【python】三帧差法实现运动目标检测

25-03-07 07:41

3744

7946

blog.csdn.net

id="article_content" class="article_content clearfix" style="height: 2000px; overflow: hidden;"> id="content_views" class="htmledit_views">

三帧差法是一种常用的运动目标检测方法，它通过比较连续三帧图像之间的差异来检测运动物体。这种方法尤其适用于背景变化较小的场景。

目录

1 方案

具体步骤如下：

① 读取视频流：使用cv2.VideoCapture()读取视频文件。

② 灰度化：将彩色图像转换为灰度图，简化后续计算。

③ 帧间差分：计算连续三帧之间的差分，absdiff函数计算两个灰度图像的绝对差值。然后，将两帧差相加。

④ 阈值处理：使用threshold函数将差分图像转换为二值图像，突出运动区域。

⑤ 形态学操作：应用闭运算（morphologyEx）去除小的噪声点。

⑥ 显示结果：使用imshow显示检测到的运动区域和当前帧。

⑦ 更新帧：将当前帧更新为下一帧，以便在循环中持续检测运动目标。

⑧ 退出循环：按’q’键退出程序。

需要注意的是，三帧差法仅适用于背景相对静止的场景。如果背景的变化较大，则需要更复杂的方法（背景减除或自适应阈值技术）。

2 实践

① 代码

 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="1">

class="hljs-ln-code"> class="hljs-ln-line">import cv2

class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="2">

 class="hljs-ln-code"> class="hljs-ln-line">import numpy as np class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="3"> class="hljs-ln-code"> class="hljs-ln-line"> 
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="4"> class="hljs-ln-code"> class="hljs-ln-line"> 
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="5"> class="hljs-ln-code"> class="hljs-ln-line">def OD(video_path):
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="6"> class="hljs-ln-code"> class="hljs-ln-line">    # 初始化摄像头
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="7"> class="hljs-ln-code"> class="hljs-ln-line">    cap = cv2.VideoCapture(video_path)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="8"> class="hljs-ln-code"> class="hljs-ln-line">    # 读取第一帧作为初始帧
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="9"> class="hljs-ln-code"> class="hljs-ln-line">    ret, frame1 = cap.read()
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="10"> class="hljs-ln-code"> class="hljs-ln-line">    frame1_gray = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="11"> class="hljs-ln-code"> class="hljs-ln-line">    # 读取第二帧
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="12"> class="hljs-ln-code"> class="hljs-ln-line">    ret, frame2 = cap.read()
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="13"> class="hljs-ln-code"> class="hljs-ln-line">    frame2_gray = cv2.cvtColor(frame2, cv2.COLOR_BGR2GRAY)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="14"> class="hljs-ln-code"> class="hljs-ln-line">    while True:
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="15"> class="hljs-ln-code"> class="hljs-ln-line">        # 读取第三帧
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="16"> class="hljs-ln-code"> class="hljs-ln-line">        ret, frame3 = cap.read()
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="17"> class="hljs-ln-code"> class="hljs-ln-line">        if not ret:
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="18"> class="hljs-ln-code"> class="hljs-ln-line">            break
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="19"> class="hljs-ln-code"> class="hljs-ln-line">        frame3_gray = cv2.cvtColor(frame3, cv2.COLOR_BGR2GRAY)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="20"> class="hljs-ln-code"> class="hljs-ln-line">        # 计算帧间差
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="21"> class="hljs-ln-code"> class="hljs-ln-line">        diff1 = cv2.absdiff(frame1_gray, frame2_gray)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="22"> class="hljs-ln-code"> class="hljs-ln-line">        diff2 = cv2.absdiff(frame2_gray, frame3_gray)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="23"> class="hljs-ln-code"> class="hljs-ln-line">        # 将两帧差相加
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="24"> class="hljs-ln-code"> class="hljs-ln-line">        diff = cv2.add(diff1, diff2)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="25"> class="hljs-ln-code"> class="hljs-ln-line">        # 应用阈值来提取运动区域
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="26"> class="hljs-ln-code"> class="hljs-ln-line">        _, thresh = cv2.threshold(diff, 30, 255, cv2.THRESH_BINARY)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="27"> class="hljs-ln-code"> class="hljs-ln-line">        # 使用形态学操作去除噪声
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="28"> class="hljs-ln-code"> class="hljs-ln-line">        kernel = np.ones((5, 5), np.uint8)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="29"> class="hljs-ln-code"> class="hljs-ln-line">        closing = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="30"> class="hljs-ln-code"> class="hljs-ln-line">        # 显示结果
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="31"> class="hljs-ln-code"> class="hljs-ln-line">        cv2.imshow("video", frame3)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="32"> class="hljs-ln-code"> class="hljs-ln-line">        cv2.imshow('Motion Detection', closing)
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="33"> class="hljs-ln-code"> class="hljs-ln-line">        # 更新帧
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="34"> class="hljs-ln-code"> class="hljs-ln-line">        frame1_gray = frame2_gray
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="35"> class="hljs-ln-code"> class="hljs-ln-line">        frame2_gray = frame3_gray
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="36"> class="hljs-ln-code"> class="hljs-ln-line">        # 按'q'退出循环
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="37"> class="hljs-ln-code"> class="hljs-ln-line">        if cv2.waitKey(1) & 0xFF == ord('q'):
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="38"> class="hljs-ln-code"> class="hljs-ln-line">            break
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="39"> class="hljs-ln-code"> class="hljs-ln-line">    # 释放资源
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="40"> class="hljs-ln-code"> class="hljs-ln-line">    cap.release()
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="41"> class="hljs-ln-code"> class="hljs-ln-line">    cv2.destroyAllWindows()
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="42"> class="hljs-ln-code"> class="hljs-ln-line"> 
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="43"> class="hljs-ln-code"> class="hljs-ln-line"> 
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="44"> class="hljs-ln-code"> class="hljs-ln-line">if __name__ == '__main__':
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="45"> class="hljs-ln-code"> class="hljs-ln-line">    OD("test.mp4")
 class="hljs-ln-numbers"> class="hljs-ln-line hljs-ln-n" data-line-number="46"> class="hljs-ln-code"> class="hljs-ln-line">    pass

class="hljs-button signin active" data-title="登录复制" data-report-click="{"spm":"1001.2101.3001.4334"}" onclick="hljs.signin(event)">

② 效果图

至此，本文分享的内容就结束啦。

id="blogExtensionBox" style="width:400px;margin:auto;margin-top:12px" class="blog-extension-box"> class="blog_extension blog_extension_type2" id="blog_extension"> class="extension_official" data-report-click="{"spm":"1001.2101.3001.6471"}"> class="blog_extension_card_left">

class="blog_extension_card_cont"> 商务合作 | 备注具体的来意 class="blog_extension_card_cont_r">

微信名片

注：本文转载自blog.csdn.net的Jackilina_Stone的文章"https://blog.csdn.net/wss794/article/details/145342966"。版权归原作者所有，此博客不拥有其著作权，亦不承担相应法律责任。如有侵权，请联系我们删除。

复制链接

发表评论

注册

评论记录：

未查询到任何数据！