1、模板匹配
运行指令：python template_matching.py --source 3.jpg --template 2.jpg
import argparseimport cv2ap = argparse.ArgumentParser()ap.add_argument("-s", "--source", required=True, help="Path to the source image")ap.add_argument("-t", "--template", required=True, help="Path to the template image")args = vars(ap.parse_args()) source = cv2.imread(args["source"])template = cv2.imread(args["template"])(tempH, tempW) = template.shape[:2] result = cv2.matchTemplate(source, template, cv2.TM_CCOEFF) #参数1：源图像 参数2：模板图像 参数3：模板匹配方法(minVal, maxVal, minLoc, (x, y)) = cv2.minMaxLoc(result) #获取最佳匹配的（x,y）坐标cv2.rectangle(source, (x, y), (x + tempW, y + tempH), (0, 255, 0), 2) #在源图像上绘制边框
2、训练自己的物体探测器
作用：结合caltech101数据集，结合.mat文件，训练对象检测器，生成SVM线性支持向量机
train_detector.py
运行指令：python train_detector.py --class stop_sign_images --annotations stop_sign_annotations \
--output output/stop_sign_detector.svm
from __future__ import print_functionfrom imutils import pathsfrom scipy.io import loadmatfrom skimage import ioimport argparseimport dlib ap = argparse.ArgumentParser()ap.add_argument("-c", "--class", required=True, help="Path to the CALTECH-101 class images")#要训练一个对象检测器的具体CALTECH-101（数据集）类的路径ap.add_argument("-a", "--annotations", required=True, help="Path to the CALTECH-101 class annotations")#指定我们正在训练的特定类的边界框的路径（caltech101数据集中对应的.mat文件夹）ap.add_argument("-o", "--output", required=True, help="Path to the output detector")#输出分类器的路径args = vars(ap.parse_args())print("[INFO] gathering images and bounding boxes...")options = dlib.simple_object_detector_training_options()images = []boxes = [] for imagePath in paths.list_images(args["class"]):#循环输入需要被训练的图像 imageID = imagePath[imagePath.rfind("/") + 1:].split("_")[1] imageID = imageID.replace(".jpg", "") p = "{}/annotation_{}.mat".format(args["annotations"], imageID) annotations = loadmat(p)["box_coord"]#从路径中提取图像ID，然后使用图像ID ，从磁盘加载相应的 注释（即边界框） bb = [dlib.rectangle(left=long(x), top=long(y), right=long(w), bottom=long(h)) for (y, h, x, w) in annotations]#构 矩形 对象来表示边界框 boxes.append(bb) images.append(io.imread(imagePath))#更新边界当前图像框和添加图片到列表中，在DLIB库将需要的两个图像和函数加载到训练分类器中 test_detector.py
运行指令：python test_detector.py --detector output/stop_sign_detector.svm --testing stop_sign_testing
作用：测试自定义对象检测器效果
from imutils import pathsimport argparseimport dlibimport cv2 ap = argparse.ArgumentParser()ap.add_argument("-d", "--detector", required=True, help="Path to trained object detector")#训练出的SVM线性检测器ap.add_argument("-t", "--testing", required=True, help="Path to directory of testing images")#包含停止标志图像进行测试的目录的路径args = vars(ap.parse_args()) detector = dlib.simple_object_detector(args["detector"])for testingPath in paths.list_images(args["testing"]):#循环测试需要测试的图像 image = cv2.imread(testingPath) boxes = detector(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)) for b in boxes: (x, y, w, h) = (b.left(), b.top(), b.right(), b.bottom()) cv2.rectangle(image, (x, y), (w, h), (0, 255, 0), 2) cv2.imshow("Image", image) cv2.waitKey(0)
3.1、图像金字塔
目录：
作用：指图像按一定比例缩放，并且返回。
知识点：关键字 yield 返回并不结束，理解为延迟返回结果
helper.py:
import imutils#自定义金字塔函数def pyramid(image, scale=1.5, minSize=(30, 30)): #参数1：源图像 参数2：每次缩放比例 参数3：设置最小尺寸 yield image #定义为金字塔原图像 while True: w = int(image.shape[1] / scale) image = imutils.resize(image, width=w) #设置长宽按比例缩放 if image.shape[0] < minSize[1] or image.shape[1] < minSize[0]:#判断缩放的图片是否满足需求 break yield image#定义滑动穿口函数def sliding_window(image, stepSize, windowSize):#参数1：要检查的对象 参数2：每次跳过多少像素，参数3：每次窗口要检查的大小
