淄博网站客户,网站怎么做下拉刷新页面数据,久久建筑服务网,商城网站开发代码案例工业中#xff0c;机器视觉物体分拣时#xff0c;需要制作#xff0c;数据集#xff0c;那么#xff0c;一般情况下#xff0c;可以选择几个物体的几张图片#xff0c;或者视频#xff0c;将待识别的物体的掩模扣取出来#xff0c;随机的贴在 传送带背景中#xff0c…工业中机器视觉物体分拣时需要制作数据集那么一般情况下可以选择几个物体的几张图片或者视频将待识别的物体的掩模扣取出来随机的贴在 传送带背景中并批量自动的写成 VOC 数据集 使用图像处理的技术手段将上述的目标的掩模扣取出来或者使用 ps 的技术扣取掩模均可。
# -*- coding : utf-8 -*-
# Data : 2019-08-16
# Author : xm
# Email :
# File : image_process.py
# Desctiption: 求取图像中物体的边界矩形import numpy as np
import cv2
import osdef calculatBoundImage(src_Image):求取图像中物体的边界矩形框:param src_Image: 输出的源图像:return: 返回图像中的物体边界矩形tmp_image src_Image.copy()#print(tmp_image)if (len(tmp_image.shape) 3):tmp_image cv2.cvtColor(tmp_image, cv2.COLOR_BGR2GRAY)# 自适应阈值进行二值化thresh_image cv2.adaptiveThreshold(tmp_image, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 71, 10)thresh_image cv2.morphologyEx(thresh_image, cv2.MORPH_CLOSE, cv2.getStructuringElement(cv2.MORPH_RECT, (25, 25)))# 寻找最外层轮廓contours_ls, hierarchy cv2.findContours(thresh_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_TC89_KCOS)pnt_cnt_ls np.array([tmp_contour.shape[0] for tmp_contour in contours_ls])contour_image src_Image.copy()contours_idx np.argmax(pnt_cnt_ls)contour_image cv2.drawContours(contour_image, contours_ls, contours_idx, (0, 0, 255))longest_contour contours_ls[contours_idx]countour_image_gray np.zeros(src_Image.shape, dtypenp.uint8)countour_image_gray cv2.drawContours(countour_image_gray, contours_ls, contours_idx, (1, 1, 1), cv2.FILLED)obj_image src_Image * countour_image_graybound_box cv2.boundingRect(longest_contour)return bound_box, contour_image, obj_imagedef rotateImage(src_Image, angle_deg, rotate_centerNone):对目标图像进行旋转:param src_Image: 输入的源图像:param angle_deg: 旋转的角度:param rotate_center: 旋转的中心:return: 旋转后的图片(h, w) src_Image.shape[:2]if rotate_center is None:rotate_center ((w -1) / 2, (h - 1) / 2)rot_mat cv2.getRotationMatrix2D(rotate_center, angle_deg, 1.0)rot_iamge cv2.warpAffine(src_Image, rot_mat, (w, h))return rot_iamgedef VideotoImage(video_file, folder_path):数据的视频保存为提取之后的物体图:param video_file: 视频文件:param folder_path: 保存图片的路径:return: 保存的图片video_cap cv2.VideoCapture(video_file)image_idx 2000while True:ret, frame video_cap.read()if (frame is None):continuebound_box, contour_image, obj_image calculatBoundImage(frame)bound_thres 4500if (bound_box[2] bound_thres or bound_box[3] bound_thres):continuecontour_image cv2.rectangle(contour_image, (bound_box[0], bound_box[1]),(bound_box[0] bound_box[2],bound_box[1] bound_box[3]), (225, 0, 0), thickness2)#cv2.imshow(frame, contour_image)image_name str(image_idx).zfill(6) .jpgimage_idx 1if image_idx % 2 0:cv2.imwrite(folder_path image_name, obj_image)cv2.waitKey(25)if 0xFF cv2.waitKey(5) 27:breakvideo_cap.release()def BatchImageProcess(image_path, folder_path):批量图片物体提取背景为黑色:param Image_path: 图片的路径:param folder_path: 图像处理之后的保存路径:return: 保存的图片image_file_list os.listdir(image_path)# 获取物体图像的文件名image_idx 0for image_name in range(len(image_file_list)):obj_image_path image_path image_file_list[image_idx]src_Image cv2.imread(obj_image_path)bound_box, contour_image, obj_image calculatBoundImage(src_Image)bound_thres 