代码收藏家技术教程 2022-07-21

YOLOv5如何进行区域目标检测（手把手教学）

YOLOv5如何进行区域目标检测（手把手教学）
提示：本项目的源码是基于yolov5 6.0版本修改

文章目录
YOLOv5如何进行区域目标检测（手把手教学）效果展示一、确定检测范围二、detect.py代码修改1.确定区域检测范围2.画检测区域线（若不想像效果图一样显示出检测区域可不添加）
总结整体detect.py修改代码

效果展示
在使用YOLOv5的有些时候，我们会遇到一些具体的目标检测要求，比如要求不检测全图，只在规定的区域内才检测。所以为了满足这个需求，可以用一个mask覆盖掉不想检测的区域，使得YOLOv5在检测的时候，该覆盖区域就不纳入检测范围。
话不多说，直接上检测效果，可以很直观的看到目标在进入规定的检测区域才得到检测。

一、确定检测范围
快捷查询方法：
用windows自带画图打开图片鼠标移到想要框选检测区域的四个顶点，查询点的像素坐标分别计算点的像素坐标与图片总像素坐标的比例（后面要用）查询方法如下图所示：提示：以下是计算的举例说明，仅供参考例如：图中所标注的点（1010，174）代表（x，y）坐标 hl1 = 174 / 768 （可约分）监测区域纵坐标距离图片***顶部*** 比例 wl1 = 1010 / 1614 （可约分）监测区域横坐标距离图片***左部*** 比例这里只举例了一个点，如检测范围是四边形，需要计算左上，右上，右下，左下四个顶点。
二、detect.py代码修改
1.确定区域检测范围

在下面代码位置填上计算好的比例：

# mask for certain region
#1,2,3,4 分别对应左上，右上，右下，左下四个点
hl1 = 1.4 / 10 #监测区域高度距离图片顶部比例
wl1 = 6.4 / 10 #监测区域高度距离图片左部比例
hl2 = 1.4 / 10 # 监测区域高度距离图片顶部比例
wl2 = 6.8 / 10 # 监测区域高度距离图片左部比例
hl3 = 4.5 / 10 # 监测区域高度距离图片顶部比例
wl3 = 7.6 / 10 # 监测区域高度距离图片左部比例
hl4 = 4.5 / 10 # 监测区域高度距离图片顶部比例
wl4 = 5.5 / 10 # 监测区域高度距离图片左部比例

在135行：for path, img, im0s, vid_cap in dataset: 下插入代码：

# mask for certain region
#1,2,3,4 分别对应左上，右上，右下，左下四个点
hl1 = 1.6 / 10 #监测区域高度距离图片顶部比例
wl1 = 6.4 / 10 #监测区域高度距离图片左部比例
hl2 = 1.6 / 10 # 监测区域高度距离图片顶部比例
wl2 = 6.8 / 10 # 监测区域高度距离图片左部比例
hl3 = 4.5 / 10 # 监测区域高度距离图片顶部比例
wl3 = 7.6 / 10 # 监测区域高度距离图片左部比例
hl4 = 4.5 / 10 # 监测区域高度距离图片顶部比例
wl4 = 5.5 / 10 # 监测区域高度距离图片左部比例
if webcam:
for b in range(0,img.shape[0]):
mask = np.zeros([img[b].shape[1], img[b].shape[2]], dtype=np.uint8)
#mask[round(img[b].shape[1] * hl1):img[b].shape[1], round(img[b].shape[2] * wl1):img[b].shape[2]] = 255
pts = np.array([[int(img[b].shape[2] * wl1), int(img[b].shape[1] * hl1)], # pts1
[int(img[b].shape[2] * wl2), int(img[b].shape[1] * hl2)], # pts2
[int(img[b].shape[2] * wl3), int(img[b].shape[1] * hl3)], # pts3
[int(img[b].shape[2] * wl4), int(img[b].shape[1] * hl4)]], np.int32)
mask = cv2.fillPoly(mask,[pts],(255,255,255))
imgc = img[b].transpose((1, 2, 0))
imgc = cv2.add(imgc, np.zeros(np.shape(imgc), dtype=np.uint8), mask=mask)
#cv2.imshow('1',imgc)
img[b] = imgc.transpose((2, 0, 1))

