使用PyTorch实现目标检测和跟踪
python教程栏目介绍使用PyTorch实现目标检测与跟踪
引言
图像中的目标检测
下面让我们开始吧,依然从导入模块开始:
from models import *
from utils import *
import os, sys, time, datetime, random
import torch
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torch.autograd import Variable
import matplotlib.pyplot as plt
import matplotlib.patches as patches
from PIL import Image
然后加载预训练的配置和权重,以及一些预定义的值,包括:图像的尺寸、置信度阈值和非最大抑制阈值。
config_path='config/yolov3.cfg'
weights_path='config/yolov3.weights'
class_path='config/coco.names'
img_size=416
conf_thres=0.8
nms_thres=0.4
# Load model and weights
model = Darknet(config_path, img_size=img_size)
model.load_weights(weights_path)
model.cuda()
model.eval()
classes = utils.load_classes(class_path)
Tensor = torch.cuda.FloatTensor
下面的函数将返回对指定图像的检测结果。
def detect_image(img):
# scale and pad image
ratio = min(img_size/img.size[0], img_size/img.size[1])
imw = round(img.size[0] * ratio)
imh = round(img.size[1] * ratio)
img_transforms=transforms.Compose([transforms.Resize((imh,imw)),
transforms.Pad((max(int((imh-imw)/2),0),
max(int((imw-imh)/2),0), max(int((imh-imw)/2),0),
max(int((imw-imh)/2),0)), (128,128,128)),
transforms.ToTensor(),
])
# convert image to Tensor
image_tensor = img_transforms(img).float()
image_tensor = image_tensor.unsqueeze_(0)
input_img = Variable(image_tensor.type(Tensor))
# run inference on the model and get detections
with torch.no_grad():
detections = model(input_img)
detections = utils.non_max_suppression(detections, 80,
conf_thres, nms_thres)
return detections[0]
最后,让我们通过加载一个图像,获取检测结果,然后用检测到的对象周围的包围框来显示它。并为不同的类使用不同的颜色来区分。
# load image and get detections
img_path = "images/blueangels.jpg"
prev_time = time.time()
img = Image.open(img_path)
detections = detect_image(img)
inference_time = datetime.timedelta(seconds=time.time() - prev_time)
print ('Inference Time: %s' % (inference_time))
# Get bounding-box colors
cmap = plt.get_cmap('tab20b')
colors = [cmap(i) for i in np.linspace(0, 1, 20)]
img = np.array(img)
plt.figure()
fig, ax = plt.subplots(1, figsize=(12,9))
ax.imshow(img)
pad_x = max(img.shape[0] - img.shape[1], 0) * (img_size / max(img.shape))
pad_y = max(img.shape[1] - img.shape[0], 0) * (img_size / max(img.shape))
unpad_h = img_size - pad_y
unpad_w = img_size - pad_x
if detections is not None:
unique_labels = detections[:, -1].cpu().unique()
n_cls_preds = len(unique_labels)
bbox_colors = random.sample(colors, n_cls_preds)
# browse detections and draw bounding boxes
for x1, y1, x2, y2, conf, cls_conf, cls_pred in detections:
box_h = ((y2 - y1) / unpad_h) * img.shape[0]
box_w = ((x2 - x1) / unpad_w) * img.shape[1]
y1 = ((y1 - pad_y // 2) / unpad_h) * img.shape[0]
x1 = ((x1 - pad_x // 2) / unpad_w) * img.shape[1]
color = bbox_colors[int(np.where(
unique_labels == int(cls_pred))[0])]
bbox = patches.Rectangle((x1, y1), box_w, box_h,