4500if (bound_box[2] bound_thres or bound_box[3] bound_thres):continuecontour_image cv2.rectangle(contour_image, (bound_box[0], bound_box[1]), (bound_box[0] bound_box[2], bound_box[1] bound_box[3]), (225, 0, 0), thickness2)#cv2.imshow(frame, contour_image)image_name str(image_idx).zfill(6) .jpgcv2.imwrite(folder_path image_name, obj_image)image_idx 1def main():image_path /home/xm/workspace/ImageProcess/tmp/circle/folder_path /home/xm/workspace/ImageProcess/tmp/BatchImageProcess(image_path, folder_path)# def main():
# src_Image cv2.imread(./Images/00001.png)
# bound_box, contour_image, obj_image calculatBoundImage(src_Image)
# print(bound_box, bound_box)
#
# cv2.namedWindow(input image, cv2.WINDOW_AUTOSIZE)
# cv2.imshow(input image, contour_image)
#
#
# # 一般源图像进行旋转再提取轮廓
# rot_image rotateImage(src_Image, 20, rotate_centerNone)
# cv2.imshow(obj image, obj_image)
# cv2.imshow(rot image, rot_image)
# cv2.waitKey(0)
#
# # vide_file ./Images/blue_1_82.mp4
# # folder_path ./results/
# #
# # VideotoImage(vide_file, folder_path)if __name__ __main__:main() # -*- coding : utf-8 -*-
# Data : 2019-08-17
# Author : xm
# Email :
# File : ImageDataSetGeneration.py
# Desctiption: 生成物体分类的图像数据集import numpy as np
import cv2
import os
from lxml import etree, objectifydef rotateImage(src_image, rotate_deg):对图像进行旋转:param src_image: 输入源图像:param rotate_dog: 旋转角度:return: 旋转后的图像img_h, img_w src_image.shape[0:2]rotate_mat cv2.getRotationMatrix2D((img_w / 2.0, img_h / 2.0), rotate_deg, 1.0)dst_image cv2.warpAffine(src_image, rotate_mat, (img_w, img_h))return dst_imagedef calculateBoundImage(src_image):求图像中物体的边界矩形:param src_image: 源图像:return: 图像中物体的边界矩形、轮廓图、目标图像tmp_image src_image.copy()if len(tmp_image.shape) 3:tmp_image cv2.cvtColor(tmp_image, cv2.COLOR_BGR2GRAY)ret, thresh_images cv2.threshold(tmp_image, 0, 255,cv2.THRESH_BINARY)contours_ls, _ cv2.findContours(thresh_images, cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)all_points np.concatenate(contours_ls, axis0)bound_box cv2.boundingRect(all_points)return bound_boxdef randomMoveObjectInImage(src_image, src_bound_box):将物体在图像中随机摆放:param src_image: 背景图 COCO/VOC:param src_bound_box: 原始边界框:return: 相机旋转后的边界框x, y, w, h src_bound_boximg_h, img_w src_image.shape[0:2]img_h - himg_w - wrandom_array np.random.uniform(0.0, 1.0, 2)bbox_x np.floor(img_w * random_array[0])bbox_y np.floor(img_h * random_array[1])return np.array([bbox_x, bbox_y, w, h])def calculateIOU(bound_box_1, bound_box_2):计算两个 bound_box 之间的 IOU:param bound_box_1: 边界框 1, shape [x, y, w, h]:param bound_box_2: 边界框 2shape [x, y, w, h]:return: 两个 bound box 之间的 IOU 值min_xy np.maximum(bound_box_1[0:2], bound_box_2[0:2])max_xy np.minimum(bound_box_1[0:2] bound_box_2[2:4],bound_box_2[0:2] bound_box_2[2:4])delta_xy max_xy - min_xyintersection_area delta_xy[0] * delta_xy[1]if (intersection_area 0):returnbox_area_1 bound_box_1[2] * bound_box_1[3]box_area_2 bound_box_2[2] * bound_box_2[3]union_area box_area_1 box_area_2 - intersection_areareturn intersection_area / union_areadef resizeObjectImage(src_image, max_min_box_size):对物体图像进行随机缩放:param src_image: 原始图像:param max_min_box_size: 