目标检测物体检测标注数据集object detection如何python生成带图片路径和坐标的csv文件yolov2fasterrcnn

在深度学习的物体检测中，我们需要一个csv文件来存储我们训练集图片的文件和图片里面对应物体的boundingbox的位置坐标。今天来教教生成CSV的python代码。
首先你要生成训练数据的GT图，就是训练原图里的物体的bounding box 对应位置转化成白色方块放在纯黑色图里
这个代码可以需要放入原图的路径和GT图的路径，最后生成的CSV文件是原图路径+boundingbox的位置大小及坐标。

导入各种库和对图片进行读取和处理

import cv2
import numpy as np 
import pandas as pd
import glob
import csv
import os
import pdb
import natsort
#图片的读取和预处理
#path to gt image folder
gt_image_folder = 'training_data_gt_0525_4/'   
gt_images = glob.glob(gt_image_folder + '*.jpg') + glob.glob(gt_image_folder + '*.png') +  glob.glob(gt_image_folder + '*.jpeg') + glob.glob(gt_image_folder + '*.JPEG')
 #set name of the label
label_name = 'cell2' 
gt_images = natsort.natsorted(gt_images)

生成Boundingbox 并转化成CSV字典格式

bbox_directory = 'bbox_matlab_cell2_train_0525_4'
os.makedirs(bbox_directory,exist_ok=True)
#training_path = 'original/' #Training data file path
training_path = './training_data_original_0525_4/' #Training data file path

new_dict = {'fn':[],label_name:[]}

for j,i in enumerate(gt_images):
        img = cv2.imread(i)
        ret,thresh = cv2.threshold(cv2.cvtColor(img, cv2.COLOR_RGB2GRAY),127,255,cv2.THRESH_BINARY)
        contours,hier = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
        bbox_list = []
        x = None
        for c in contours:
            x,y,w,h = cv2.boundingRect(c)
            #pdb.set_trace()
            #only keep large boxes or 0 0 0 0 (negative example) boxes
            
            if w>1 and w>1 : #suppress small bounding boxes (optional)
                #bbox_list.extend([x,y,x+w-1,y+h-1])
                bbox_list.extend([x+1,y+1,w,h]) #MATLAB convention: start from 1 instead of 0
                cv2.rectangle(img,(x,y),(x+w-1,y+h-1),(0,255,0),1)
            else: 
                continue
        #new_dict.setdefault('fn', []).append(i.replace('.png','.jpeg').replace('\\','/').replace(gt_image_folder,training_path))
        if bbox_list: #remove gt files that do not contain any bboxes
            new_dict.setdefault('fn', []).append(training_path+i.split('/')[1].split('_')[0]+'.png')
            new_dict.setdefault(label_name, []).append(' '.join (str(p) for p in bbox_list))
            #draw bounding boxes on gt images
            cv2.imwrite('{}/{}_BBox.png'.format(bbox_directory,j),img)
            #print (x,y,w,h)
            print('writing {}/{}_BBox.png...'.format(bbox_directory,j))
        else:
            #output 0,0,0,0 for empty image (negative training samples)
            bbox_list.extend([1,1,1,1])
            #这里是把原图的路径经过处理后，放入CSV里
            new_dict.setdefault('fn', []).append(training_path+i.split('/')[1].split('_')[0]+'.png')
            new_dict.setdefault(label_name, []).append(' '.join (str(p) for p in bbox_list))

由字典格式转化成CSV文件

df = pd.DataFrame(new_dict, columns=['fn',label_name])
df.to_csv('train_cell2.csv', index=False) #change the name of the output .csv file

生成的CSV文件截图