663 lines
31 KiB
Python
663 lines
31 KiB
Python
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
|
"""
|
|
Run prediction on images, videos, directories, globs, YouTube, webcam, streams, etc.
|
|
|
|
Usage - sources:
|
|
$ yolo mode=predict model=yolov8n.pt source=0 # webcam
|
|
img.jpg # image
|
|
vid.mp4 # video
|
|
screen # screenshot
|
|
path/ # directory
|
|
list.txt # list of images
|
|
list.streams # list of streams
|
|
'path/*.jpg' # glob
|
|
'https://youtu.be/Zgi9g1ksQHc' # YouTube
|
|
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
|
|
|
|
Usage - formats:
|
|
$ yolo mode=predict model=yolov8n.pt # PyTorch
|
|
yolov8n.torchscript # TorchScript
|
|
yolov8n.onnx # ONNX Runtime or OpenCV DNN with dnn=True
|
|
yolov8n_openvino_model # OpenVINO
|
|
yolov8n.engine # TensorRT
|
|
yolov8n.mlmodel # CoreML (macOS-only)
|
|
yolov8n_saved_model # TensorFlow SavedModel
|
|
yolov8n.pb # TensorFlow GraphDef
|
|
yolov8n.tflite # TensorFlow Lite
|
|
yolov8n_edgetpu.tflite # TensorFlow Edge TPU
|
|
yolov8n_paddle_model # PaddlePaddle
|
|
"""
|
|
import math
|
|
import os
|
|
import platform
|
|
import time
|
|
from math import sqrt
|
|
from pathlib import Path
|
|
from random import random
|
|
|
|
import cv2
|
|
import numpy as np
|
|
import torch
|
|
from PIL import Image
|
|
|
|
from ultralytics.nn.autobackend import AutoBackend
|
|
from ultralytics.yolo.cfg import get_cfg
|
|
from ultralytics.yolo.data import load_inference_source
|
|
from ultralytics.yolo.data.augment import LetterBox, classify_transforms
|
|
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, SETTINGS, callbacks, colorstr, ops
|
|
from ultralytics.yolo.utils.checks import check_imgsz, check_imshow
|
|
from ultralytics.yolo.utils.files import increment_path
|
|
from ultralytics.yolo.utils.torch_utils import select_device, smart_inference_mode
|
|
from ultralytics.yolo.engine.ids import check_tings
|
|
|
|
|
|
STREAM_WARNING = """
|
|
WARNING ⚠️ stream/video/webcam/dir predict source will accumulate results in RAM unless `stream=True` is passed,
|
|
causing potential out-of-memory errors for large sources or long-running streams/videos.
|
|
|
|
Usage:
|
|
results = model(source=..., stream=True) # generator of Results objects
|
|
for r in results:
|
|
boxes = r.boxes # Boxes object for bbox outputs
|
|
masks = r.masks # Masks object for segment masks outputs
|
|
probs = r.probs # Class probabilities for classification outputs
|
|
"""
|
|
|
|
|
|
class BasePredictor:
|
|
"""
|
|
BasePredictor
|
|
|
|
A base class for creating predictors.
|
|
|
|
Attributes:
|
|
args (SimpleNamespace): Configuration for the predictor.
|
|
save_dir (Path): Directory to save results.
|
|
done_setup (bool): Whether the predictor has finished setup.
|
|
model (nn.Module): Model used for prediction.
|
|
data (dict): Data configuration.
|
|
device (torch.device): Device used for prediction.
|
|
dataset (Dataset): Dataset used for prediction.
|
|
vid_path (str): Path to video file.
|
|
vid_writer (cv2.VideoWriter): Video writer for saving video output.
|
|
annotator (Annotator): Annotator used for prediction.
|
|
data_path (str): Path to data.
|
|
"""
|
|
|
|
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
|
|
"""
|
|
Initializes the BasePredictor class.
|
|
|
|
Args:
|
|
cfg (str, optional): Path to a configuration file. Defaults to DEFAULT_CFG.
