由于该项目是针对中小学生竞赛并且是第一次举行，所以识别的目标交通标志仅仅只有直行、右转、左转和停车让行。
数据集：
链接: https://pan.baidu.com/s/1sl0qe-qd4cuatmfzenuk0q 提取码: vuvi
源代码：https://github.com/ccxiao5/traffic_sign_recognition
整体流程如下：
- 数据集收集（包括训练集和测试集的分类）
- 图像预处理
- 图像标注
- 根据标注分割得到目标图像
- hog特征提取
- 训练得到模型
- 将模型带入识别算法进行识别
我的数据目录树。其中test_images/train_images是收集得到原始数据集。realtest/realtrain是预处理后的图像。datatest/datatrain是经过分类处理得到的图像，hogtest/hogtrain是通过xml标注后裁剪得到的图像。hogtest_affine/hogtrain_affine是经过仿射变换处理扩充的训练集和测试集。imgtest_hog.txt/imgtrain_hog.txt是测试集和训练集的hog特征
一、图像处理
由于得到的数据集图像大小不一（如下），我们首先从中心区域裁剪并调整正方形图像的大小，然后将处理后的图像保存到realtrain和realtest里面。
图片名称对应关系如下：
img_label = {
"000":"speed_limit_5",
"001":"speed_limit_15",
"002":"speed_limit_30",
"003":"speed_limit_40",
"004":"speed_limit_50",
"005":"speed_limit_60",
"006":"speed_limit_70",
"007":"speed_limit_80",
"008":"no straight or right turn",
"009":"no straight or left turn",
"010":"no straight",
"011":"no left turn",
"012":"do not turn left and right",
"013":"no right turn",
"014":"no overhead",
"015":"no u-turn",
"016":"no motor vehicle",
"017":"no whistle",
"018":"unrestricted speed_40",
"019":"unrestricted speed_50",
"020":"straight or turn right",
"021":"straight",
"022":"turn left",
"023":"turn left or turn right",
"024":"turn right",
"025":"drive on the left side of the road",
"026":"drive on the right side of the road",
"027":"driving around the island",
"028":"motor vehicle driving",
"029":"whistle",
"030":"non-motorized",
"031":"u-turn",
"032":"left-right detour",
"033":"traffic light",
"034":"drive cautiously",
"035":"caution pedestrians",
"036":"attention non-motor vehicle",
"037":"mind the children",
"038":"sharp turn to the right",
"039":"sharp turn to the left",
"040":"downhill steep slope",
"041":"uphill steep slope",
"042":"go slow",
"044":"right t-shaped cross",
"043":"left t-shaped cross",
"045":"village",
"046":"reverse detour",
"047":"railway crossing-1",
"048":"construction",
"049":"continuous detour",
"050":"railway crossing-2",
"051":"accident-prone road section",
"052":"stop",
"053":"no passing",
"054":"no parking",
"055":"no entry",
"056":"deceleration and concession",
"057":"stop for check"
}
def center_crop(img_array, crop_size=-1, resize=-1, write_path=none):
##从中心区域裁剪并调整正方形图像的大小。
rows = img_array.shape[0]
cols = img_array.shape[1]
if crop_size==-1 or crop_size>max(rows,cols):
crop_size = min(rows, cols)
row_s = max(int((rows-crop_size)/2), 0)
row_e = min(row_s+crop_size, rows)
col_s = max(int((cols-crop_size)/2), 0)
col_e = min(col_s+crop_size, cols)
img_crop = img_array[row_s:row_e,col_s:col_e,]
if resize>0:
img_crop = cv2.resize(img_crop, (resize, resize))
if write_path is not none:
cv2.imwrite(write_path, img_crop)
return img_crop
然后根据得到的realtrain和realtest自动生成带有<size><width><height><depth><filename>的xml文件
def write_img_to_xml(imgfile, xmlfile):
img = cv2.imread(imgfile)
img_folder, img_name = os.path.split(imgfile)
img_height, img_width, img_depth = img.shape
doc = document()
annotation = doc.createelement("annotation")
doc.appendchild(annotation)
folder = doc.createelement("folder")
folder.appendchild(doc.createtextnode(img_folder))
annotation.appendchild(folder)
filename = doc.createelement("filename")
filename.appendchild(doc.createtextnode(img_name))
annotation.appendchild(filename)
size = doc.createelement("size")
annotation.appendchild(size)
width = doc.createelement("width")
width.appendchild(doc.createtextnode(str(img_width)))
size.appendchild(width)
height = doc.createelement("height")
height.appendchild(doc.createtextnode(str(img_height)))
size.appendchild(height)
depth = doc.createelement("depth")
depth.appendchild(doc.createtextnode(str(img_depth)))
size.appendchild(depth)
with open(xmlfile, "w") as f:
doc.writexml(f, indent="\t", addindent="\t", newl="\n", encoding="utf-8")
<annotation> <folder>/home/xiao5/desktop/test2/data/realtest/pngimages</folder> <filename>000_1_0001_1_j.png</filename> <size> <width>640</width> <height>640</height> <depth>3</depth> </size> </annotation>
然后对realtrain和realtest的图片进行标注，向默认xml添加新的信息（矩形信息）。