linewidth=2, edgecolor=color, facecolor='none')
ax.add_patch(bbox)
plt.text(x1, y1, s=classes[int(cls_pred)],
color='white', verticalalignment='top',
bbox={'color': color, 'pad': 0})
plt.axis('off')
# save image
plt.savefig(img_path.replace(".jpg", "-det.jpg"),
bbox_inches='tight', pad_inches=0.0)
plt.show()
下面是我们的一些检测结果:
视频中的目标跟踪
现在你知道了如何在图像中检测不同的物体。当你在一个视频中一帧一帧地看时,你会看到那些跟踪框在移动。但是如果这些视频帧中有多个对象,你如何知道一个帧中的对象是否与前一个帧中的对象相同?这被称为目标跟踪,它使用多次检测来识别一个特定的对象。
现在开始编写代码,前3个代码段将与单幅图像检测中的代码段相同,因为它们处理的是在单帧上获得 YOLO 检测。差异在最后一部分出现,对于每个检测,我们调用 Sort 对象的 Update 函数,以获得对图像中对象的引用。因此,与前面示例中的常规检测(包括边界框的坐标和类预测)不同,我们将获得跟踪的对象,除了上面的参数,还包括一个对象 ID。并且需要使用OpenCV来读取视频并显示视频帧。
videopath = 'video/interp.mp4'
%pylab inline
import cv2
from IPython.display import clear_output
cmap = plt.get_cmap('tab20b')
colors = [cmap(i)[:3] for i in np.linspace(0, 1, 20)]
# initialize Sort object and video capture
from sort import *
vid = cv2.VideoCapture(videopath)
mot_tracker = Sort()
#while(True):
for ii in range(40):
ret, frame = vid.read()
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
pilimg = Image.fromarray(frame)
detections = detect_image(pilimg)
img = np.array(pilimg)
pad_x = max(img.shape[0] - img.shape[1], 0) *
(img_size / max(img.shape))
pad_y = max(img.shape[1] - img.shape[0], 0) *
(img_size / max(img.shape))
unpad_h = img_size - pad_y
unpad_w = img_size - pad_x
if detections is not None:
tracked_objects = mot_tracker.update(detections.cpu())
unique_labels = detections[:, -1].cpu().unique()
n_cls_preds = len(unique_labels)
for x1, y1, x2, y2, obj_id, cls_pred in tracked_objects:
box_h = int(((y2 - y1) / unpad_h) * img.shape[0])
box_w = int(((x2 - x1) / unpad_w) * img.shape[1])
y1 = int(((y1 - pad_y // 2) / unpad_h) * img.shape[0])
x1 = int(((x1 - pad_x // 2) / unpad_w) * img.shape[1])
color = colors[int(obj_id) % len(colors)]
color = [i * 255 for i in color]
cls = classes[int(cls_pred)]
cv2.rectangle(frame, (x1, y1), (x1 box_w, y1 box_h),
color, 4)
cv2.rectangle(frame, (x1, y1-35), (x1 len(cls)*19 60,
y1), color, -1)
cv2.putText(frame, cls "-" str(int(obj_id)),
(x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX,
1, (255,255,255), 3)
fig=figure(figsize=(12, 8))
title("Video Stream")
imshow(frame)
show()
clear_output(wait=True)
这篇好文章是转载于:学新通技术网
- 版权申明: 本站部分内容来自互联网,仅供学习及演示用,请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系,请提供相关证据及您的身份证明,我们将在收到邮件后48小时内删除。
- 本站站名: 学新通技术网
- 本文地址: /boutique/detail/tangbieih
系列文章
更多
同类精品
更多
-
photoshop保存的图片太大微信发不了怎么办
PHP中文网 06-15 -
Android 11 保存文件到外部存储,并分享文件
Luke 10-12 -
word里面弄一个表格后上面的标题会跑到下面怎么办
PHP中文网 06-20 -
《学习通》视频自动暂停处理方法
HelloWorld317 07-05 -
微信公众号没有声音提示怎么办
PHP中文网 03-31 -
photoshop扩展功能面板显示灰色怎么办
PHP中文网 06-14 -
excel下划线不显示怎么办
PHP中文网 06-23 -
怎样阻止微信小程序自动打开
PHP中文网 06-13 -
excel打印预览压线压字怎么办
PHP中文网 06-22 -
photoshop蒙版画笔没反应怎么办
PHP中文网 06-24