|
|
overrides (dict, optional): Configuration overrides. Defaults to None.
|
|
"""
|
|
# self.real_MovBox = None
|
|
self.args = get_cfg(cfg, overrides)
|
|
project = self.args.project or Path(SETTINGS['runs_dir']) / self.args.task
|
|
name = self.args.name or f'{self.args.mode}'
|
|
self.save_dir = increment_path(Path(project) / name, exist_ok=self.args.exist_ok)
|
|
if self.args.conf is None:
|
|
self.args.conf = 0.25 # default conf=0.25
|
|
self.done_warmup = False
|
|
if self.args.show:
|
|
self.args.show = check_imshow(warn=True)
|
|
|
|
# Usable if setup is done
|
|
self.model = None
|
|
self.data = self.args.data # data_dict
|
|
self.imgsz = None
|
|
self.device = None
|
|
self.dataset = None
|
|
self.vid_path, self.vid_writer = None, None
|
|
self.plotted_img = None
|
|
self.data_path = None
|
|
self.source_type = None
|
|
self.batch = None
|
|
self.callbacks = _callbacks or callbacks.get_default_callbacks()
|
|
callbacks.add_integration_callbacks(self)
|
|
|
|
def preprocess(self, im):
|
|
"""Prepares input image before inference.
|
|
|
|
Args:
|
|
im (torch.Tensor | List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list.
|
|
"""
|
|
if not isinstance(im, torch.Tensor):
|
|
im = np.stack(self.pre_transform(im)) #size(640,XX)
|
|
im = im[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW, (n, 3, h, w)
|
|
im = np.ascontiguousarray(im) # contiguous
|
|
im = torch.from_numpy(im)
|
|
# NOTE: assuming im with (b, 3, h, w) if it's a tensor
|
|
img = im.to(self.device)
|
|
img = img.half() if self.model.fp16 else img.float() # uint8 to fp16/32
|
|
img /= 255 # 0 - 255 to 0.0 - 1.0
|
|
return img
|
|
|
|
def pre_transform(self, im):
|
|
"""Pre-tranform input image before inference.
|
|
|
|
Args:
|
|
im (List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list.
|
|
|
|
Return: A list of transformed imgs.
|
|
"""
|
|
same_shapes = all(x.shape == im[0].shape for x in im)
|
|
auto = same_shapes and self.model.pt
|
|
return [LetterBox(self.imgsz, auto=auto, stride=self.model.stride)(image=x) for x in im]
|
|
|
|
def write_results(self, idx, results, batch):
|
|
"""Write inference results to a file or directory."""
|
|
p, im, _ = batch
|
|
log_string = ''
|
|
if len(im.shape) == 3:
|
|
im = im[None] # expand for batch dim
|
|
self.seen += 1
|
|
if self.source_type.webcam or self.source_type.from_img: # batch_size >= 1
|
|
log_string += f'{idx}: '
|
|
frame = self.dataset.count
|
|
else:
|
|
frame = getattr(self.dataset, 'frame', 0)
|
|
self.data_path = p
|
|
self.txt_path = str(self.save_dir / 'labels' / p.stem) + ('' if self.dataset.mode == 'image' else f'_{frame}')
|
|
log_string += '%gx%g ' % im.shape[2:] # print string
|
|
result = results[idx]
|
|
# print('result', result)
|
|
log_string += result.verbose()
|
|
|
|
if self.args.save or self.args.show: # Add bbox to image
|
|
plot_args = dict(line_width=self.args.line_width,
|
|
boxes=self.args.boxes,
|
|
conf=self.args.show_conf,
|
|
labels=self.args.show_labels)
|
|
if not self.args.retina_masks:
|
|
plot_args['im_gpu'] = im[idx]
|
|
self.plotted_img = result.plot(**plot_args)
|
|
# Write
|
|
if self.args.save_txt:
|
|
result.save_txt(f'{self.txt_path}.txt', save_conf=self.args.save_conf)
|
|
if self.args.save_crop:
|
|
result.save_crop(save_dir=self.save_dir / 'crops', file_name=self.data_path.stem)
|
|
|
|
return log_string
|
|
|
|
def postprocess(self, preds, img, orig_img):
|
|
"""Post-processes predictions for an image and returns them."""