for y in xrange(0, image.shape[0], stepSize): for x in xrange(0, image.shape[1], stepSize): yield (x, y, image[y:y + windowSize[1], x:x + windowSize[0]])
test_pyramid.py
示例：python test_pyramid.py --image florida_trip.png --scale 1.5
#对金字塔函数的使用 from pyimagesearch.object_detection.helpers import pyramidimport argparseimport cv2 ap = argparse.ArgumentParser()ap.add_argument("-i", "--image", required=True, help="path to the input image")ap.add_argument("-s", "--scale", type=float, default=1.5, help="scale factor size") #每次图像缩小比例args = vars(ap.parse_args()) image = cv2.imread(args["image"]) for (i, layer) in enumerate(pyramid(image, scale=args["scale"])): cv2.imshow("Layer {}".format(i + 1), layer) cv2.waitKey(0) 3.2、滑动窗户
test_sliding_window.py
作用：金字塔与滑动窗口的联合的运用
运行指令：python test_sliding_window.py --image florida_trip.png --width 64 --height 64
from pyimagesearch.object_detection.helpers import sliding_windowfrom pyimagesearch.object_detection.helpers import pyramidimport argparseimport timeimport cv2 ap = argparse.ArgumentParser()ap.add_argument("-i", "--image", required=True, help="path to the input image")#需要处理的图像ap.add_argument("-w", "--width", type=int, help="width of sliding window")#滑动窗口的宽度ap.add_argument("-t", "--height", type=int, help="height of sliding window")#滑动窗口的高度ap.add_argument("-s", "--scale", type=float, default=1.5, help="scale factor size")#图像金字塔的调整大小因子args = vars(ap.parse_args()) image = cv2.imread(args["image"])(winW, winH) = (args["width"], args["height"])for layer in pyramid(image, scale=args["scale"]): for (x, y, window) in sliding_window(layer, stepSize=32, windowSize=(winW, winH)): if window.shape[0] != winH or window.shape[1] != winW: continue clone = layer.copy() cv2.rectangle(clone, (x, y), (x + winW, y + winH), (0, 255, 0), 2) cv2.imshow("Window", clone) cv2.waitKey(1) time.sleep(0.025) 4.1构建自定义检测框架的6个步骤
哈尔级联的问题（Viola-Jones探测器（2））：OpenCV中检测到面孔/人物/对象/任何东西，将花费大量时间调整cv2.detectMultiScale参数。
Viola-Jones探测器不是我们唯一的物体检测选择。我们可以使用关键点对象检测，局部不变描述符和一系列的视觉词模型。
六步框架：
步骤1：从想要检测的对象的训练数据中取样p个正样本，并从这些样本中提取HOG描述符。将提取对象的边界框（包括图像的训练数据），然后在该ROI上计算HOG特征，HOG功能将作为正面例子。
步骤2：负面训练集不包含任何要检测的对象，并从这些样品中提取HOG描述为好。实践中负面样本远远大于正样本
步骤3：在正负样本上训练线性支持向量机。
步骤4：应用硬阴极开采。对于负面训练集中的每个图像和每个图像的每个可能的比例（即图像金字塔），应用滑动窗口技术将窗口滑过图像。减少我们最终检测器中的假阳性数量。
步骤5：采取在硬阴极开采阶段发现的假阳性样本，以其置信度（即概率）进行排序，并使用这些阴性样本重新训练分类器
步骤6：分类器现在已经受过培训，可以应用于测试数据集。再次，就像在步骤4中，对于测试集中的每个图像，并且对于图像的每个比例，应用滑动窗口技术。在每个窗口中，提取HOG描述符并应用分类器。如果分类器以很大的概率检测到对象，记录窗口的边界框。完成扫描图像后，应用非最大抑制来删除冗余和重叠的边界框。
扩展和其他方法：
在物体检测中使用HOG+线性SVM方法简单易懂。与使用的标准6步框架略有不同。
第一个变化是关于HOG滑动窗口和非最大抑制方法。代替从提取特征的二者的正和负数据集，所述方法DLIB优化HOG滑动窗口使得上的错误的数目 的每个训练图像。这意味着 整个 训练图像都用于（1）提取正例，和（2） 从图像的所有其他区域提取 负样本。这完全减轻 了负面培训的需要和强烈的消极采矿的要求。这是Max-Margin Object 检测方法如此之快的原因之一 。
其次，在实际的训练阶段，dlib也考虑到非最大的压制。我们通常只应用NMS来获得最终的边界框，但在这种情况下，我们实际上可以在训练阶段使用NMS。这有助于减少误报 实质上并再次减轻了硬负开采的需要。
最后，dlib使用非常精确的算法来找到分离两个图像类的最优超平面。该方法比许多其他最先进的对象检测器获得更高的精度（具有较低的假阳性率）。
5、准备实验和培训数据
框架的完整目录结构：（pyimagesearch同级目录还有conf目录存放json文件，datasets目录，存放数据集）
实验配置：运用JSON配置文件
json配置文件优势：
1、不需要明确定义一个永无止尽的命令行参数列表，只需要提供的是我们配置文件的路径。
2、配置文件允许将所有相关参数整合到一个 位置。
3、确保我们不会忘记为每个Python脚本使用哪些命令行选项。所有选项将在我们的配置文件中定义。
