darknet yolo4:

darknet yolo4:

# -*- coding: utf-8 -*-
"""
Created on Sat Mar 13 10:24:50 2021
@author: S
"""

import numpy as np
import cv2
import os
import time


def video_demo():
    # 加载已经训练好的模型路径，可以是绝对路径或者相对路径
    weightsPath = "./backup/yolo-obj_fre_final.weights"
    configPath = "./backup/yolo-obj_fre.cfg"
    labelsPath = "./backup/fre.names"
    # 初始化一些参数
    LABELS = open(labelsPath).read().strip().split("\n")  # 物体类别
    COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8")  # 颜色
    boxes = []
    confidences = []
    classIDs = []
    central_points = []
    counts = 0
    net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)
    net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
    net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)  ####GPU
    # 读入待检测的图像
    # 0是代表摄像头编号，只有一个的话默认为0
    capture = cv2.VideoCapture("./E20.mp4")
    while (True):
        start_drawing = time.time()
        fps = int(capture.get(cv2.CAP_PROP_FPS))
        ref, image = capture.read()
        (H, W) = image.shape[:2]
        # 得到 YOLO需要的输出层
        ln = net.getLayerNames()
        ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]
        # 从输入图像构造一个blob，然后通过加载的模型，给我们提供边界框和相关概率
        blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416), swapRB=True, crop=False)
        net.setInput(blob)
        layerOutputs = net.forward(ln)
        # 在每层输出上循环
        for output in layerOutputs:
            # 对每个检测进行循环
            for detection in output:
                scores = detection[5:]
                classID = np.argmax(scores)
                confidence = scores[classID]
                # 过滤掉那些置信度较小的检测结果
                if confidence > 0.5:
                    # 框后接框的宽度和高度
                    box = detection[0:4] * np.array([W, H, W, H])
                    (centerX, centerY, width, height) = box.astype("int")
                    # 边框的左上角
                    x = int(centerX - (width / 2))
                    y = int(centerY - (height / 2))
                    # 更新检测出来的框
                    boxes.append([x, y, int(width), int(height)])
                    confidences.append(float(confidence))
                    classIDs.append(classID)
        # 极大值抑制
        idxs = cv2.dnn.NMSBoxes(boxes, confidences, 0.3, 0.3)


        if len(idxs) > 0:
            for i in idxs.flatten():  # indxs是二维的，第0维是输出层，所以这里把它展平成1维

                counts=counts +1
                (x, y) = (boxes[i][0], boxes[i][1])
                (w, h) = (boxes[i][2], boxes[i][3])
                (x_center,y_center) = ( int(x+w/2), int(y + h/2))
                central_points.append([x_center,y_center])
               # print(i)
               # print(x_center)
                # 在原图上绘制边框和类别
                color = [int(c) for c in COLORS[classIDs[i]]]
                cv2.rectangle(image, (x, y), (x + w, y + h), color, 2)
                cv2.circle(image,(x_center, y_center),10,(0,0,255),2)  #画圆

                text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
                cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)

        counts=len(idxs)
        end_drawing = time.time()
        fps_label = "FPS: %.2d" % fps
        cv2.putText(image,fps_label , (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.5, (0, 0, 255), 2)

        cv2.imshow("Image", image)

        # 等待30ms显示图像，若过程中按“ESC”退出


        c = cv2.waitKey(1) & 0xff
        if c == 27:
            capture.release()
            break

        boxes = []
        confidences = []
        classIDs =[]


video_demo()