<annotation> <folder>pngimages</folder> <filename>021_1_0001_1_j.png</filename> <path> c:\users\xiao5\desktop\realtest\pngimages1_1_0001_1_j.png </path> <source> <database>unknown</database> </source> <size> <width>640</width> <height>640</height> <depth>3</depth> </size> <segmented>0</segmented> <object> <name>straight</name> <pose>unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>13</xmin> <ymin>22</ymin> <xmax>573</xmax> <ymax>580</ymax> </bndbox> </object> </annotation>
处理完后利用我们添加的矩形将图片裁剪下来并且重命名进行分类。主要思路是：解析xml文档，根据<name>标签进行分类，如果是直行、右转、左转、停止，那么就把它从原图中裁剪下来并重命名,如果没有<object>那么就认为是负样本，其中在处理负样本的时候，我进行了颜色识别，把一张负样本图片根据颜色（红色、蓝色）裁剪成几张负样本，这样做的好处是：我们在进行交通标志的识别时，也是使用的颜色识别来选取到交通标志，我们从负样本中分割出来的相近颜色样本有利于负样本的训练，提高模型精度。
def produce_proposals(xml_dir, write_dir, square=false, min_size=30):
##返回proposal_num对象
proposal_num = {}
for cls_name in classes_name:
proposal_num[cls_name] = 0
index = 0
for xml_file in os.listdir(xml_dir):
img_path, labels = parse_xml(os.path.join(xml_dir,xml_file))
img = cv2.imread(img_path)
##如果图片中没有出现定义的那几种交通标志就把它当成负样本
if len(labels) == 0:
neg_proposal_num = produce_neg_proposals(img_path, write_dir, min_size, square, proposal_num["background"])
proposal_num["background"] = neg_proposal_num
else:
proposal_num = produce_pos_proposals(img_path, write_dir, labels, min_size, square=true, proposal_num=proposal_num)
if index%100 == 0:
print ("total xml file number = ", len(os.listdir(xml_dir)), "current xml file number = ", index)
print ("proposal num = ", proposal_num)
index += 1
return proposal_num
为了提高模型的精确度，还对目标图片（四类图片）进行仿射变换来扩充训练集。
def affine(img, delta_pix):
rows, cols, _ = img.shape
pts1 = np.float32([[0,0], [rows,0], [0, cols]])
pts2 = pts1 + delta_pix
m = cv2.getaffinetransform(pts1, pts2)
res = cv2.warpaffine(img, m, (rows, cols))
return res
def affine_dir(img_dir, write_dir, max_delta_pix):
img_names = os.listdir(img_dir)
img_names = [img_name for img_name in img_names if img_name.split(".")[-1]=="png"]
for index, img_name in enumerate(img_names):
img = cv2.imread(os.path.join(img_dir,img_name))
save_name = os.path.join(write_dir, img_name.split(".")[0]+"f.png")
delta_pix = np.float32(np.random.randint(-max_delta_pix,max_delta_pix+1,[3,2]))
img_a = affine(img, delta_pix)
cv2.imwrite(save_name, img_a)
二、hog特征提取
处理好图片后分别对训练集和测试集进行特征提取得到imgtest_hog.txt和imgtrain_hog.txt
def hog_feature(img_array, resize=(64,64)):
##提取hog特征
img = cv2.cvtcolor(img_array, cv2.color_bgr2gray)
img = cv2.resize(img, resize)
bins = 9
cell_size = (8, 8)
cpb = (2, 2)
norm = "l2"
features = ft.hog(img, orientations=bins, pixels_per_cell=cell_size,
cells_per_block=cpb, block_norm=norm, transform_sqrt=true)
return features
def extra_hog_features_dir(img_dir, write_txt, resize=(64,64)):
##提取目录中所有图像hog特征
img_names = os.listdir(img_dir)
img_names = [os.path.join(img_dir, img_name) for img_name in img_names]
if os.path.exists(write_txt):
os.remove(write_txt)
with open(write_txt, "a") as f:
index = 0
for img_name in img_names:
img_array = cv2.imread(img_name)
features = hog_feature(img_array, resize)
label_name = img_name.split("/")[-1].split("_")[0]
label_num = img_label[label_name]
row_data = img_name + "\t" + str(label_num) + "\t"
for element in features:
row_data = row_data + str(round(element,3)) + " "
row_data = row_data + "\n"
f.write(row_data)
if index%100 == 0:
print ("total image number = ", len(img_names), "current image number = ", index)
index += 1
三、模型训练
利用得到的hog特征进行训练模型得到svm_model.pkl
def load_hog_data(hog_txt):
img_names = []
labels = []
hog_features = []
with open(hog_txt, "r") as f:
data = f.readlines()
for row_data in data:
row_data = row_data.rstrip()
img_path, label, hog_str = row_data.split("\t")
img_name = img_path.split("/")[-1]
hog_feature = hog_str.split(" ")
hog_feature = [float(hog) for hog in hog_feature]
#print "hog feature length = ", len(hog_feature)
img_names.append(img_name)
labels.append(label)
hog_features.append(hog_feature)
return img_names, np.array(labels), np.array(hog_features)
def svm_train(hog_features, labels, save_path="./svm_model.pkl"):
clf = svc(c=10, tol=1e-3, probability = true)
clf.fit(hog_features, labels)
joblib.dump(clf, save_path)
print ("finished.")
