行人检测 |
您所在的位置：网站首页 › caltech怎么读 › 行人检测 |
行人检测
|
Caltech Pedestrian Dataset 数据集
加理工(caltech)提供的数据集， 该数据集主要包括 训练集+测试集：seq格式的数据；行人标签数据:vbb(video bounding box)格式的数据，该格式数据主要是数据集1中的行人bounding box。 由于我们training时需要的主要是图像格式的数据，所以需要将.seq .vbb这两个格式的数据转换为图像。 数据集下载谷歌网盘：Caltech Pedestrian Dataset 数据集下载脚本 #!/bin/bash # # Get files from Google Drive annolist=(https://drive.google.com/file/d/1EsAL5Q9FfOQls28qYmr2sO6rha1d4YVz/view?usp=sharing) for dir in ${annolist[@]};do echo ${dir} echo ${dir:32:33} URL="https://drive.google.com/u/0/uc?export=download&id=${dir:32:33}" wget --load-cookies /tmp/cookies.txt "https://drive.google.com/u/0/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate $URL -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=${dir:32:33}" -O anno.zip && rm -rf /tmp/cookies.txt unzip anno.zip done rm -rf anno.zip # USA set00-set10 setlist=(https://drive.google.com/file/d/1tPeaQr1cVmSABNCJQsd8OekOZIjpJivj/view?usp=sharing https://drive.google.com/file/d/1apo5VxoZA5m-Ou4GoGR_voUgLN0KKc4g/view?usp=sharing https://drive.google.com/file/d/1yvfjtQV6EnKez6TShMZQq_nkGyY9XA4q/view?usp=sharing https://drive.google.com/file/d/1jvF71hw4ztorvz0FWurtyCBs0Dy_Fh0A/view?usp=sharing https://drive.google.com/file/d/11Q7uZcfjHLdwpLKwDQmr5gT8LoGF82xY/view?usp=sharing https://drive.google.com/file/d/1Q0pnxM5cnO8MJJdqzMGIEryZaEKk_Un_/view?usp=sharing https://drive.google.com/file/d/1ft6clVXKdaxFGeihpth_jdBQxOIirSk7/view?usp=sharing https://drive.google.com/file/d/1-E_B3iAPQKTvkZ8XyuLcE2Lytog3AofW/view?usp=sharing https://drive.google.com/file/d/1oXCaTPOV0UYuxJJrxVtY9_7byhOLTT8G/view?usp=sharing https://drive.google.com/file/d/1f0mpL2C2aRoF8bVex8sqWaD8O3f9ZgfR/view?usp=sharing https://drive.google.com/file/d/18TvsJ5TKQYZRlj7AmcIvilVapqAss97X/view?usp=sharing ) for setdir in ${setlist[@]};do echo ${setdir} echo ${setdir:32:33} URL="https://drive.google.com/u/0/uc?export=download&id=${setdir:32:33}" wget --load-cookies /tmp/cookies.txt "https://drive.google.com/u/0/uc?export=download&confirm=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate $URL -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')&id=${setdir:32:33}" -O set.tar && rm -rf /tmp/cookies.txt tar -xvf set.tar done rm -rf set.tar
脚本：seq2jpg.py #!/usr/bin/env python # encoding: utf-8 ''' @Author : pentiumCM @Email : [email protected] @Software: PyCharm @File : seq_process.py @Time : 2020/9/7 21:44 @desc : Caltech数据集 seq 类型文件数据集处理 ''' # Deal with .seq format for video sequence # The .seq file is combined with images, # so I split the file into several images with the image prefix # "\xFF\xD8\xFF\xE0\x00\x10\x4A\x46\x49\x46". import os.path import fnmatch import shutil def open_save(file, savepath): """ read .seq file, and save the images into the savepath :param file: .seq文件路径 :param savepath: 保存的图像路径 :return: """ # 读入一个seq文件，然后拆分成image存入savepath当中 f = open(file, 'rb+') # 将seq文件的内容转化成str类型 string = f.read().decode('latin-1') # splitstring是图片的前缀，可以理解成seq是以splitstring为分隔的多个jpg合成的文件 splitstring = "\xFF\xD8\xFF\xE0\x00\x10\x4A\x46\x49\x46" # split函数做一个测试,因此返回结果的第一个是在seq文件中是空，因此后面省略掉第一个 """ >>> a = ".12121.3223.4343" >>> a.split('.') ['', '12121', '3223', '4343'] """ # split .seq file into segment with the image prefix strlist = string.split(splitstring) f.close() count = 0 # delete the image folder path if it exists # if