|
|
return preds
|
|
def boxesMov_output(self, path, img_MovBoxes):
|
|
return img_MovBoxes
|
|
|
|
def __call__(self, source=None, model=None, stream=False):
|
|
"""Performs inference on an image or stream."""
|
|
self.stream = stream
|
|
if stream:
|
|
return self.stream_inference(source, model)
|
|
else:
|
|
# print('*****************',list(self.stream_inference(source, model)))
|
|
return list(self.stream_inference(source, model)) # merge list of Result into one
|
|
|
|
def predict_cli(self, source=None, model=None):
|
|
"""Method used for CLI prediction. It uses always generator as outputs as not required by CLI mode."""
|
|
gen = self.stream_inference(source, model)
|
|
for _ in gen: # running CLI inference without accumulating any outputs (do not modify)
|
|
pass
|
|
|
|
def setup_source(self, source):
|
|
"""Sets up source and inference mode."""
|
|
self.imgsz = check_imgsz(self.args.imgsz, stride=self.model.stride, min_dim=2) # check image size
|
|
self.transforms = getattr(self.model.model, 'transforms', classify_transforms(
|
|
self.imgsz[0])) if self.args.task == 'classify' else None
|
|
self.dataset = load_inference_source(source=source, imgsz=self.imgsz, vid_stride=self.args.vid_stride)
|
|
self.dataset0 = load_inference_source(source=source, imgsz=self.imgsz, vid_stride=self.args.vid_stride)
|
|
self.source_type = self.dataset.source_type
|
|
if not getattr(self, 'stream', True) and (self.dataset.mode == 'stream' or # streams
|
|
len(self.dataset) > 1000 or # images
|
|
any(getattr(self.dataset, 'video_flag', [False]))): # videos
|
|
LOGGER.warning(STREAM_WARNING)
|
|
self.vid_path, self.vid_writer = [None] * self.dataset.bs, [None] * self.dataset.bs
|
|
|
|
|
|
|
|
@smart_inference_mode()
|
|
def stream_inference(self, source=None, model=None):
|
|
"""Streams real-time inference on camera feed and saves results to file."""
|
|
if self.args.verbose:
|
|
LOGGER.info('')
|
|
# Setup model
|
|
if not self.model:
|
|
self.setup_model(model)
|
|
# Setup source every time predict is called
|
|
self.setup_source(source if source is not None else self.args.source)
|
|
|
|
# Check if save_dir/ label file exists
|
|
if self.args.save or self.args.save_txt:
|
|
(self.save_dir / 'labels' if self.args.save_txt else self.save_dir).mkdir(parents=True, exist_ok=True)
|
|
# Warmup model
|
|
if not self.done_warmup:
|
|
self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz))
|
|
self.done_warmup = True
|
|
self.seen, self.windows, self.batch, self.batch0, profilers = 0, [], None, None, (ops.Profile(), ops.Profile(), ops.Profile())
|
|
self.run_callbacks('on_predict_start')
|
|
allMovBoxes = []
|
|
boxesAll = []
|
|
id = 0
|
|
img_MovBoxes = []
|
|
idx = []
|
|
id0 = 0
|
|
fgbg = cv2.createBackgroundSubtractorMOG2(history=500, varThreshold=16, detectShadows=True)
|
|
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
|
|
for batch0 in self.dataset0:
|
|
path, im0, vid_cap, s = batch0
