yolov5+deepsort实现实时键盘自动切换单目标跟踪
Posted 成都_小吴
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了yolov5+deepsort实现实时键盘自动切换单目标跟踪相关的知识，希望对你有一定的参考价值。
距离上一次博客好像有一段时间了，一直在搞瑞芯微、海思之类的东西也没搞不明白，最近我的好同学有一个需求或者项目上有一些需求，如何实现单目标跟踪用键盘自动切换目标进行跟踪，我只能从python的yolov5+deepsort进行入手，我的好同学的话是用在jeston NX英伟达的板子上使用tensortRT进行实现，这里我只能实现python的版本，实现键盘输入目标ID进行跟踪：大家可以看下面的效果：
目标跟踪
首先代码中要使用键盘响应事件，这个键盘响应事件查阅资料必须与GUI-opencv结合使用才可以，所以要在显示图片的地方进行键盘响应事件，如下：
cv2.imshow(p, im0)
key = cv2.waitKey(1)
if(key == 49):
a.append(key-48)
if(key == 50):
a.append(key-48)
if(key == 51):
a.append(key-48)
if(key == 52):
a.append(key-48)
if(key == 53):
a.append(key-48)
if (key == 54):
a.append(key - 48)
if (key == 55):
a.append(key - 48)
if (key == 56):
a.append(key - 48)
if (key == 57):
a.append(key - 48)大家可以看到这里是有一个元组a,为什么要设置这个元组呢，因为检测图片是在不断地刷新KEY的值，这样通过key按键进行目标切换每次循环都会重置，所以需要将你的切换目标的ID存放在一个全局变量a = []中，下面就是切换ID的函数，如果我输入键盘1，则KEY==49，a里面就成了a[1];如果跟踪第一个目标则a的长度为1，要跟踪的ID号就是a[0]，只将ID号为1的目标进行输出，或者将这个目标的坐标传递出来给转台进行转动，如果想要切换跟踪自己的目标键盘输入;2,则这时key==50,a[1,2];a[1] == 2;所以这是len(a)==2,选择跟踪第二个目标，对第二个目标的信息进行输出。
def draw_boxes(img, bbox, identities=None, offset=(0, 0)):
for i, box in enumerate(bbox):
x1, y1, x2, y2 = [int(i) for i in box]
x1 += offset[0]
x2 += offset[0]
y1 += offset[1]
y2 += offset[1]
# box text and bar
id = int(identities[i]) if identities is not None else 0
if(len(a) == 1):
if (id == a[0]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 3):
if(id == a[2]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 4):
if(id == a[3]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 5):
if(id == a[4]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 6):
if(id == a[5]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 7):
if(id == a[6]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 8):
if(id == a[7]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 9):
if(id == a[8]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) > 9):
if(id == a[len(a) - 1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
else:
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 2, [255, 此代码只针对少目标的单目标跟踪比如飞机、坦克、船之类的，所以我们还需要改动的地方就是ID号的限制，我们将ID号限制在9以内如下：在deepsort的tracker里面进行ID的限制，大家也可以根据自己的需求进行设置：
def _initiate_track(self, detection):
mean, covariance = self.kf.initiate(detection.to_xyah())
self.tracks.append(Track(
mean, covariance, self._next_id, self.n_init, self.max_age,
detection.feature))
self._next_id += 1
if (self._next_id==10):
self._next_id = 1下面是完整的track.py代码大家可以自行修改。
import sys
sys.path.insert(0, './yolov5')
from yolov5.utils.google_utils import attempt_download
from yolov5.models.experimental import attempt_load
from yolov5.utils.datasets import LoadImages, LoadStreams
from yolov5.utils.general import check_img_size, non_max_suppression, scale_coords, \\
check_imshow
from yolov5.utils.torch_utils import select_device, time_synchronized
from deep_sort_pytorch.utils.parser import get_config
from deep_sort_pytorch.deep_sort import DeepSort
import argparse
import os
import platform
import shutil
import time
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
a = []
palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1)
def xyxy_to_xywh(*xyxy):
"""" Calculates the relative bounding box from absolute pixel values. """
bbox_left = min([xyxy[0].item(), xyxy[2].item()])
bbox_top = min([xyxy[1].item(), xyxy[3].item()])
bbox_w = abs(xyxy[0].item() - xyxy[2].item())
bbox_h = abs(xyxy[1].item() - xyxy[3].item())
x_c = (bbox_left + bbox_w / 2)
y_c = (bbox_top + bbox_h / 2)