os.path.exists(savepath): # shutil.rmtree(savepath) # create the image folder path # if not os.path.exists(savepath): # os.makedirs(savepath) # deal with file segment, every segment is an image except the first one for img in strlist: filename = str(count) + '.jpg' filenamewithpath = savepath + '_' + filename #os.path.join(savepath, filename) # abandon the first one, which is filled with .seq header if count > 0: i = open(filenamewithpath, 'wb+') i.write(splitstring.encode('latin-1')) i.write(img.encode('latin-1')) i.close() count += 1 if __name__ == "__main__": rootdir = "/workspace/dataset/zfjuan/data/CaltechPedestrian/" saveroot = "/workspace/dataset/zfjuan/data/CaltechPedestrian/caltech_voc/JPEGImages" # walk in the rootdir, take down the .seq filename and filepath for parent, dirnames, filenames in os.walk(rootdir): for filename in filenames: # check .seq file with suffix # fnmatch 全称是 filename match，主要是用来匹配文件名是否符合规则的 if fnmatch.fnmatch(filename, '*.seq'): # take down the filename with path of .seq file thefilename = os.path.join(parent, filename) # create the image folder by combining .seq file path with .seq filename parent_path = parent parent_path = parent_path.replace('\\', '/') thesavepath = saveroot + '/' + parent_path.split('/')[-1] + '_' + filename.split('.')[0] print("Filename=" + thefilename) print("Savepath=" + thesavepath) open_save(thefilename, thesavepath) vbb转voc xml脚本：vbb2voc.py # -*- coding:utf-8 -*- # -*- coding:utf-8 -*- import os, glob from scipy.io import loadmat from collections import defaultdict import numpy as np from lxml import etree, objectify def vbb_anno2dict(vbb_file, cam_id): filename = os.path.splitext(os.path.basename(vbb_file))[0] # 定义字典对象annos annos = defaultdict(dict) vbb = loadmat(vbb_file) # object info in each frame: id, pos, occlusion, lock, posv objLists = vbb['A'][0][0][1][0] objLbl = [str(v[0]) for v in vbb['A'][0][0][4][0]] # 可查看所有类别 # person index person_index_list = np.where(np.array(objLbl) == "person")[0] # 只选取类别为‘person’的xml for frame_id, obj in enumerate(objLists): if len(obj) > 0: frame_name = str(cam_id) + "_" + str(filename) + "_" + str(frame_id+1) + ".jpg" annos[frame_name] = defaultdict(list) annos[frame_name]["id"] = frame_name annos[frame_name]["label"] = "person" for id, pos, occl in zip(obj['id'][0], obj['pos'][0], obj['occl'][0]): id = int(id[0][0]) - 1 # for matlab start from 1 not 0 if not id in person_index_list: # only use bbox whose label is person continue pos = pos[0].tolist() occl = int(occl[0][0]) annos[frame_name]["occlusion"].append(occl) annos[frame_name]["bbox"].append(pos) if not annos[frame_name]["bbox"]: del annos[frame_name] print(annos) return annos def instance2xml_base(anno, bbox_type='xyxy'): """bbox_type: xyxy (xmin, ymin, xmax, ymax); xywh (xmin, ymin, width, height)""" assert bbox_type in ['xyxy', 'xywh'] E = objectify.ElementMaker(annotate=False) anno_tree = E.annotation( E.folder('VOC2014_instance/person'), E.filename(anno['id']), E.source( E.database('Caltech pedestrian'), E.annotation('Caltech pedestrian'), E.image('Caltech pedestrian'), E.url('None') ), E.size( E.width(640), E.height(480), E.depth(3) ), E.segmented(0), ) for index, bbox in enumerate(anno['bbox']): bbox = [float(x) for x in bbox] if bbox_type == 'xyxy': xmin, ymin, w, h = bbox xmax = xmin+w ymax = ymin+h else: xmin, ymin, xmax, ymax = bbox E = objectify.ElementMaker(annotate=False) anno_tree.append( E.object( E.name(anno['label']), E.bndbox( E.xmin(int(xmin)), E.ymin(int(ymin)), E.xmax(int(xmax)), E.ymax(int(ymax)) ), E.difficult(0), E.occlusion(anno["occlusion"][index]) ) ) return anno_tree def parse_anno_file(vbb_inputdir, vbb_outputdir): # annotation sub-directories in hda annotation input directory assert os.path.exists(vbb_inputdir) sub_dirs = os.listdir(vbb_inputdir) # 对应set00,set01... for sub_dir in sub_dirs: print("Parsing annotations of camera: ", sub_dir) cam_id = sub_dir # 获取某一个子set下面的所有vbb文件 vbb_files = glob.glob(os.path.join(vbb_inputdir, sub_dir, "*.vbb")) for vbb_file in vbb_files: # 返回一个vbb文件中所有的帧的标注结果 annos = vbb_anno2dict(vbb_file, cam_id) if annos: # 组成xml文件的存储文件夹，形如“/Users/chenguanghao/Desktop/Caltech/xmlresult/” vbb_outdir = vbb_outputdir # 如果不存在 vbb_outdir if not os.path.exists(vbb_outdir): os.makedirs(vbb_outdir) for filename, anno in sorted(annos.items(), key=lambda x: x[0]): if "bbox" in anno: anno_tree = instance2xml_base(anno) outfile = os.path.join(vbb_outdir, os.path.splitext(filename)[0]+".xml") print("Generating annotation xml file of picture: ", filename) # 生成最终的xml文件，对应一张图片 etree.ElementTree(anno_tree).write(outfile, pretty_print=True) def visualize_bbox(xml_file, img_file): import cv2 tree = etree.parse(xml_file) # load image image = cv2.imread(img_file) origin = cv2.imread(img_file) # 获取一张图片的所有bbox for bbox in tree.xpath('//bndbox'): coord = [] for corner in bbox.getchildren(): coord.append(int(float(corner.text))) print(coord) cv2.rectangle(image, (coord[0], coord[1]), (coord[2], coord[3]), (0, 0, 255), 2) # visualize image cv2.imshow("test", image) cv2.imshow('origin', origin) cv2.waitKey(0) def main(): vbb_inputdir = "data/CaltechPedestrian/annotations" vbb_outputdir = "data/CaltechPedestrian/caltech_voc/Annotations" parse_anno_file(vbb_inputdir, vbb_outputdir) if __name__ == "__main__": main() print("Success!") 数据筛选很多xml文件内标注的person由于目标太小，导致极其不清晰，应该将其去除； 同时，删掉无person目标或目标小于预设面积的图片； import xml.etree.ElementTree as ET import os import shutil space = 40*70 xml_path = "data/CaltechPedestrian/caltech_voc/Annotations" jpg_path = "data/CaltechPedestrian/caltech_voc/JPEGImages" save_xml_path = "data/CaltechPedestrian/caltech_voc/Annotations_filtered" save_jpg_path = "data/CaltechPedestrian/caltech_voc/JPEGImages_filtered" def filter_xml(): for file_name in os.listdir(xml_path): file_path = os.path.join(xml_path, file_name) print(file_path) in_file = open(file_path) tree = ET.parse(in_file) # ET是一个xml文件解析库，ET.parse（）打开xml文件。parse--"解析" root = tree.getroot() # 获取根节点 write_flag = False for obj in root.findall('object'): # 找到根节点下所有“object”节点 bbox = obj.find('bndbox') x1 = int(bbox.find('xmin').text) y1 = int(bbox.find('ymin').text) x2 = int(bbox.find('xmax').text) y2 = int(bbox.find('ymax').text) if (x2-x1)*(y2-y1) >= space: write_flag = True if write_flag: tree.write(os.path.join(save_xml_path, file_name)) print("save xml file: {}".format(os.path.join(save_xml_path, file_name))) jpg_name = file_name.replace('xml', 'jpg') old_path = os.path.join(jpg_path, jpg_name) new_path = os.path.join(save_jpg_path, jpg_name) shutil.copyfile(old_path, new_path) print("save jpg file: {}".format(new_path)) if __name__ == '__main__': filter_xml() |
【本文地址】
今日新闻 |
推荐新闻 |