else:
mask = np.zeros([img.shape[1], img.shape[2]], dtype=np.uint8)
#mask[round(img.shape[1] * hl1):img.shape[1], round(img.shape[2] * wl1):img.shape[2]] = 255
pts = np.array([[int(img.shape[2] * wl1), int(img.shape[1] * hl1)], # pts1
[int(img.shape[2] * wl2), int(img.shape[1] * hl2)], # pts2
[int(img.shape[2] * wl3), int(img.shape[1] * hl3)], # pts3
[int(img.shape[2] * wl4), int(img.shape[1] * hl4)]], np.int32)
mask = cv2.fillPoly(mask, [pts], (255,255,255))
img = img.transpose((1, 2, 0))
img = cv2.add(img, np.zeros(np.shape(img), dtype=np.uint8), mask=mask)
img = img.transpose((2, 0, 1))

2.画检测区域线（若不想像效果图一样显示出检测区域可不添加）

在196行： p, s, im0, frame = path, ‘’, im0s.copy(), getattr(dataset, ‘frame’, 0) 后添加

if webcam: # batch_size >= 1
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
cv2.putText(im0, "Detection_Region", (int(im0.shape[1] * wl1 – 5), int(im0.shape[0] * hl1 – 5)),
cv2.FONT_HERSHEY_SIMPLEX,
1.0, (255, 255, 0), 2, cv2.LINE_AA)

pts = np.array([[int(im0.shape[1] * wl1), int(im0.shape[0] * hl1)], # pts1
[int(im0.shape[1] * wl2), int(im0.shape[0] * hl2)], # pts2
[int(im0.shape[1] * wl3), int(im0.shape[0] * hl3)], # pts3
[int(im0.shape[1] * wl4), int(im0.shape[0] * hl4)]], np.int32) # pts4
# pts = pts.reshape((-1, 1, 2))
zeros = np.zeros((im0.shape), dtype=np.uint8)
mask = cv2.fillPoly(zeros, [pts], color=(0, 165, 255))
im0 = cv2.addWeighted(im0, 1, mask, 0.2, 0)
cv2.polylines(im0, [pts], True, (255, 255, 0), 3)
# plot_one_box(dr, im0, label='Detection_Region', color=(0, 255, 0), line_thickness=2)
else:
p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
cv2.putText(im0, "Detection_Region", (int(im0.shape[1] * wl1 – 5), int(im0.shape[0] * hl1 – 5)),
cv2.FONT_HERSHEY_SIMPLEX,
1.0, (255, 255, 0), 2, cv2.LINE_AA)
pts = np.array([[int(im0.shape[1] * wl1), int(im0.shape[0] * hl1)], # pts1
[int(im0.shape[1] * wl2), int(im0.shape[0] * hl2)], # pts2
[int(im0.shape[1] * wl3), int(im0.shape[0] * hl3)], # pts3
[int(im0.shape[1] * wl4), int(im0.shape[0] * hl4)]], np.int32) # pts4
# pts = pts.reshape((-1, 1, 2))
zeros = np.zeros((im0.shape), dtype=np.uint8)
mask = cv2.fillPoly(zeros, [pts], color=(0, 165, 255))
im0 = cv2.addWeighted(im0, 1, mask, 0.2, 0)

cv2.polylines(im0, [pts], True, (255, 255, 0), 3)

总结
基于yolov5的区域目标检测实质上就是在图片选定检测区域做一个遮掩mask，检测区域不一定为四边形，也可是其他形状。该方法可检测图片/视频/摄像头。提示：使用该方法要先确定数据集图像是否像监控图像一样，画面主体保持不变原理展现如图所示：（图片参考http://t.csdn.cn/lgyO1）
整体detect.py修改代码
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Run inference on images, videos, directories, streams, etc.