缩放后图像中的物体的 bound box 的最大边的范围:return: 缩放后的图像src_bbox calculateBoundImage(src_image)src_bbox_max np.max(src_bbox[2:4])cur_bbox_max np.random.uniform(max_min_box_size[1], max_min_box_size[0], 1)[-1]cur_ratio cur_bbox_max / src_bbox_maxsrc_h, src_w src_image.shape[0:2]dst_h, dst_w np.floor(src_h * cur_ratio), np.floor(src_w * cur_ratio)dst_image cv2.resize(src_image, (np.int(dst_w), np.int(dst_h)))return dst_imagedef addObjectToImage(backgroup_image, obj_image, bound_box):将目标物体添加到背景图中:param backgroup_image: 背景图:param obj_image: 目标物体图:param bound_box: 边界矩形框:return: 添加了目标物体的背景图tmp_image obj_image.copy()if len(tmp_image.shape) 3:tmp_image cv2.cvtColor(tmp_image, cv2.COLOR_BGR2GRAY)mask tmp_image 5min_x, min_y, max_x, max_y bound_box[0], bound_box[1], bound_box[0] bound_box[2], bound_box[1] bound_box[3]backgroup_image[np.int(min_y):np.int(max_y), np.int(min_x):np.int(max_x)][mask] obj_image[mask]return backgroup_imagedef formImageAndlabel(background_image, obj_ls, max_min_size_ration, iou_thres):形成训练图像并生成对应的 label 列表:param background_image: 输入背景图:param obj_ls: 目标 list:param max_min_size_ration: 最大最小旋转角度:param iou_thres: IOU 阈值:return: 返训练的图像对应的 labelmax_ratio, min_ratio max_min_size_rationimage_size np.min(background_image.shape[0:2])dst_image background_image.copy()max_min_box_size [np.floor(max_ratio * image_size), np.floor(min_ratio * image_size)]label_ls []for obj_image, obj_name in obj_ls:# 对图像进行随机缩放resize_obj_image resizeObjectImage(obj_image, max_min_box_size)# 对图像进行随机旋转rotate_image rotateImage(resize_obj_image, np.random.uniform(0, 360, 1)[-1])# 多次迭代, 直到将图像平移到适当位置为止src_bbox calculateBoundImage(rotate_image)sub_obj_image rotate_image[src_bbox[1]:src_bbox[1] src_bbox[3], src_bbox[0]:src_bbox[0] src_bbox[2]]iter_cnt 100if len(label_ls) 0:iter_cnt 1for iter_idx in range(iter_cnt):dst_bbox randomMoveObjectInImage(dst_image, src_bbox)if len(label_ls) ! 0:is_fit Truefor tmp_box, tmp_obj_name in label_ls:#print(...., tmp_box)#print(, dst_bbox)IOU calculateIOU(tmp_box, dst_bbox)if (IOU is not None) and (IOU iou_thres):is_fit Falsebreakif is_fit False:continueelse:breakdst_image addObjectToImage(dst_image, sub_obj_image, dst_bbox)label_ls.append([dst_bbox, obj_name])return dst_image, label_lsdef formImageLableXML(src_image, image_file_name, label_info, label_path):生成图片的 label XML:param src_image: 原始图像:param image_file_name: 图像的文件名:param label_infor: 标签信息:param label_path: 标签的路径:return: XMLele objectify.ElementMaker(annotateFalse)anno_tree ele.annotation(ele.folder(VOC2019_xm),ele.filename(image_file_name),ele.source(ele.database(The VOC2019 Database),ele.annotation(PASCAL VOC2019),ele.image(flickr),ele.flickrid(264265361)),ele.owner(ele.flickrid(xm),ele.name(xm)),ele.size(ele.width(str(src_image.shape[0])),ele.height(str(src_image.shape[1])),ele.depth(str(src_image.shape[2]))),ele.segmented(0))for cur_box, cur_obj_name in label_info:cur_ele objectify.ElementMaker(annotateFalse)cur_tree cur_ele.object(ele.name(cur_obj_name),ele.pose(Frontal),ele.truncated(0),ele.difficult(0),ele.bndbox(ele.xmin(str(cur_box[0])),ele.ymin(str(cur_box[1])),ele.xmax(str(cur_box[0] cur_box[2])),ele.ymax(str(cur_box[1] cur_box[3]))))anno_tree.append(cur_tree)etree.ElementTree(anno_tree).write(label_path, pretty_printTrue)def