OpenCV KAKUUCHI

猫認識

Gallery

src_1

dst_1

src_2

dst_2

what process?

opencvのライブラリで最初に試したいのは人の顔認識で、qiitaやブログで記載するひとが多いです。ですが、haarcascadesフォルダ内には[ネコの顔を認識する分類器](https://github.com/opencv/opencv/blob/master/data/haarcascades/haarcascade_frontalcatface_extended.xml)も存在します。

[ねこと画像処理 part 2 – 猫検出 (モデル配布)](https://rest-term.com/archives/3131/)では最初から猫の顔が写っている画像にアノテーションをかけ、機械学習にて分類器を生成しています。

cook code C++

#include <iostream>
#include <opencv2/core.hpp>
#include <opencv2/core/utility.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/videoio.hpp>
#include <opencv2/objdetect.hpp>

int main(int argc, const char* argv[])
{
    // ./out -src=[image path] -cascade=haarcascade_frontalcatface_extended.xml
    cv::String keys = "{src||}""{cascade||}";
    cv::CommandLineParser parser(argc, argv, keys);
    cv::String src_path = parser.get<cv::String>("src");
    cv::String cascade_path = parser.get<cv::String>("cascade");

cv::VideoCapture capture(src_path);
    if (!capture.isOpened()){
        //error in opening the video input
        std::cerr << "Unable to open file!" << std::endl;
        return 0;
    }

/* 初期設定 */
    int cap_width = int(capture.get(cv::CAP_PROP_FRAME_WIDTH));
    int cap_height = int(capture.get(cv::CAP_PROP_FRAME_HEIGHT));
    int fps = int(capture.get(cv::CAP_PROP_FPS));
    int fourcc = cv::VideoWriter::fourcc('m','p','4','v');
    cv::Size video_size = cv::Size(cap_width,cap_height);

cv::VideoWriter writer("output.mp4", fourcc, fps, video_size);

cv::CascadeClassifier cascade;
    if(!cascade.load(cascade_path))
        return -1;

while(true){
        cv::Mat frame;
        capture >> frame;

if (frame.empty())
            break;

std::vector<cv::Rect> objects;
        cascade.detectMultiScale(frame, objects);

for (int i = 0; i < objects.size(); ++i) {
            cv::rectangle(frame, objects[i], cv::Scalar( 0, 255, 0 ), 2);
        }

writer << frame;
        frame.release();

}

capture.release();
    writer.release();

return 0;
}

cook code Python

import numpy as np
import cv2
import argparse

def main():

# python main.py --src [movie path] --cascade [cascade path]
    parser = argparse.ArgumentParser()
    parser.add_argument('--src')
    parser.add_argument('--cascade')
    args = parser.parse_args()

cap = cv2.VideoCapture(args.src)

cap_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    cap_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    fps = cap.get(cv2.CAP_PROP_FPS)

fmt = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
    writer = cv2.VideoWriter('output.mp4', fmt, fps, (cap_width,cap_height))

cascade = cv2.CascadeClassifier(args.cascade)

while cap.isOpened():
        _ret, frame = cap.read()
        
        if frame is None:
            break
        
        objects = cascade.detectMultiScale(frame)
        if 0 < len(objects):
            for (x,y,w,h) in objects:
                cv2.rectangle(frame,(x,y),(x+w, y+h),(0,255,0),2)

writer.write(frame)

cap.release()
    writer.release()

if __name__ == '__main__':
    main()

Reference

戻る(Back Page)