4、允许我们为每个要创建的对象检测器配置一个配置文件 。这是一个巨大的优势，允许我们通过修改单个文件来定义对象检测器 。
cars.json:
{ ####### # DATASET PATHS ####### "image_dataset": "datasets/caltech101/101_ObjectCategories/car_side",#我们的“正例”图像的路径，需要训练的基础数据 "image_annotations": "datasets/caltech101/Annotations/car_side",#包含与image_dataset中每个图像相关联的边界框的目录的路径 "image_distractions": "datasets/sceneclass13",#不包含我们想要检测的对象的任何示例的“否定示例” } explore_dims.py
作用：在caltech101数据中提取.mat文件信息，遍历所有图片轮廓信息，同时获取滑动活动窗口尺寸
涉及到知识点：1、处理caltech101数据集方法及提取.mat文件信息
2、用用golb.golb()函数遍历文件夹中的文件方法
运行指令：python explore_dims.py --conf conf/cars.json
from __future__ import print_functionfrom pyimagesearch.utils import Conffrom scipy import ioimport numpy as npimport argparseimport glob ap = argparse.ArgumentParser()ap.add_argument("-c", "--conf", required=True, help="path to the configuration file")args = vars(ap.parse_args())conf = Conf(args["conf"])#加载配置文件widths = []#初始化检测对象的宽度heights = []#初始化检测对象的高度 for p in glob.glob(conf["image_annotations"] + "/*.mat"):#循环检测对象的注释文件 (y, h, x, w) = io.loadmat(p)["box_coord"][0] widths.append(w - x) heights.append(h - y)#加载每个检测对象的注释文件相关联的边界框，并更新相应的宽度和高度列表。 #计算平均宽度和高度(avgWidth, avgHeight) = (np.mean(widths), np.mean(heights))print("[INFO] avg. width: {:.2f}".format(avgWidth))print("[INFO] avg. height: {:.2f}".format(avgHeight))print("[INFO] aspect ratio: {:.2f}".format(avgWidth / avgHeight)) conf.py:解析命令行参数
作用：解析car.json文件的类python内置函数__getitem__的作用:
在类中定义了__getitem__()方法，那么他的实例对象（假设为P）就可以这样P[key]取值。当实例对象做P[key]运算时，就会调用类中的__getitem__()方法
import commentjson as json class Conf: def __init__(self, confPath): conf = json.loads(open(confPath).read()) self.__dict__.update(conf) def __getitem__(self, k): return self.__dict__.get(k, None)
6、构建HOG描述符
cars.json:
{ ####### # DATASET PATHS ####### "image_dataset": "datasets/caltech101/101_ObjectCategories/car_side", "image_annotations": "datasets/caltech101/Annotations/car_side", "image_distractions": "datasets/sceneclass13", ####### # FEATURE EXTRACTION ####### "features_path": "output/cars/car_features.hdf5", "percent_gt_images": 0.5, "offset": 5, "use_flip": true, "num_distraction_images": 500, "num_distractions_per_image": 10, ####### # HISTOGRAM OF ORIENTED GRADIENTS DESCRIPTOR 使用的方向梯度直方图 ####### "orientations": 9, "pixels_per_cell": [4, 4], #能被滑动窗口尺寸整除 "cells_per_block": [2, 2], "normalize": true, ####### # OBJECT DETECTOR 定义滑动窗口大小 ####### "window_step": 4, "overlap_thresh": 0.3, "pyramid_scale": 1.5, "window_dim": [96, 32], "min_probability": 0.7} dataset.py
作用：定义h5py数据库运用的方法
涉及到知识点：1、对h5py数据库的运用
疑问：create_dataset（）函数参数作用:
参数：数据库的名字，参数2：数据库维度，参数3：数据类型
扩展：h5py文件是存放两类对象的容器，数据集(dataset)和组(group)，dataset类似数组类的数据集合，和numpy的数组差不多。group是像文件夹一样的容器，它好比python中的字典，有键(key)和值(value)。group中可以存放dataset或者其他的group。”键”就是组成员的名称。
import numpy as npimport h5py #从磁盘上的数据集加载特征向量和标签def dump_dataset(data,labels,path,datasetName,writeMethod="w"):#参数1：要写入HDF5数据集的特征向量列表。参数2：标签，与每个特征向量相关联的标签列表。参数3：HDF5数据集在磁盘上的存储位置。参数5：HDF5文件中数据集的名称。参数5：HDF5数据集的写入方法 db = h5py.File(path, writeMethod) dataset = db.create_dataset(datasetName, (len(data), len(data[0]) + 1), dtype="float") dataset[0:len(data)] = np.c_[labels, data] db.close() def load_dataset(path, datasetName):#加载与datasetName相关联的特征向量和标签 db = h5py.File(path, "r") (labels, data) = (db[datasetName][:, 0], db[datasetName][:, 1:]) db.close() return (data, labels)