Usage:
$ python path/to/detect.py –source path/to/img.jpg –weights yolov5s.pt –img 640
"""

import argparse
import os
import sys
from pathlib import Path

import cv2
import numpy as np
import torch
import torch.backends.cudnn as cudnn

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 models.experimental import attempt_load
from utils.datasets import LoadImages, LoadStreams
from utils.general import apply_classifier, check_img_size, check_imshow, check_requirements, check_suffix, colorstr, \
increment_path, non_max_suppression, print_args, save_one_box, scale_coords, set_logging, \
strip_optimizer, xyxy2xywh
from utils.plots import Annotator, colors
from utils.torch_utils import load_classifier, select_device, time_sync

@torch.no_grad()
def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
imgsz=640, # inference size (pixels)
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_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
):
source = str(source)
save_img = not nosave and not source.endswith('.txt') # save inference images
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))

# 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

# Initialize
set_logging()
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA

# Load model
w = str(weights[0] if isinstance(weights, list) else weights)
classify, suffix, suffixes = False, Path(w).suffix.lower(), ['.pt', '.onnx', '.tflite', '.pb', '']
check_suffix(w, suffixes) # check weights have acceptable suffix
pt, onnx, tflite, pb, saved_model = (suffix == x for x in suffixes) # backend booleans
stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
if pt:
model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device)
stride = int(model.stride.max()) # model stride
names = model.module.names if hasattr(model, 'module') else model.names # get class names
if half:
model.half() # to FP16
if classify: # second-stage classifier
modelc = load_classifier(name='resnet50', n=2) # initialize
modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()
elif onnx:
if dnn:
# check_requirements(('opencv-python>=4.5.4',))
net = cv2.dnn.readNetFromONNX(w)
else:
check_requirements(('onnx', 'onnxruntime'))
import onnxruntime
session = onnxruntime.InferenceSession(w, None)
else: # TensorFlow models
check_requirements(('tensorflow>=2.4.1',))
import tensorflow as tf
if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
def wrap_frozen_graph(gd, inputs, outputs):
x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped import
return x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs),
tf.nest.map_structure(x.graph.as_graph_element, outputs))

graph_def = tf.Graph().as_graph_def()
graph_def.ParseFromString(open(w, 'rb').read())
frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0")
elif saved_model:
model = tf.keras.models.load_model(w)
elif tflite:
interpreter = tf.lite.Interpreter(model_path=w) # load TFLite model
interpreter.allocate_tensors() # allocate
input_details = interpreter.get_input_details() # inputs
output_details = interpreter.get_output_details() # outputs
int8 = input_details[0]['dtype'] == np.uint8 # is TFLite quantized uint8 model
imgsz = check_img_size(imgsz, s=stride) # check image size