main():obj_name_ls [circle, square]# 各种物体对应的图像的路径base_obj_file_name /home/xm/workspace/ImageProcess/DataSet/obj_file_name [base_obj_file_name cur_obj for cur_obj in obj_name_ls]print(obj_file_name)# 每个种类的样本数量obj_count 600# 图像中物体最大的数量image_max_obj_cnt 2# 图像中物体的 bound box 的最大尺寸点整个图像最小尺寸比例max_size_radio 0.45min_size_radio 0.20# 图像的总数image_count len(obj_name_ls) * 600# 数据集的保存路径dataset_basic_path /home/xm/workspace/ImageProcess/COCO/VOCdevkit/VOC2019/image_folder dataset_basic_path JPEGImages/#print(image_folder)label_folder dataset_basic_path Annotations/#print(label_folder)image_set_folder dataset_basic_path ImageSets/Main/#print(image_set_folder)for data_idx in range(image_count):# 获取 VOC 数据集中图像文件夹中所有文件的名称voc_folder_dir /home/xm/workspace/ImageProcess/VOCvoc_image_file_list os.listdir(voc_folder_dir)#获取物体图像的文件名列表obj_image_ls_ls []for obj_image_dir in obj_name_ls:cur_image_dir base_obj_file_name obj_image_dirobj_image_ls_ls.append(os.listdir(cur_image_dir))# 随机取一张 VOC 图做背景background_image_file voc_image_file_list[np.random.randint(0, len(voc_image_file_list), 1)[-1]]background_image_file voc_folder_dir / background_image_filebackground_image cv2.imread(background_image_file)# 随机取若干物体obj_image_name_ls []obj_cnt np.random.randint(1, image_max_obj_cnt, 1)[-1]for obj_idx in range(obj_cnt):cur_obj_idx np.random.randint(0, len(obj_image_ls_ls), 1)[-1]cur_obj_image_ls obj_image_ls_ls[cur_obj_idx]cur_obj_file cur_obj_image_ls[np.random.randint(0, len(cur_obj_image_ls), 1)[-1]]cur_obj_image cv2.imread(base_obj_file_name obj_name_ls[cur_obj_idx] / cur_obj_file)obj_image_name_ls.append([cur_obj_image, obj_name_ls[cur_obj_idx]])# 随机生成图像get_image, label_ls formImageAndlabel(background_image, obj_image_name_ls, [max_size_radio, min_size_radio], iou_thres0.05)## # 保存图像与标签cur_image_name str(data_idx).zfill(6) .jpg#print(cur_image_name)cur_label_name str(data_idx).zfill(6) .xml#print(cur_label_name)cv2.imwrite(image_folder cur_image_name, get_image)formImageLableXML(get_image, cur_image_name, label_ls, label_folder cur_label_name)for obj_bbox, obj_name in label_ls:pnt_1 tuple(map(int, obj_bbox[0:2]))pnt_2 tuple(map(int, obj_bbox[0:2]))cv2.rectangle(get_image, pnt_1, pnt_2, (0, 0, 255))print(cur_image_name)cv2.imshow(get image, get_image)cv2.waitKey(10)train_set_name train.txttrain_val_name val.txttest_set_name test.txtidx_thre np.floor(0.6 * image_count)idx_thre_ np.floor(0.8 * image_count)train_file open(image_set_folder train_set_name, w)for line_idx in range(int(idx_thre)):line_str str(line_idx).zfill(6) \ntrain_file.write(line_str)train_file.close()train_val_file open(image_set_folder train_val_name, w)for line_idx in range(int(idx_thre), int(idx_thre_)):line_str str(line_idx).zfill(6) \ntrain_val_file.write(line_str)train_val_file.close()test_file open(image_set_folder test_set_name, w)for line_idx in range(int(idx_thre_), image_count):line_str str(line_idx).zfill(6) \ntest_file.write(line_str)test_file.close()if __name__ __main__:main()