四、交通标志识别及实验测试
交通标志识别的流程：颜色识别得到阈值范围内的二值图、然后进行轮廓识别、剔除多余矩阵。
def preprocess_img(imgbgr):
##将图像由rgb模型转化成hsv模型
imghsv = cv2.cvtcolor(imgbgr, cv2.color_bgr2hsv)
bmin = np.array([110, 43, 46])
bmax = np.array([124, 255, 255])
##使用inrange(hsv,lower,upper)设置阈值去除背景颜色
img_bbin = cv2.inrange(imghsv,bmin, bmax)
rmin2 = np.array([165, 43, 46])
rmax2 = np.array([180, 255, 255])
img_rbin = cv2.inrange(imghsv,rmin2, rmax2)
img_bin = np.maximum(img_bbin, img_rbin)
return img_bin
'''
提取轮廓,返回轮廓矩形框
'''
def contour_detect(img_bin, min_area=0, max_area=-1, wh_ratio=2.0):
rects = []
##检测轮廓，其中cv2.retr_external只检测外轮廓，cv2.chain_approx_none 存储所有的边界点
##findcontours返回三个值:第一个值返回img，第二个值返回轮廓信息，第三个返回相应轮廓的关系
contours, hierarchy= cv2.findcontours(img_bin.copy(), cv2.retr_external, cv2.chain_approx_none)
if len(contours) == 0:
return rects
max_area = img_bin.shape[0]*img_bin.shape[1] if max_area<0 else max_area
for contour in contours:
area = cv2.contourarea(contour)
if area >= min_area and area <= max_area:
x, y, w, h = cv2.boundingrect(contour)
if 1.0*w/h < wh_ratio and 1.0*h/w < wh_ratio:
rects.append([x,y,w,h])
return rects
然后加载模型进行测验
if __name__ == "__main__":
cap = cv2.videocapture(0)
cv2.namedwindow('camera')
cv2.resizewindow("camera",640,480)
cols = int(cap.get(cv2.cap_prop_frame_width))
rows = int(cap.get(cv2.cap_prop_frame_height))
clf = joblib.load("/home/xiao5/desktop/test2/svm_model.pkl")
i=0
while (1):
i+=1
ret, img = cap.read()
img_bin = preprocess_img(img)
min_area = img_bin.shape[0]*img.shape[1]/(25*25)
rects = contour_detect(img_bin, min_area=min_area)
if rects:
max_x=0
max_y=0
max_w=0
max_h=0
for r in rects:
if r[2]*r[3]>=max_w*max_h:
max_x,max_y,max_w,max_h=r
proposal = img[max_y:(max_y+max_h),max_x:(max_x+max_w)]##用numpy数组对图像像素进行访问时，应该先写图像高度所对应的坐标(y,row)，再写图像宽度对应的坐标(x,col)。
cv2.rectangle(img,(max_x,max_y), (max_x+max_w,max_y+max_h), (0,255,0), 2)
cv2.imshow("proposal", proposal)
cls_prop = hog_extra_and_svm_class(proposal, clf)
cls_prop = np.round(cls_prop, 2)
cls_num = np.argmax(cls_prop)##找到最大相似度的索引
if cls_names[cls_num] is not "background":
print(cls_names[cls_num])
else:
print("n/a")
cv2.imshow('camera',img)
cv2.waitkey(40)
cv2.destroyallwindows()
cap.release()
到此这篇关于python3+opencv实现简单交通标志识别的文章就介绍到这了,更多相关python3 opencv交通标志识别内容请搜索www.887551.com以前的文章或继续浏览下面的相关文章希望大家以后多多支持www.887551.com！
黄山市民网：https://www.huangshanshimin.com/