|
|
id0 += 1
|
|
# video_len = int(str(s).split(')')[0].split('/')[-1])
|
|
# print('video_len', id0, video_len)
|
|
img0 = np.array(im0).squeeze()
|
|
frame = cv2.resize(img0, (512, 640), interpolation=cv2.INTER_CUBIC)
|
|
frame = cv2.medianBlur(frame, ksize=3)
|
|
# 计算前景掩码
|
|
fgmask = fgbg.apply(frame)
|
|
draw1 = cv2.threshold(fgmask, 230, 255, cv2.THRESH_BINARY)[1] # 二值化
|
|
draw1 = cv2.erode(draw1, kernel, iterations=1)
|
|
draw1 = cv2.dilate(draw1, kernel, iterations=1)
|
|
dics = {}
|
|
contours_m, hierarchy_m = cv2.findContours(draw1.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
|
for contour in contours_m:
|
|
dics[len(contour)] = contour
|
|
if len(dics.keys()) > 0:
|
|
cc = sorted(dics.keys())
|
|
iouArea = cv2.contourArea(dics[cc[-1]])
|
|
print("***********id0", id0, iouArea)
|
|
if iouArea>3000:
|
|
idx.append(id0)
|
|
|
|
# if len(idx) != 0 and abs(id0 - idx[-1]) > 30:
|
|
# break
|
|
# print('*******id0', id0, idx)
|
|
if len(idx) != 0:
|
|
idx.sort()
|
|
print('idx', idx)
|
|
for batch in self.dataset:
|
|
t0 = time.time()
|
|
id += 1
|
|
if idx[0] <= id <= idx[-1]:
|
|
self.run_callbacks('on_predict_batch_start')
|
|
self.batch = batch
|
|
path, im0s, vid_cap, s = batch
|
|
|
|
visualize = increment_path(self.save_dir / Path(path[0]).stem,
|
|
mkdir=True) if self.args.visualize and (not self.source_type.tensor) else False
|
|
# Preprocess
|
|
with profilers[0]:
|
|
im = self.preprocess(im0s)
|
|
|
|
# Inference
|
|
with profilers[1]:
|
|
preds = self.model(im, augment=self.args.augment, visualize=visualize)
|
|
|
|
# Postprocess
|
|
with profilers[2]:
|
|
self.results = self.postprocess(preds, im, im0s)
|
|
|
|
self.run_callbacks('on_predict_postprocess_end')
|
|
|
|
# Visualize, save, write results
|
|
n = len(im0s)
|
|
for i in range(n):
|
|
tt0 = time.time()
|
|
im1 = im0s[i].copy()
|
|
### create class MovingBox
|
|
boxesMov = MovingBox(id, self.results[i].boxes.xywh, self.results[i].boxes.xyxy, self.results[i].boxes.conf, path)
|
|
if id == idx[0]:
|
|
boxesAll= boxesMov._initiate_box()
|
|
else:
|
|
### allMovBoxes->是运动框的坐标
|
|
boxesAll, allMovBoxes = boxesMov.update(boxesAll, im1, self.save_dir)
|
|
if len(allMovBoxes) != 0:
|
|
mov_id = 0
|
|
for box in allMovBoxes:
|
|
box_xyxy = xywh2xyxy(box[0])
|
|
cropMov = im0s[i][int(box_xyxy[1]):int(box_xyxy[3]), int(box_xyxy[0]):int(box_xyxy[2]), ::-1]
|
|
# crop_save = os.path.abspath(im0s[i])
|
|
# Image.fromarray(cropMov).show()
|
|
### img_MovBoxes->运动商品图片
|
|
img_MovBoxes.append([id, cropMov])
|
|
tt1 = time.time() - tt0
|
|
# print('运动框判断所需时间{}s'.format(tt1))
|
|
crop_save = self.save_dir / 'movboxes/'
|
|
ori_img = self.save_dir / 'oriImage/'
|
|
if not os.path.exists(crop_save):
|
|
# crop_save.parent.mkdir(parents=True, exist_ok=True)
|
|
crop_save.mkdir(parents=True, exist_ok=True)
|
|
if not os.path.exists(ori_img):
|
|
ori_img.mkdir()
|
|
f = str(crop_save) + '\\frame' + str(id) + '_' + str(mov_id) + '_' + '.jpg'