helpers.py:
作用：返回每张图片的ROI,（最小包围矩阵）
import imutilsimport cv2 def crop_ct101_bb(image, bb, padding=10, dstSize=(32, 32)): (y, h, x, w) = bb (x, y) = (max(x - padding, 0), max(y - padding, 0)) roi = image[y:h + padding, x:w + padding] roi = cv2.resize(roi, dstSize, interpolation=cv2.INTER_AREA) return roi
extract_features.py:
作用：提取图片的hog特征向量，为SVC数据分类提供数据
涉及到知识点：1、运用imutils中的paths模块遍历文件
疑惑：1、 progressbar模块的作用：
创建一个进度条显示对象
widgets可选参数含义：
'Progress: ' ：设置进度条前显示的文字
Percentage() ：显示百分比
Bar('#') ： 设置进度条形状
ETA() ： 显示预计剩余时间
Timer() ：显示已用时间
2、HOG函数的详解
https://blog.csdn.net/zhazhiqiang/article/details/20221143
https://baike.baidu.com/item/HOG/9738560?fr=aladdin
3、random.sample函数作用？
sample(seq, n) 从序列seq中选择n个随机且独立的元素；
4、random.choice函数的作用？
choice(seq) 从序列seq中返回随机的元素
random模块拓展：
1 )、random() 返回0<=n<1之间的随机实数n；
2)、getrandbits(n) 以长整型形式返回n个随机位；
3)、shuffle(seq[, random]) 原地指定seq序列；5、sklearn.feature_extraction.image模块中extract_patches_2d函数的作用？
6）提示信息：Default value of `block_norm`==`L1` is deprecated and will be changed to `L2-Hys` in v0.15 比Py中特征少？
运行指令：python extract_features.py --conf conf/cars.json
# import the necessary packagesfrom __future__ import print_functionfrom sklearn.feature_extraction.image import extract_patches_2dfrom pyimagesearch.object_detection import helpersfrom pyimagesearch.descriptors import HOGfrom pyimagesearch.utils import datasetfrom pyimagesearch.utils import Conffrom imutils import pathsfrom scipy import ioimport numpy as npimport progressbarimport argparseimport randomimport cv2ap = argparse.ArgumentParser()ap.add_argument("-c", "--conf", required=True, help="path to the configuration file")args = vars(ap.parse_args()) conf = Conf(args["conf"])#加载配置文件#调用函数初始化HOG描述符hog = HOG(orientations=conf["orientations"], pixelsPerCell=tuple(conf["pixels_per_cell"]), cellsPerBlock=tuple(conf["cells_per_block"]), normalize=conf["normalize"])data = []labels = []#随机抽取车测试图trnPaths = list(paths.list_images(conf["image_dataset"]))trnPaths = random.sample(trnPaths, int(len(trnPaths) * conf["percent_gt_images"]))print("[INFO] describing training ROIs...")widgets = ["Extracting: ", progressbar.Percentage(), " ", progressbar.Bar(), " ", progressbar.ETA()]pbar = progressbar.ProgressBar(maxval=len(trnPaths), widgets=widgets).start()#训练每个图像for (i, trnPath) in enumerate(trnPaths): image = cv2.imread(trnPath) image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) imageID = trnPath[trnPath.rfind("_") + 1:].replace(".jpg", "")#提取文件名 p = "{}/annotation_{}.mat".format(conf["image_annotations"], imageID) bb = io.loadmat(p)["box_coord"][0] roi = helpers.crop_ct101_bb(image, bb, padding=conf["offset"], dstSize=tuple(conf["window_dim"])) #确定我们是否应该使用ROI的水平翻转作为额外的训练数据 rois = (roi, cv2.flip(roi, 1)) if conf["use_flip"] else (roi,) #中提取HOG特征，并更新 数据 和 标签 列表 for roi in rois: features = hog.describe(roi) data.append(features) labels.append(1) pbar.update(i)dstPaths = list(paths.list_images(conf["image_distractions"]))pbar = progressbar.ProgressBar(maxval=conf["num_distraction_images"], widgets=widgets).start()print("[INFO] describing distraction ROIs...") #训练负图像样本for i in np.arange(0, conf["num_distraction_images"]): image = cv2.imread(random.choice(dstPaths)) image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) patches = extract_patches_2d(image, tuple(conf["window_dim"]), max_patches=conf["num_distractions_per_image"]) for patch in patches: features = hog.describe(patch) data.append(features) labels.append(-1) pbar.update(i)pbar.finish()print("[INFO] dumping features and labels to file...")dataset.dump_dataset(data, labels, conf["features_path"], "features") 7、初始训练阶段
car.json:
{ ####### # DATASET PATHS ####### "image_dataset": "datasets/caltech101/101_ObjectCategories/car_side", "image_annotations": "datasets/caltech101/Annotations/car_side", "image_distractions": "datasets/sceneclass13", ####### # FEATURE EXTRACTION ####### "features_path": "output/cars/car_features.hdf5", "percent_gt_images": 0.5, "offset": 5, "use_flip": true, "num_distraction_images": 500, "num_distractions_per_image": 10, ####### # HISTOGRAM OF ORIENTED GRADIENTS DESCRIPTOR ####### "orientations": 9, "pixels_per_cell": [4, 4], "cells_per_block": [2, 2], "normalize": true, ####### # OBJECT DETECTOR ####### "window_step": 4, "overlap_thresh": 0.3, "pyramid_scale": 1.5, "window_dim": [96, 32], "min_probability": 0.7, ####### # LINEAR SVM ####### "classifier_path": "output/cars/model.cpickle",#分类器被储存的位置 "C": 0.01,} train_model.py
作用：对获取的图像hog特征向量，运用SVC线性分类处理
疑问：1、sklearn函数模块详解？
2、args["hard_negatives"]参数作用？
3、numpy.stack()函数作业用：
改变列表数据维度
参数1：列表数据，参数2：设置列表维度
4、numpy.hstack()函数作用
水平(按列顺序)把数组给堆叠起来，vstack()函数正好和它相反
参数tup可以是元组，列表，或者numpy数组，返回结果为numpy的数组。
运行指令：python train_model.py --conf conf/cars.json
from __future__ import print_functionfrom pyimagesearch.utils import datasetfrom pyimagesearch.utils import Conffrom sklearn.svm import SVCimport numpy as npimport argparseimport cPickle ap = argparse.ArgumentParser()ap.add_argument("-c", "--conf", required=True, help="path to the configuration file")ap.add_argument("-n", "--hard-negatives", type=int, default=-1, help="flag indicating whether or not hard negatives should be used")args = vars(ap.parse_args())print("[INFO] loading dataset...")conf = Conf(args["conf"])(data, labels) = dataset.load_dataset(conf["features_path"], "features")#抓取提取的特征向量和标签 if args["hard_negatives"] > 0: print("[INFO] loading hard negatives...") (hardData, hardLabels) = dataset.load_dataset(conf["features_path"], "hard_negatives") data = np.vstack([data, hardData]) labels = np.hstack([labels, hardLabels])print("[INFO] training classifier...")model = SVC(kernel="linear", C=conf["C"], probability=True, random_state=42)model.fit(data, labels) print("[INFO] dumping classifier...")f = open(conf["classifier_path"], "w")f.write(cPickle.dumps(model))#将分类器转储成档f.close() objectdetector.py:
作用：经过滑动窗口和金字塔处理后的图像，提取符合概率的轮廓列表。 疑惑：改变概率参数，符合要求的轮廓数量没有发生改变？ pyramid函数（3.1）、sliding_window函数（3.2）写到helpers.py中
iimport helpers class ObjectDetector: def __init__(self, model, desc): self.model = model self.desc = desc def detect(self, image, winDim, winStep=4, pyramidScale=1.5, minProb=0.7):#image:需要检测的图像，winDim:滑动窗口尺寸大小 boxes = [] probs = [] for layer in helpers.pyramid(image, scale=pyramidScale, minSize=winDim):#循环金子塔中的图像 scale = image.shape[0] / float(layer.shape[0]) for (x, y, window) in helpers.sliding_window(layer, winStep, winDim): (winH, winW) = window.shape[:2] if winH == winDim[1] and winW == winDim[0]: features = self.desc.describe(window).reshape(1, -1) prob = self.model.predict_proba(features)[0][1] if prob > minProb: (startX, startY) = (int(scale * x), int(scale * y)) endX = int(startX + (scale * winW)) endY = int(startY + (scale * winH)) boxes.append((startX, startY, endX, endY)) probs.append(prob) return (boxes, probs)