w = bbox_w
h = bbox_h
return x_c, y_c, w, h
def xyxy_to_tlwh(bbox_xyxy):
tlwh_bboxs = []
for i, box in enumerate(bbox_xyxy):
x1, y1, x2, y2 = [int(i) for i in box]
top = x1
left = y1
w = int(x2 - x1)
h = int(y2 - y1)
tlwh_obj = [top, left, w, h]
tlwh_bboxs.append(tlwh_obj)
return tlwh_bboxs
def compute_color_for_labels(label):
"""
Simple function that adds fixed color depending on the class
"""
color = [int((p * (label ** 2 - label + 1)) % 255) for p in palette]
return tuple(color)
def draw_boxes(img, bbox, identities=None, offset=(0, 0)):
for i, box in enumerate(bbox):
x1, y1, x2, y2 = [int(i) for i in box]
x1 += offset[0]
x2 += offset[0]
y1 += offset[1]
y2 += offset[1]
# box text and bar
id = int(identities[i]) if identities is not None else 0
if(len(a) == 1):
if (id == a[0]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 2):
if(id == a[1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 3):
if(id == a[2]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 4):
if(id == a[3]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 5):
if(id == a[4]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 6):
if(id == a[5]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 7):
if(id == a[6]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 8):
if(id == a[7]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) == 9):
if(id == a[8]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
elif(len(a) > 9):
if(id == a[len(a) - 1]):
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 5, [255, 0, 0], 10)
else:
color = compute_color_for_labels(id)
label = ':d'.format("", id)
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
cv2.rectangle(
img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
cv2.putText(img, label, (x1, y1 +
t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 2, [255, 255, 255], 2)
return img
def detect(opt):
out, source, yolo_weights, deep_sort_weights, show_vid, save_vid, save_txt, imgsz, evaluate = \\
opt.output, opt.source, opt.yolo_weights, opt.deep_sort_weights, opt.show_vid, opt.save_vid, \\
opt.save_txt, opt.img_size, opt.evaluate
webcam = source == '0' or source.startswith(
'rtsp') or source.startswith('http') or source.endswith('.txt')
# initialize deepsort
cfg = get_config()
cfg.merge_from_file(opt.config_deepsort)
attempt_download(deep_sort_weights, repo='mikel-brostrom/Yolov5_DeepSort_Pytorch')
deepsort = DeepSort(cfg.DEEPSORT.REID_CKPT,
max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET,
use_cuda=True)
# Initialize
device = select_device(opt.device)
# The MOT16 evaluation runs multiple inference streams in parallel, each one writing to
# its own .txt file. Hence, in that case, the output folder is not restored
if not evaluate:
if os.path.exists(out):
pass
shutil.rmtree(out) # delete output folder
os.makedirs(out) # make new output folder
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = attempt_load(yolo_weights, map_location=device) # load FP32 model
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # check img_size
names = model.module.names if hasattr(model, 'module') else model.names # get class names
if half:
model.half() # to FP16
# Set Dataloader
vid_path, vid_writer = None, None
# Check if environment supports image displays
if show_vid:
show_vid = check_imshow()
if webcam:
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride)
else:
dataset = LoadImages(source, img_size=imgsz)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
save_path = str(Path(out))
