[Code] - yolo detection

YOLO CODE

import cv2 as cv
import argparse
import numpy as np
import os.path
from matplotlib import pyplot as plt
%matplotlib inline

# Initialize the parameters
confThreshold = 0.5  #Confidence threshold
nmsThreshold = 0.4   #Non-maximum suppression threshold
inpWidth = 416       #Width of network's input image
inpHeight = 416      #Height of network's input image

# Load names of classes
classesFile = "coco.names"
classes = None
with open(classesFile, 'rt') as f:
    classes = f.read().rstrip('\n').split('\n')

coco.names에는 80개의 클래스 이름이 있다.

# Give the configuration and weight files for the model and load the network using them.
modelConfiguration = "yolov3.cfg"
modelWeights = "yolov3.weights" # 이미 학습 되어 있는 가중치 파일

yolov3.weights file : https://pjreddie.com/media/files/yolov3.weights

yolov3.cfg file : https://github.com/pjreddie/darknet/tree/master/cfg

net = cv.dnn.readNetFromDarknet(modelConfiguration, modelWeights)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)

darknet은 C언어로 이루어진 오픈 소스 Neural networks 이다. python에서 darknet을 사용하기 위한 코드이다.

# Get the names of the output layers
def getOutputsNames(net):
    # Get the names of all the layers in the network
    layersNames = net.getLayerNames()
    # Get the names of the output layers, i.e. the layers with unconnected outputs
    return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]

# Draw the predicted bounding box
def drawPred(classId, conf, left, top, right, bottom):
    # Draw a bounding box.
    cv.rectangle(frame, (left, top), (right, bottom), (255, 178, 50), 3)

    label = '%.2f' % conf

    # Get the label for the class name and its confidence
    if classes:
        assert(classId < len(classes))
        label = '%s:%s' % (classes[classId], label)

    #Display the label at the top of the bounding box
    labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)
    top = max(top, labelSize[1])
    cv.rectangle(frame, (left, top - round(1.5*labelSize[1])), (left + round(1.5*labelSize[0]), top + baseLine), (255, 255, 255), cv.FILLED)
    cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0,0,0), 1)

# Remove the bounding boxes with low confidence using non-maxima suppression
def postprocess(frame, outs):
    frameHeight = frame.shape[0]
    frameWidth = frame.shape[1]

    # Scan through all the bounding boxes output from the network and keep only the
    # ones with high confidence scores. Assign the box's class label as the class with the highest score.
    classIds = []
    confidences = []
    boxes = []
    for out in outs:
        for detection in out:
            scores = detection[5:]
            classId = np.argmax(scores)
            confidence = scores[classId]
            if confidence > confThreshold:
                center_x = int(detection[0] * frameWidth)
                center_y = int(detection[1] * frameHeight)
                width = int(detection[2] * frameWidth)
                height = int(detection[3] * frameHeight)
                left = int(center_x - width / 2)
                top = int(center_y - height / 2)
                classIds.append(classId)
                confidences.append(float(confidence))
                boxes.append([left, top, width, height])

    # Perform non maximum suppression to eliminate redundant overlapping boxes with
    # lower confidences.
    indices = cv.dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold)
    for i in indices:
        i = i[0]
        box = boxes[i]
        left = box[0]
        top = box[1]
        width = box[2]
        height = box[3]
        drawPred(classIds[i], confidences[i], left, top, left + width, top + height)

out= cv.VideoCapture('out.jpg')

hasFrame, frame = out.read()

# 여기서 inpWidth는 영상의 크기가 아님.
blob = cv.dnn.blobFromImage(frame, 1/255, (inpWidth, inpHeight), [0,0,0], 1, crop=False)

net.setInput(blob)

outs = net.forward(getOutputsNames(net))