# Dataloader
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs

# Run inference
if pt and device.type != 'cpu':
model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.parameters()))) # run once
dt, seen = [0.0, 0.0, 0.0], 0
for path, img, im0s, vid_cap in dataset:
# mask for certain region
#1,2,3,4 分别对应左上，右上，右下，左下四个点
hl1 = 1.6 / 10 #监测区域高度距离图片顶部比例
wl1 = 6.4 / 10 #监测区域高度距离图片左部比例
hl2 = 1.6 / 10 # 监测区域高度距离图片顶部比例
wl2 = 6.8 / 10 # 监测区域高度距离图片左部比例
hl3 = 4.5 / 10 # 监测区域高度距离图片顶部比例
wl3 = 7.6 / 10 # 监测区域高度距离图片左部比例
hl4 = 4.5 / 10 # 监测区域高度距离图片顶部比例
wl4 = 5.5 / 10 # 监测区域高度距离图片左部比例
if webcam:
for b in range(0,img.shape[0]):
mask = np.zeros([img[b].shape[1], img[b].shape[2]], dtype=np.uint8)
#mask[round(img[b].shape[1] * hl1):img[b].shape[1], round(img[b].shape[2] * wl1):img[b].shape[2]] = 255
pts = np.array([[int(img[b].shape[2] * wl1), int(img[b].shape[1] * hl1)], # pts1
[int(img[b].shape[2] * wl2), int(img[b].shape[1] * hl2)], # pts2
[int(img[b].shape[2] * wl3), int(img[b].shape[1] * hl3)], # pts3
[int(img[b].shape[2] * wl4), int(img[b].shape[1] * hl4)]], np.int32)
mask = cv2.fillPoly(mask,[pts],(255,255,255))
imgc = img[b].transpose((1, 2, 0))
imgc = cv2.add(imgc, np.zeros(np.shape(imgc), dtype=np.uint8), mask=mask)
#cv2.imshow('1',imgc)
img[b] = imgc.transpose((2, 0, 1))

t1 = time_sync()
if onnx:
img = img.astype('float32')
else:
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img = img / 255.0 # 0 – 255 to 0.0 – 1.0
if len(img.shape) == 3:
img = img[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 – t1

# Inference
if pt:
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(img, augment=augment, visualize=visualize)[0]
elif onnx:
if dnn:
net.setInput(img)
pred = torch.tensor(net.forward())
else:
pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img}))
else: # tensorflow model (tflite, pb, saved_model)
imn = img.permute(0, 2, 3, 1).cpu().numpy() # image in numpy
if pb:
pred = frozen_func(x=tf.constant(imn)).numpy()
elif saved_model:
pred = model(imn, training=False).numpy()
elif tflite:
if int8:
scale, zero_point = input_details[0]['quantization']
imn = (imn / scale + zero_point).astype(np.uint8) # de-scale
interpreter.set_tensor(input_details[0]['index'], imn)
interpreter.invoke()
pred = interpreter.get_tensor(output_details[0]['index'])
if int8:
scale, zero_point = output_details[0]['quantization']
pred = (pred.astype(np.float32) – zero_point) * scale # re-scale
pred[…, 0] *= imgsz[1] # x
pred[…, 1] *= imgsz[0] # y
pred[…, 2] *= imgsz[1] # w
pred[…, 3] *= imgsz[0] # h
pred = torch.tensor(pred)
t3 = time_sync()
dt[1] += t3 – t2

# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
dt[2] += time_sync() – t3

# Second-stage classifier (optional)
if classify:
pred = apply_classifier(pred, modelc, img, im0s)

# Process predictions
for i, det in enumerate(pred): # per image
seen += 1
# if webcam: # batch_size >= 1
# p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
# else:
# p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
cv2.putText(im0, "Detection_Region", (int(im0.shape[1] * wl1 – 5), int(im0.shape[0] * hl1 – 5)),
cv2.FONT_HERSHEY_SIMPLEX,
1.0, (255, 255, 0), 2, cv2.LINE_AA)

cv2.polylines(im0, [pts], True, (255, 255, 0), 3)

p = Path(p) # to Path
save_path = str(save_dir / p.name) # img.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
s += '%gx%g ' % img.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_coords(img.shape[2:], det[:, :4], im0.shape).round()

# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == 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):
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(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)

# Print time (inference-only)
print(f'{s}Done. ({t3 – t2:.3f}s)')

# Stream results
im0 = annotator.result()
if view_img:
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 += '.mp4'
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)

# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
print(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 ''
print(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)

def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('–weights', nargs='+', type=str, default=ROOT / '权重文件', help='model path(s)')
parser.add_argument('–source', type=str, default=ROOT / '检测图片', help='file/dir/URL/glob, 0 for webcam')
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-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=1, type=int, help='bounding box thickness (pixels)')
parser.add_argument('–hide-labels', default=True, 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')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(FILE.stem, opt)
return opt