test_model_no_nms.py(与pyimagesearch同级目录下)
作用：测试通过轮廓列表寻找到轮廓是否正确
疑问：
1、sklearn.svm模块中SVC的详解
参数解释链接：https://blog.csdn.net/szlcw1/article/details/52336824
2、提示错误信息：Default value of `block_norm`==`L1` is deprecated and will be changed to `L2-Hys` in v0.15
运行指令：python test_model_no_nms.py --conf conf/cars.json--image datasets/caltech101/101_ObjectCategories/car_side/image_0004.jpg
from pyimagesearch.object_detection import ObjectDetectorfrom pyimagesearch.descriptors import HOGfrom pyimagesearch.utils import Confimport imutilsimport argparseimport cPickleimport cv2 ap = argparse.ArgumentParser()ap.add_argument("-c", "--conf", required=True, help="path to the configuration file")ap.add_argument("-i", "--image", required=True, help="path to the image to be classified")args = vars(ap.parse_args()) conf = Conf(args["conf"])model = cPickle.loads(open(conf["classifier_path"]).read()) #SVC线性值hog = HOG(orientations=conf["orientations"], pixelsPerCell=tuple(conf["pixels_per_cell"]), cellsPerBlock=tuple(conf["cells_per_block"]), normalize=conf["normalize"]) #hog特征向量值提取方法od = ObjectDetector(model, hog)image = cv2.imread(args["image"])image = imutils.resize(image, width=min(260, image.shape[1]))gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) (boxes, probs) = od.detect(gray, conf["window_dim"], winStep=conf["window_step"], pyramidScale=conf["pyramid_scale"], minProb=conf["min_probability"]) for (startX, startY, endX, endY) in boxes: cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2) cv2.imshow("Image", image)cv2.waitKey(0) 问题1：修改感兴趣概率，获取的敏感区域一样？
8、非最大抑制
作用：解决重叠边界框，寻找到最佳匹配轮廓
nms.py(object_detection目录下)：
疑问：1、numpy模块中argsort()函数的作用：
获取数组从小到的大索引值
2、numpy模块中concatenate()函数作用：
对数组进行拼接
3、while里面对idx的处理逻辑？语法规则？
讲解示例：https://blog.csdn.net/scut_salmon/article/details/79318387
nms.py
import numpy as npdef non_max_suppression(boxes, probs, overlapThresh):#参数1：边界框列表，参数2：每个框相关的概率，参数3：重叠的阀值 if len(boxes) == 0:#判断边界框列表是否为空 return [] if boxes.dtype.kind == "i": boxes = boxes.astype("float")#将边界框数据由整型转换成浮点型 #获取边界框每个角的坐标 pick = [] x1 = boxes[:, 0] y1 = boxes[:, 1] x2 = boxes[:, 2] y2 = boxes[:, 3] #获取边界框的面积 area = (x2 - x1 + 1) * (y2 - y1 + 1) idxs = np.argsort(probs) #获取列表的长度，并将其保留在边框列表中 while len(idxs) > 0: last = len(idxs) - 1 i = idxs[last] pick.append(i) #获取边最大坐标的界框和最小的坐标边界宽 xx1 = np.maximum(x1[i], x1[idxs[:last]]) yy1 = np.maximum(y1[i], y1[idxs[:last]]) xx2 = np.minimum(x2[i], x2[idxs[:last]]) yy2 = np.minimum(y2[i], y2[idxs[:last]]) w = np.maximum(0, xx2 - xx1 + 1) h = np.maximum(0, yy2 - yy1 + 1) # 计算重叠比例 overlap = (w * h) / area[idxs[:last]] idxs = np.delete(idxs, np.concatenate(([last], np.where(overlap > overlapThresh)[0]))) return boxes[pick].astype("int") test_model.py(与pyimagesearch目录同级)：
作用：测试解决重叠轮廓的边界效果
运行指令：python test_model.py --conf conf/cars.json--image datasets/caltech101/101_ObjectCategories/car_side/image_0004.jpg