|
|
g = str(ori_img) + '\\frame' + str(id) + '_' + '.jpg'
|
|
# Image.fromarray(cropMov[::-1]).save(f, quality=95, subsampling=0)
|
|
Image.fromarray(cropMov).save(f, quality=95, subsampling=0)
|
|
# Image.fromarray(im1[:,:,::-1]).save(g, quality=95, subsampling=0)
|
|
mov_id += 1
|
|
|
|
self.results[i].speed = {
|
|
'preprocess': profilers[0].dt * 1E3 / n,
|
|
'inference': profilers[1].dt * 1E3 / n,
|
|
'postprocess': profilers[2].dt * 1E3 / n}
|
|
if self.source_type.tensor: # skip write, show and plot operations if input is raw tensor
|
|
continue
|
|
p, im0 = path[i], im0s[i].copy()
|
|
p = Path(p)
|
|
if self.args.verbose or self.args.save or self.args.save_txt or self.args.show:
|
|
s += self.write_results(i, self.results, (p, im, im0))
|
|
if self.args.show and self.plotted_img is not None:
|
|
self.show(p)
|
|
|
|
if self.args.save and self.plotted_img is not None:
|
|
self.save_preds(vid_cap, i, str(self.save_dir / p.name))
|
|
elif id < idx[0]:
|
|
# self.results = []
|
|
continue
|
|
else:
|
|
break
|
|
else:
|
|
for batch in self.dataset:
|
|
t0 = time.time()
|
|
id += 1
|
|
self.run_callbacks('on_predict_batch_start')
|
|
self.batch = batch
|
|
path, im0s, vid_cap, s = batch
|
|
|
|
visualize = increment_path(self.save_dir / Path(path[0]).stem,
|
|
mkdir=True) if self.args.visualize and (
|
|
not self.source_type.tensor) else False
|
|
# Preprocess
|
|
with profilers[0]:
|
|
im = self.preprocess(im0s)
|
|
|
|
# Inference
|
|
with profilers[1]:
|
|
preds = self.model(im, augment=self.args.augment, visualize=visualize)
|
|
|
|
# Postprocess
|
|
with profilers[2]:
|
|
self.results = self.postprocess(preds, im, im0s)
|
|
|
|
self.run_callbacks('on_predict_postprocess_end')
|
|
|
|
# Visualize, save, write results
|
|
n = len(im0s)
|
|
for i in range(n):
|
|
tt0 = time.time()
|
|
im1 = im0s[i].copy()
|
|
### create class MovingBox
|
|
boxesMov = MovingBox(id, self.results[i].boxes.xywh, self.results[i].boxes.xyxy,
|
|
self.results[i].boxes.conf, path)
|
|
if id == 1:
|
|
boxesAll = boxesMov._initiate_box()
|
|
else:
|
|
### allMovBoxes->是运动框的坐标
|
|
boxesAll, allMovBoxes = boxesMov.update(boxesAll, im1, self.save_dir)
|
|
if len(allMovBoxes) != 0:
|
|
mov_id = 0
|
|
for box in allMovBoxes:
|
|
box_xyxy = xywh2xyxy(box[0])
|
|
cropMov = im0s[i][int(box_xyxy[1]):int(box_xyxy[3]), int(box_xyxy[0]):int(box_xyxy[2]),
|
|
::-1]
|
|
# crop_save = os.path.abspath(im0s[i])
|
|
# Image.fromarray(cropMov).show()
|
|
### img_MovBoxes->运动商品图片
|
|
img_MovBoxes.append([id, cropMov])
|
|
tt1 = time.time() - tt0
|
|
# print('运动框判断所需时间{}s'.format(tt1))
|
|
crop_save = self.save_dir / 'movboxes/'
|
|
ori_img = self.save_dir / 'oriImage/'
|
|
if not os.path.exists(crop_save):
|
|
# crop_save.parent.mkdir(parents=True, exist_ok=True)
|
|
crop_save.mkdir(parents=True, exist_ok=True)
|
|
if not os.path.exists(ori_img):
|
|
ori_img.mkdir()
|
|
f = str(crop_save) + '\\frame' + str(id) + '_' + str(mov_id) + '_' + '.jpg'
