OpenCV 打开双目摄像头（python版）

古城微笑少年丶 2023-01-10 13:25 339阅读 0赞

## 前言 ##

本文主要介绍在OpenCV用使用双目摄像头，包括：打开单目摄像头、设置摄像头参数、拍照、录制视频。

**环境**：编程语言：Python3        主要依赖库：OpenCV3.x 或 OpenCV4.x

## 双目摄像头 ##

双目同步摄像头，两个镜头共用一个设备ID，左右摄像机同一频率。这款摄像头分辨率支持2560\*960或以上。

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMjA0NDY0_size_16_color_FFFFFF_t_70][]

## 思路流程 ##

1、由于两个镜头共用一个设备ID，打开摄像头时使用cv2.VideoCapture()函数，只需打开一次。区别有的双目摄像头是左右镜头各用一个设备ID，需要打开两次cv2.VideoCapture(0)，cv2.VideoCapture(1)。

2、双目摄像头的总分辨率是由左右镜头组成的，比如：左右摄像机总分辨率1280x480；分割为左相机640x480、右相机640x480

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMjA0NDY0_size_16_color_FFFFFF_t_70 1][]

为了方便理解画了张草图；图中的“原点”是图像像素坐标系的原点。

3、分割后，左相机的分辨率：高度 0:480、宽度 0:640

右相机的分辨率：高度 0:480、宽度 640:1280

4、转换为代码后

# 读取摄像头数据
        ret, frame = camera.read()
        #裁剪坐标为[y0:y1, x0:x1]  HEIGHT * WIDTH
        left_frame = frame[0:480, 0:640]
        right_frame = frame[0:480, 640:1280]
     
        cv2.imshow("left", left_frame)
        cv2.imshow("right", right_frame)

## 1）分辨率1280x480 ##

源代码：

# -*- coding: utf-8 -*-
    import cv2
    import time
    
     
    AUTO = False  # 自动拍照，或手动按s键拍照
    INTERVAL = 2 # 自动拍照间隔
     
    cv2.namedWindow("left")
    cv2.namedWindow("right")
    camera = cv2.VideoCapture(0)
    
    # 设置分辨率 左右摄像机同一频率，同一设备ID；左右摄像机总分辨率1280x480；分割为两个640x480、640x480
    camera.set(cv2.CAP_PROP_FRAME_WIDTH,1280)
    camera.set(cv2.CAP_PROP_FRAME_HEIGHT,480)
     
    counter = 0
    utc = time.time()
    folder = "./SaveImage/" # 拍照文件目录
     
    def shot(pos, frame):
        global counter
        path = folder + pos + "_" + str(counter) + ".jpg"
     
        cv2.imwrite(path, frame)
        print("snapshot saved into: " + path)
     
    while True:
        ret, frame = camera.read()
        # 裁剪坐标为[y0:y1, x0:x1] HEIGHT*WIDTH
        left_frame = frame[0:480, 0:640]
        right_frame = frame[0:480, 640:1280]
     
        cv2.imshow("left", left_frame)
        cv2.imshow("right", right_frame)
     
        now = time.time()
        if AUTO and now - utc >= INTERVAL:
            shot("left", left_frame)
            shot("right", right_frame)
            counter += 1
            utc = now
     
        key = cv2.waitKey(1)
        if key == ord("q"):
            break
        elif key == ord("s"):
            shot("left", left_frame)
            shot("right", right_frame)
            counter += 1
    camera.release()
    cv2.destroyWindow("left")
    cv2.destroyWindow("right")

补充理解

> OpenCV有VideoCapture()函数，能用来定义“摄像头”对象，0表示第一个摄像头（一般是电脑内置的摄像头）；如果有两个摄像头，第二个摄像头则对应VideoCapture(1)。
> 
> 在while循环中使用“摄像头对象”的read()函数一帧一帧地读取摄像头画面数据。
> 
> imshow函数是显示摄像头的某帧画面；cv2.waitKey(1)是等待1ms，如果期间检测到了键盘输入q，则退出while循环。

效果

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMjA0NDY0_size_16_color_FFFFFF_t_70 2][]

## 2）分辨率2560x720 ##

源代码：

# -*- coding: utf-8 -*-
    import cv2
    import time
    
     
    AUTO = False  # 自动拍照，或手动按s键拍照
    INTERVAL = 2 # 自动拍照间隔
     
    cv2.namedWindow("left")
    cv2.namedWindow("right")
    camera = cv2.VideoCapture(0)
    
    # 设置分辨率左右摄像机同一频率，同一设备ID；左右摄像机总分辨率2560x720；分割为两个1280x720
    camera.set(cv2.CAP_PROP_FRAME_WIDTH,2560)
    camera.set(cv2.CAP_PROP_FRAME_HEIGHT,720)
     
    counter = 0
    utc = time.time()
    folder = "./SaveImage/" # 拍照文件目录
     
    def shot(pos, frame):
        global counter
        path = folder + pos + "_" + str(counter) + ".jpg"
     
        cv2.imwrite(path, frame)
        print("snapshot saved into: " + path)
     
    while True:
        ret, frame = camera.read()
        print("ret:",ret)
        # 裁剪坐标为[y0:y1, x0:x1]    HEIGHT * WIDTH
        left_frame = frame[0:720, 0:1280]
        right_frame = frame[0:720, 1280:2560]
     
        cv2.imshow("left", left_frame)
        cv2.imshow("right", right_frame)
     
        now = time.time()
        if AUTO and now - utc >= INTERVAL:
            shot("left", left_frame)
            shot("right", right_frame)
            counter += 1
            utc = now
     
        key = cv2.waitKey(1)
        if key == ord("q"):
            break
        elif key == ord("s"):
            shot("left", left_frame)
            shot("right", right_frame)
            counter += 1
    camera.release()
    cv2.destroyWindow("left")
    cv2.destroyWindow("right")

其他版本：[OpenCV 双目摄像头拍照 C++][OpenCV _ C]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMjA0NDY0_size_16_color_FFFFFF_t_70]: /images/20221119/aa1d42bc1c824a37ada826473474ec12.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMjA0NDY0_size_16_color_FFFFFF_t_70 1]: /images/20221119/0427320d83d646a4ab2d48f1484b294a.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMjA0NDY0_size_16_color_FFFFFF_t_70 2]: /images/20221119/b603977502c84c19b1d8fa9171bbf79b.png
[OpenCV _ C]: https://blog.csdn.net/qq_41204464/article/details/86518807?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522161147097116780255261030%2522%252C%2522scm%2522%253A%252220140713.130102334.pc%255Fblog.%2522%257D&request_id=161147097116780255261030&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~blog~first_rank_v2~rank_v29-3-86518807.pc_v2_rank_blog_default&utm_term=%E5%8F%8C%E7%9B%AE&spm=1018.2226.3001.4450