser.add_argument(
|
|
"--save-format",
|
|
type=int,
|
|
default=0,
|
|
help="whether to save boxes coordinates in YOLO format or Pascal-VOC format when save-txt is True, 0 for YOLO and 1 for Pascal-VOC",
|
|
)
|
|
parser.add_argument("--save-csv", action="store_true", help="save results in CSV format")
|
|
parser.add_argument("--save-conf", action="store_true", help="save confidences in --save-txt labels")
|
|
parser.add_argument("--save-crop", action="store_true", help="save cropped prediction boxes")
|
|
parser.add_argument("--nosave", action="store_true", help="do not save images/videos")
|
|
parser.add_argument("--classes", nargs="+", type=int, help="filter by class: --classes 0, or --classes 0 2 3")
|
|
parser.add_argument("--agnostic-nms", action="store_true", help="class-agnostic NMS")
|
|
parser.add_argument("--augment", action="store_true", help="augmented inference")
|
|
parser.add_argument("--visualize", action="store_true", help="visualize features")
|
|
parser.add_argument("--update", action="store_true", help="update all models")
|
|
parser.add_argument("--project", default=ROOT / "runs/detect", help="save results to project/name")
|
|
parser.add_argument("--name", default="exp", help="save results to project/name")
|
|
parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment")
|
|
parser.add_argument("--line-thickness", default=3, type=int, help="bounding box thickness (pixels)")
|
|
parser.add_argument("--hide-labels", default=False, action="store_true", help="hide labels")
|
|
parser.add_argument("--hide-conf", default=False, action="store_true", help="hide confidences")
|
|
parser.add_argument("--half", action="store_true", help="use FP16 half-precision inference")
|
|
parser.add_argument("--dnn", action="store_true", help="use OpenCV DNN for ONNX inference")
|
|
parser.add_argument("--vid-stride", type=int, default=1, help="video frame-rate stride")
|
|
opt = parser.parse_args()
|
|
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
|
|
print_args(vars(opt))
|
|
return opt
|
|
|
|
|
|
def main(opt):
|
|
|
|
check_requirements(ROOT / "requirements.txt", exclude=("tensorboard", "thop"))
|
|
run(**vars(opt))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
opt = parse_opt()
|
|
main(opt)
|