|
|
g = str(ori_img) + '\\frame' + str(id) + '_' + '.jpg'
|
|
# Image.fromarray(cropMov[::-1]).save(f, quality=95, subsampling=0)
|
|
Image.fromarray(cropMov).save(f, quality=95, subsampling=0)
|
|
# Image.fromarray(im1[:,:,::-1]).save(g, quality=95, subsampling=0)
|
|
mov_id += 1
|
|
|
|
self.results[i].speed = {
|
|
'preprocess': profilers[0].dt * 1E3 / n,
|
|
'inference': profilers[1].dt * 1E3 / n,
|
|
'postprocess': profilers[2].dt * 1E3 / n}
|
|
if self.source_type.tensor: # skip write, show and plot operations if input is raw tensor
|
|
continue
|
|
p, im0 = path[i], im0s[i].copy()
|
|
p = Path(p)
|
|
if self.args.verbose or self.args.save or self.args.save_txt or self.args.show:
|
|
s += self.write_results(i, self.results, (p, im, im0))
|
|
if self.args.show and self.plotted_img is not None:
|
|
self.show(p)
|
|
|
|
if self.args.save and self.plotted_img is not None:
|
|
self.save_preds(vid_cap, i, str(self.save_dir / p.name))
|
|
|
|
self.run_callbacks('on_predict_batch_end')
|
|
yield from self.results
|
|
# Print time (inference-only)
|
|
if self.args.verbose:
|
|
LOGGER.info(f'{s}{profilers[1].dt * 1E3:.1f}ms')
|
|
t1 = time.time() - t0
|
|
# print('推理所需时间：{}s'.format(t1))
|
|
|
|
t2 = time.time()
|
|
self.real_MovBox = self.boxesMov_output(path, img_MovBoxes)
|
|
for i in range(len(self.results)):
|
|
self.results[i].movBoxes = self.real_MovBox
|
|
# print("self.results11111111111", self.results[i])
|
|
t3 = time.time() - t2
|
|
print('保留最后十帧所有运动框所需时间：{}s'.format(t3))
|
|
|
|
# Release assets
|
|
if isinstance(self.vid_writer[-1], cv2.VideoWriter):
|
|
self.vid_writer[-1].release() # release final video writer
|
|
|
|
# Print results
|
|
if self.args.verbose and self.seen:
|
|
t = tuple(x.t / self.seen * 1E3 for x in profilers) # speeds per image
|
|
LOGGER.info(f'Speed: %.1fms preprocess, %.1fms inference, %.1fms postprocess per image at shape '
|
|
f'{(1, 3, *self.imgsz)}' % t)
|
|
if self.args.save or self.args.save_txt or self.args.save_crop:
|
|
nl = len(list(self.save_dir.glob('labels/*.txt'))) # number of labels
|
|
s = f"\n{nl} label{'s' * (nl > 1)} saved to {self.save_dir / 'labels'}" if self.args.save_txt else ''
|
|
LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}{s}")
|
|
|
|
self.run_callbacks('on_predict_end')
|
|
|
|
|
|
|
|
def setup_model(self, model, verbose=True):
|
|
"""Initialize YOLO model with given parameters and set it to evaluation mode."""
|
|
device = select_device(self.args.device, verbose=verbose)
|
|
model = model or self.args.model
|
|
self.args.half &= device.type != 'cpu' # half precision only supported on CUDA
|
|
self.model = AutoBackend(model,
|
|
device=device,
|
|
dnn=self.args.dnn,
|
|
data=self.args.data,
|
|
fp16=self.args.half,
|
|
fuse=True,
|
|
verbose=verbose)
|
|
self.device = device
|
|
self.model.eval()
|
|
|
|
def show(self, p):
|
|
"""Display an image in a window using OpenCV imshow()."""