from pyimagesearch.object_detection import non_max_suppressionfrom pyimagesearch.object_detection import ObjectDetectorfrom pyimagesearch.descriptors import HOGfrom pyimagesearch.utils import Confimport numpy as npimport imutilsimport argparseimport cPickleimport cv2 ap = argparse.ArgumentParser()ap.add_argument("-c", "--conf", required=True, help="path to the configuration file")ap.add_argument("-i", "--image", required=True, help="path to the image to be classified")args = vars(ap.parse_args()) conf = Conf(args["conf"]) model = cPickle.loads(open(conf["classifier_path"]).read())hog = HOG(orientations=conf["orientations"], pixelsPerCell=tuple(conf["pixels_per_cell"]), cellsPerBlock=tuple(conf["cells_per_block"]), normalize=conf["normalize"])od = ObjectDetector(model, hog)image = cv2.imread(args["image"])image = imutils.resize(image, width=min(260, image.shape[1]))gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) (boxes, probs) = od.detect(gray, conf["window_dim"], winStep=conf["window_step"], pyramidScale=conf["pyramid_scale"], minProb=conf["min_probability"])pick = non_max_suppression(np.array(boxes), probs, conf["overlap_thresh"])orig = image.copy() for (startX, startY, endX, endY) in boxes: cv2.rectangle(orig, (startX, startY), (endX, endY), (0, 0, 255), 2) for (startX, startY, endX, endY) in pick: cv2.rectangle(image, (startX, startY), (endX, endY), (0, 255, 0), 2) cv2.imshow("Original", orig)cv2.imshow("Image", image)cv2.waitKey(0) 9、坚硬的负面特征采集
作用：训练与需要提取的特征完全不相关的特征，一般是物体的背面场景，所以一般应用sceneclass13数据集，训练负面特征变量，减少误判情况。将负面数据也写入h5py数据库中。
运行指令：python hard_negative_mine.py --conf conf/cars.json
hard_negative_mine.py
from __future__ import print_functionfrom pyimagesearch.object_detection.objectdetector import ObjectDetectorfrom pyimagesearch.descriptors.hog import HOGfrom pyimagesearch.utils import datasetfrom pyimagesearch.utils.conf import Conffrom imutils import pathsimport numpy as npimport progressbarimport argparseimport cPickleimport randomimport cv2ap = argparse.ArgumentParser()ap.add_argument("-c", "--conf", required = True, help = "path to the configuration file")args = vars(ap.parse_args())conf =Conf(args["conf"])data =[]model =cPickle.loads(open(conf["classifier_path"]).read())hog =HOG(orientations = conf["orientations"], pixelsPerCell = tuple(conf["pixels_per_cell"]), cellsPerBlock = tuple(conf["cells_per_block"]), normalize = conf["normalize"])od = ObjectDetector(model, hog)dstPaths = list(paths.list_images(conf["image_distractions"]))dstPaths =random.sample(dstPaths, conf["hn_num_distraction_images"])widgets = ["Mining:", progressbar.Percentage(), " ", progressbar.Bar(), "", progressbar.ETA()]pbar = progressbar.ProgressBar(maxval = len(dstPaths), widgets = widgets).start()myindex = 0for (i, imagePath) in enumerate(dstPaths): image = cv2.imread(imagePath) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) (boxes, probs) = od.detect(gray, conf["window_dim"], winStep = conf["hn_window_step"], pyramidScale = conf["hn_pyramid_scale"], minProb = conf["hn_min_probability"]) for (prob, (startX, startY, endX, endY)) in zip(probs, boxes): roi = cv2.resize(gray[startY:endY, startX:endX], tuple(conf["window_dim"]), interpolation = cv2.INTER_AREA) features = hog.describe(roi) data.append(np.hstack([[prob], features])) pbar.update(i)pbar.finish()print("[INFO] sorting by probability...")data = np.array(data)data = data[data[:, 0].argsort()[::-1]]print("[INFO] dmping hard negatives to file...")dataset.dump_dataset(data[:, 1:], [-1] * len(data), conf["features_path"], "hard_negatives", writeMethod = "a") 10、重新训练对象检测器