# extract what is in between the last '/' and last '.'
txt_file_name = source.split('/')[-1].split('.')[0]
txt_path = str(Path(out)) + '/' + txt_file_name + '.txt'
for frame_idx, (path, img, im0s, vid_cap) in enumerate(dataset):
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
# Inference
t1 = time_synchronized()
pred = model(img, augment=opt.augment)[0]
# Apply NMS
pred = non_max_suppression(
pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
t2 = time_synchronized()
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
else:
p, s, im0 = path, '', im0s
s += '%gx%g ' % img.shape[2:] # print string
save_path = str(Path(out) / Path(p).name)
if det is not None and 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 += '%g %ss, ' % (n, names[int(c)]) # add to string
xywh_bboxs = []
confs = []
# Adapt detections to deep sort input format
for *xyxy, conf, cls in det:
# to deep sort format
x_c, y_c, bbox_w, bbox_h = xyxy_to_xywh(*xyxy)
xywh_obj = [x_c, y_c, bbox_w, bbox_h]
xywh_bboxs.append(xywh_obj)
confs.append([conf.item()])
xywhs = torch.Tensor(xywh_bboxs)
confss = torch.Tensor(confs)
# pass detections to deepsort
outputs = deepsort.update(xywhs, confss, im0)
# draw boxes for visualization
if len(outputs) > 0:
bbox_xyxy = outputs[:, :4]
identities = outputs[:, -1]
draw_boxes(im0, bbox_xyxy, identities)
# to MOT format
tlwh_bboxs = xyxy_to_tlwh(bbox_xyxy)
# Write MOT compliant results to file
# if save_txt:
# for j, (tlwh_bbox, output) in enumerate(zip(tlwh_bboxs, outputs)):
# bbox_top = tlwh_bbox[0]
# bbox_left = tlwh_bbox[1]
# bbox_w = tlwh_bbox[2]
# bbox_h = tlwh_bbox[3]
# identity = output[-1]
# with open(txt_path, 'a') as f:
# f.write(('%g ' * 10 + '\\n') % (frame_idx, identity, bbox_top,
# bbox_left, bbox_w, bbox_h, -1, -1, -1, -1)) # label format
else:
deepsort.increment_ages()
# Print time (inference + NMS)
# print('%sDone. (%.3fs)' % (s, t2 - t1))
# Stream results
if 1:
cv2.imshow(p, im0)
key = cv2.waitKey(1)
if(key == 49):
a.append(key-48)
if(key == 50):
a.append(key-48)
if(key == 51):
a.append(key-48)
if(key == 52):
a.append(key-48)
if(key == 53):
a.append(key-48)
if (key == 54):
a.append(key - 48)
if (key == 55):
a.append(key - 48)
if (key == 56):
a.append(key - 48)
if (key == 57):
a.append(key - 48)
# Save results (image with detections)
# if 1:
# if vid_path != save_path: # new video
# vid_path = save_path
# if isinstance(vid_writer, cv2.VideoWriter):
# vid_writer.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 = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
# vid_writer.write(im0)
# if save_txt or save_vid:
# print('Results saved to %s' % os.getcwd() + os.sep + out)
# if platform == 'darwin': # MacOS
# os.system('open ' + save_path)
# print('Done. (%.3fs)' % (time.time() - t0))
if __name__ == '__main__':
# a = cv2.imread('194.jpg')
parser = argparse.ArgumentParser()
parser.add_argument('--yolo_weights', type=str, default='yolov5/weights/yolov5s.pt', help='model.pt path')
parser.add_argument('--deep_sort_weights', type=str, default='deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7', help='ckpt.t7 path')
# file/folder, 0 for webcam
parser.add_argument('--source', type=str, default='./Demo.mp4', help='source')
parser.add_argument('--output', type=str, default='inference/output', help='output folder') # output folder
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.4, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.5, help='IOU threshold for NMS')
parser.add_argument('--fourcc', type=str, default='mp4v', help='output video codec (verify ffmpeg support)')
parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--show-vid', action='store_true', help='display tracking video results')
parser.add_argument('--save-vid', action='store_true', help='save video tracking results')
parser.add_argument('--save-txt', action='store_true', help='save MOT compliant results to *.txt')
# class 0 is person, 1 is bycicle, 2 is car... 79 is oven
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 16 17')
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('--evaluate', action='store_true', help='augmented inference')
parser.add_argument("--config_deepsort", type=str, default="deep_sort_pytorch/configs/deep_sort.yaml")
args = parser.parse_args()
args.img_size = check_img_size(args.img_size)
with torch.no_grad():
detect(args)
大家如果有兴趣的话可以进群交流：135163517
以上是关于yolov5+deepsort实现实时键盘自动切换单目标跟踪的主要内容，如果未能解决你的问题，请参考以下文章
视频实时行为检测——基于yolov5+deepsort+slowfast算法
基于Yolov5的目标追踪（非Yolov5+DeepSort版）
用C++部署yolov5+deepsort+tensorrt实现目标跟踪