|
|
im0 = self.plotted_img
|
|
if platform.system() == 'Linux' and p not in self.windows:
|
|
self.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(500 if self.batch[3].startswith('image') else 1) # 1 millisecond
|
|
|
|
def save_preds(self, vid_cap, idx, save_path):
|
|
"""Save video predictions as mp4 at specified path."""
|
|
im0 = self.plotted_img
|
|
# Save imgs
|
|
if self.dataset.mode == 'image':
|
|
cv2.imwrite(save_path, im0)
|
|
else: # 'video' or 'stream'
|
|
if self.vid_path[idx] != save_path: # new video
|
|
self.vid_path[idx] = save_path
|
|
if isinstance(self.vid_writer[idx], cv2.VideoWriter):
|
|
self.vid_writer[idx].release() # release previous video writer
|
|
if vid_cap: # video
|
|
fps = int(vid_cap.get(cv2.CAP_PROP_FPS)) # integer required, floats produce error in MP4 codec
|
|
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
|
|
self.vid_writer[idx] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
|
|
self.vid_writer[idx].write(im0)
|
|
|
|
def run_callbacks(self, event: str):
|
|
"""Runs all registered callbacks for a specific event."""
|
|
for callback in self.callbacks.get(event, []):
|
|
callback(self)
|
|
|
|
def add_callback(self, event: str, func):
|
|
"""
|
|
Add callback
|
|
"""
|
|
self.callbacks[event].append(func)
|
|
|
|
class BoxState:
|
|
Static = 0
|
|
Moving = 1
|
|
class allBoxes:
|
|
def __init__(self, fame_id, tr_id, xywh):
|
|
self.fame_id = fame_id
|
|
self.state = BoxState.Static
|
|
self.track_id = tr_id
|
|
self.xywh = xywh
|
|
def is_static(self):
|
|
return self.state == BoxState.Static
|
|
def is_moving(self):
|
|
return self.state == BoxState.Moving
|
|
def xywh2xyxy(x):
|
|
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
|
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
|
y[0] = x[0] - x[2] / 2 # top left x
|
|
y[1] = x[1] - x[3] / 2 # top left y
|
|
y[2] = x[0] + x[2] / 2 # bottom right x
|
|
y[3] = x[1] + x[3] / 2 # bottom right y
|
|
return y
|
|
def plot_one_box(x, img, trid, line_thickness=3,color=None):
|
|
# Plots one bounding box on image img
|
|
tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
|
|
# print('x',x)
|
|
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
|
|
cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
|
|
cv2.putText(img, str(trid), (c1[0], c1[1] - 2), 0, tl / 3, [0, 0, 255], thickness=6, lineType=cv2.LINE_AA)
|
|
def compute_iou(box1, box2):
|
|
xx1 = max(box1[0], box2[0])
|
|
yy1 = max(box1[1], box2[1])
|
|
xx2 = min(box1[2], box2[2])
|
|
yy2 = min(box1[3], box2[3])
|
|
w = max(0., xx2 - xx1)
|
|
h = max(0., yy2 - yy1)
|
|
wh = w * h
|
|
o = wh / ((box1[2] - box1[0]) * (box1[3] - box1[1])
|
|
+ (box2[2] - box2[0]) * (box2[3] - box2[1]) - wh)
|
|
return o
|
|
|
|
# def sort_(elem):
|
|
# return elem[0]
|
|
class MovingBox(object):
|
|