作用：将坚硬的负面特征加入到SVM中，减少虚假轮廓的出现
运行指令：python train_model.py --conf conf/cars.json --hard-negatives 1
train_model.py
from __future__ import print_functionfrom pyimagesearch.utils import datasetfrom pyimagesearch.utils.conf import Conffrom sklearn.svm import SVCimport argparseimport pickleimport numpy as npap = argparse.ArgumentParser()ap.add_argument("-c", "--conf", required = True, help = "path to the configuration file")ap.add_argument("-n", "--hard-negatives", type = int, default = -1, help="flag indicating whether or not hard negatives should be used")args = vars(ap.parse_args())print("[INFO] loading dataset...")conf = Conf(args["conf"])(data, labels) = dataset.load_dataset(conf["features_path"], "features")if args["hard_negatives"] > 0: print("[INFO] loading hard negatives...") (hardData,hardLabels) = dataset.load_dataset(conf["features_path"], "hard_negatives") data = np.vstack([data, hardData]) labels = np.hstack([labels, hardLabels])print("[INFO] training classifier...")model = SVC(kernel = "linear", C = conf["C"], probability = True, random_state = 42)model.fit(data, labels)print("[INFO] dumping classifier...")f = open(conf["classifier_path"], "wb")f.write(pickle.dumps(model))f.close()
11、imglab的运用
前期准备工作：生成xml文件，运用imglab生成器，选取特征轮廓。
步骤1：imglab -c 文件夹路径 生成xml文件路径 步骤2：imglab xml文件 手动框选特征区域
作用：将提取图片的边界框，并且将其特征运用svm分类。
运行指令：python train_detector.py --xml face_detector/faces_annotations.xml --detector face_detector/detector.svm
from __future__ import print_functionimport argparseimport dlibap = argparse.ArgumentParser()ap.add_argument("-x", "--xml", required = True, help = "path to input XML file")ap.add_argument("-d", "--detector", required = True, help = "path to output director")args = vars(ap.parse_args())print("[INFO] training detector....")options = dlib.simple_object_detector_training_options()options.C = 1.0options.num_threads = 4options.bei_verbose = Truedlib.train_simple_object_detector(args["xml"], args["detector"], options)print("[INFO] training accuracy:{}".format(dlib.test_simple_object_detector(args["xml"], args["detector"])))detector = dlib.simple_object_detector(args["detector"])win = dlib.image_window()win.set_image(detector)dlib.hit_enter_to_continue()
test_detector.py
作用：测试训练出来SVM线性向量
运行指令：python test_detector.py --detector face_detector/detector.svm--testing face_detector/testing
from imutils import pathsimport argparseimport dlibimport cv2ap = argparse.ArgumentParser()ap.add_argument("-d", "--detector", required = True, help = "Path to train object detector")ap.add_argument("-t", "--testing", required = True, help = "Path to directory of testing images")args = vars(ap.parse_args())detector = dlib.simple_object_detector(args["detector"])for testingPath in paths.list_images(args["testing"]): image = cv2.imread(testingPath) boxes = detector(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)) for b in boxes: (x, y, w, h) = (b.left(), b.top(), b.right(), b.bottom()) cv2.rectangle(image, (x, y), (w, h), (0, 255, 0), 2)