opencv信号放大

最新推荐文章于 2025-07-01 09:43:33 发布

原创最新推荐文章于 2025-07-01 09:43:33 发布 · 108 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#opencv #计算机视觉 #python

计算机视觉专栏收录该内容

107 篇文章

订阅专栏

该代码实现了一个视频处理流程，包括构建高斯金字塔、应用时域理想带通滤波器、放大视频、以及从原始视频和高斯金字塔重建视频，最终保存处理后的视频。主要针对特定频率范围的颜色进行增强。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import cv2
import numpy as np
import scipy.fftpack as fftpack


# Build Gaussian Pyramid
def build_gaussian_pyramid(src, level=3):
    s = src.copy()
    pyramid = [s]
    for i in range(level):
        s = cv2.pyrDown(s)
        pyramid.append(s)
    return pyramid


# load video from file
def load_video(video_filename):
    cap = cv2.VideoCapture(video_filename)
    frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
    width, height = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)), int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    fps = int(cap.get(cv2.CAP_PROP_FPS))
    video_tensor = np.zeros((frame_count, height, width, 3), dtype='float')
    x = 0
    while cap.isOpened():
        ret, frame = cap.read()
        if ret is True:
            video_tensor[x] = frame
            x += 1
        else:
            break
    return video_tensor, fps


# apply temporal ideal bandpass filter to gaussian video
def temporal_ideal_filter(tensor, low, high, fps, axis=0):
    fft = fftpack.fft(tensor, axis=axis)
    frequencies = fftpack.fftfreq(tensor.shape[0], d=1.0 / fps)
    bound_low = (np.abs(frequencies - low)).argmin()
    bound_high = (np.abs(frequencies - high)).argmin()
    fft[:bound_low] = 0
    fft[bound_high:-bound_high] = 0
    fft[-bound_low:] = 0
    iff = fftpack.ifft(fft, axis=axis)
    return np.abs(iff)


# build gaussian pyramid for video
def gaussian_video(video_tensor, levels=3):
    for i in range(0, video_tensor.shape[0]):
        frame = video_tensor[i]
        pyr = build_gaussian_pyramid(frame, level=levels)
        gaussian_frame = pyr[-1]
        if i == 0:
            vid_data = np.zeros((video_tensor.shape[0], gaussian_frame.shape[0], gaussian_frame.shape[1], 3))
        vid_data[i] = gaussian_frame
    return vid_data


# amplify the video
def amplify_video(gaussian_vid, amplification=50):
    return gaussian_vid * amplification


# reconstract video from original video and gaussian video
def reconstract_video(amp_video, origin_video, levels=3):
    final_video = np.zeros(origin_video.shape)
    for i in range(0, amp_video.shape[0]):
        img = amp_video[i]
        for x in range(levels):
            img = cv2.pyrUp(img)
        img = img + origin_video[i]
        final_video[i] = img
    return final_video


# save video to files
def save_video(video_tensor):
    fourcc = cv2.VideoWriter_fourcc('M', 'J', 'P', 'G')
    [height, width] = video_tensor[0].shape[0:2]
    writer = cv2.VideoWriter("out.avi", fourcc, 30, (width, height), 1)
    for i in range(0, video_tensor.shape[0]):
        writer.write(cv2.convertScaleAbs(video_tensor[i]))
    writer.release()


# magnify color
def magnify_color(video_name, low, high, levels=3, amplification=20):
    t, f = load_video(video_name)
    gau_video = gaussian_video(t, levels=levels)
    filtered_tensor = temporal_ideal_filter(gau_video, low, high, f)
    amplified_video = amplify_video(filtered_tensor, amplification=amplification)
    final = reconstract_video(amplified_video, t, levels=3)
    save_video(final)


if __name__ == "__main__":
    magnify_color("baby.mp4", 0.4, 3)