def __init__(self, frame_id, xywh, xyxy, conf, path):
|
|
# self.track_id = 0
|
|
self.frame_id = frame_id
|
|
# self.state = 1 # 0 static, 1 moving
|
|
self.xywh = xywh
|
|
self.conf = conf
|
|
self.xyxy = xyxy
|
|
self.min_thr = 0.8
|
|
self.max_thr = 1.2
|
|
self.iou_thr = 0.9
|
|
self.path = path
|
|
|
|
def _initiate_box(self):
|
|
boxes = []
|
|
state = 0
|
|
for i in range(len(self.xywh)):
|
|
boxes.append([self.xywh[i], state, self.xyxy[i]])
|
|
# print('moving_box', boxes)
|
|
return boxes
|
|
|
|
def update(self, boxes, img, save_dir):
|
|
index = []
|
|
allBoxes = []
|
|
state = 1
|
|
print(">>>>>>>>>>>>id", self.frame_id)
|
|
# if len(self.xywh) != 0: ##detect box 不为空
|
|
if len(boxes) == 0:
|
|
for i in range(len(self.xywh)):
|
|
allBoxes.append([self.xywh[i], state, self.xyxy[i]])
|
|
|
|
else:
|
|
for i in range(len(self.xywh)): ## self.xywh为当前帧的检测框
|
|
flag0 = 0 # 0 长宽比未匹配上, 1 匹配上
|
|
for j in range(len(boxes)): ## boxes为前一帧的检测框
|
|
rw = self.xywh[i][2] / boxes[j][0][2]
|
|
rh = self.xywh[i][3] / boxes[j][0][3]
|
|
area0 = boxes[j][0][2] * boxes[j][0][3]
|
|
area1 = self.xywh[i][2] * self.xywh[i][3]
|
|
area_r = area1 / area0
|
|
# print(f'detect_{i} track_{j}')
|
|
# print("rw,rh,area_r", rw, rh, area_r)
|
|
##可能短边比长边，可能长边比短边
|
|
if (rw < self.max_thr and rw > self.min_thr) and (rh < self.max_thr and rh > self.min_thr) \
|
|
and (area_r < self.max_thr and area_r > self.min_thr):
|
|
flag0 = 1
|
|
iou = compute_iou(self.xyxy[i], boxes[j][2])
|
|
print('iou',iou)
|
|
if iou > self.iou_thr:
|
|
index.append(i)
|
|
break
|
|
print("=====last_box", boxes)
|
|
print('index', index)
|
|
|
|
for i in range(len(self.xywh)):
|
|
if i in index:
|
|
state = 0
|
|
allBoxes.append([self.xywh[i], state, self.xyxy[i]])
|
|
else:
|
|
state = 1
|
|
allBoxes.append([self.xywh[i], state, self.xyxy[i]])
|
|
# track_id += 1
|
|
moving_boxes = [box for box in allBoxes if box[1]==1]
|
|
if len(self.xywh) != 0:
|
|
for i, x in enumerate(allBoxes):
|
|
xyxy = xywh2xyxy(x[0])
|
|
if x[1] == 1:
|
|
# flag = str(i) + '_moving_'
|
|
flag = 'moving_'
|
|
box_color = (0,255,0)
|
|
else:
|
|
# flag = str(i) + '_static_'
|
|
flag = 'static_'
|
|
box_color = (0,0,255)
|
|
plot_one_box(xyxy, img, f'{flag}{self.conf[i].cpu().numpy():.2f}', color=box_color)
|
|
path2 = save_dir / 'detect_result/'
|
|
if not os.path.exists(path2):
|
|
path2.mkdir(parents=True, exist_ok=True)
|
|
cv2.imwrite(os.sep.join([str(path2), str(self.path).split('.mp4')[0].split('\\')[-1]+ "_" + str(self.frame_id) + '.jpg']), img)
|
|
else:
|
|
path2 = save_dir / 'detect_result/'
|
|
if not os.path.exists(path2):
|
|
path2.mkdir(parents=True, exist_ok=True)
|
|
cv2.imwrite(os.sep.join([str(path2), str(self.path).split('.mp4')[0].split('\\')[-1] + "_" + str(self.frame_id) + '.jpg']), img)
|
|
return allBoxes, moving_boxes
|
|
|
|
|
|
|
|
|
|
|