（openCV 七）汽车检测

汽车图片下载地址，下载后解压，解压后的包名为CarData
https://l2r.cs.uiuc.edu/~cogcomp/Data/Car/CarData.tar.gz

import cv2
import numpy as np
from os.path import join
#此数据集为UIUC Car Detection 可网上下载
datapath = "CarData/TrainImages/"
def path(cls,i):
  return "%s/%s%d.pgm"  % (datapath,cls,i+1)

pos, neg = "pos-", "neg-"#数据集中图片命名方式

detect = cv2.xfeatures2d.SIFT_create()#提取关键点
extract = cv2.xfeatures2d.SIFT_create()#提取特征
#FLANN匹配器有两个参数：indexParams和searchParams,以字典的形式进行参数传参
flann_params = dict(algorithm = 1, trees = 5)#1为FLANN_INDEX_KDTREE
matcher = cv2.FlannBasedMatcher(flann_params, {})#匹配特征
#创建bow训练器，簇数为40
bow_kmeans_trainer = cv2.BOWKMeansTrainer(40)
#初始化bow提取器
extract_bow = cv2.BOWImgDescriptorExtractor(extract, matcher)

def extract_sift(fn):#参数为路径
  im = cv2.imread(fn,0)
  return extract.compute(im, detect.detect(im))[1]#返回描述符
#读取8个正样本和8个负样本
for i in range(8):
  bow_kmeans_trainer.add(extract_sift(path(pos,i)))
  bow_kmeans_trainer.add(extract_sift(path(neg,i)))
#利用训练器的cluster（）函数，执行k-means分类并返回词汇
#k-means：属于聚类算法，所谓的聚类算法属于无监督学习，将样本x潜在所属类别Y找出来，具体稍后写一篇补上
voc = bow_kmeans_trainer.cluster()
extract_bow.setVocabulary( voc )

def bow_features(fn):
  im = cv2.imread(fn,0)
  return extract_bow.compute(im, detect.detect(im))
#两个数组，分别为训练数据和标签，并用bow提取器产生的描述符填充
traindata, trainlabels = [],[]
for i in range(20):
  traindata.extend(bow_features(path(pos, i))); trainlabels.append(1)#1为正匹配
  traindata.extend(bow_features(path(neg, i))); trainlabels.append(-1)#-1为负匹配
#创建SVM实例，将训练数据和标签放到numpy数组中进行训练，有关SVM知识稍后写一篇补上
svm = cv2.ml.SVM_create()
svm.train(np.array(traindata), cv2.ml.ROW_SAMPLE, np.array(trainlabels))

def predict(fn):
  f = bow_features(fn)
  p = svm.predict(f)
  print(fn, "\t", p[1][0][0])
  return p
#预测结果
car, notcar = "img/car.jpg", "img/2.jpg"
car_img = cv2.imread(car)
notcar_img = cv2.imread(notcar)
car_predict = predict(car)
not_car_predict = predict(notcar)
#添加文字说明
font = cv2.FONT_HERSHEY_SIMPLEX

if (car_predict[1][0][0] == 1.0):#predict结果为1.0表示能检测到汽车
  cv2.putText(car_img,'Car Detected',(10,30), font, 1,(0,255,0),2,cv2.LINE_AA)

if (not_car_predict[1][0][0] == -1.0):#predict结果为-1.0表示不能检测到汽车
  cv2.putText(notcar_img,'Car Not Detected',(10,30), font, 1,(0,0, 255),2,cv2.LINE_AA)

cv2.imshow('BOW + SVM Success', car_img)
cv2.imshow('BOW + SVM Failure', notcar_img)
cv2.waitKey(0)
cv2.destroyAllWindows()