save tracking results into csv file for oxuva long-term tracking dataset (from txt to csv)
save tracking results into csv file for oxuva long-term tracking dataset (from txt to csv)
2019-10-25 09:42:03
Official Tools: OxUvA long-term tracking benchmark [ECCV'18] [Github]
Project page: https://oxuva.github.io/long-term-tracking-benchmark/
import os
import numpy as np
import cv2
import time
import oxuva
import pdb # export PYTHONPATH="/home/wangxiao/THOR/long-term-tracking-benchmark-master/python:$PYTHONPATH" # txtPath = '/home/wangxiao/THOR/benchmark/results/OXUVA/Tracker/'
# txtFiles = os.listdir(txtPath) # csv_path = './oxuva_csv_results/' # for index in range(len(txtFiles)): # txtName = txtFiles[index]
# pointPosition = txtName.find('.')
# videoName = txtName[:pointPosition] # preds = np.loadtxt(txtPath + txtName, delimiter=',')
# preds = preds.tolist() # spacePosition = txtName.find('_')
# if spacePosition:
# obj =
# else:
# obj = txtName[spacePosition:spacePosition+] # preds_file = os.path.join(csv_path, '{}_{}.csv'.format(videoName, obj)) # tmp_preds_file = os.path.join(csv_path, '{}_{}.csv.tmp'.format(videoName, obj))
# with open(tmp_preds_file, 'w', encoding='utf-8-sig') as fp:
# pdb.set_trace() # oxuva.dump_predictions_csv(videoName, obj, preds, fp)
# os.rename(tmp_preds_file, preds_file) # pdb.set_trace() import json
import pdb
import cv2
import os
import pandas as pd
resultpath= '/home/wangxiao/tracking_results_oxuva/'
videopath="/home/wangxiao/dataset/OxUvA/images/test/"
videos=os.listdir(videopath)
txtFiles = os.listdir(resultpath) for i in range(len(videos)):
txtName = videos[i] + "_oxuva-baseline.txt"
preds = np.loadtxt(resultpath + txtName, delimiter=',') print("==>> txtName: ", txtName)
xmin=[]
xmax=[]
ymin=[]
ymax=[]
video_ids=[]
obj_ids=[]
frame_nums=[]
presents=[]
scores=[]
video_id=videos[i][:]
if(len(videos[i])==):
obj_id='obj0000'
elif(videos[i][-]==''):
obj_id='obj0001'
else:
obj_id='obj0002'
present='True'
score=0.5
# l=result['res'] imgs=os.listdir(videopath+videos[i]+'/')
imgs = np.sort(imgs)
# pdb.set_trace() image=cv2.imread(videopath+videos[i]+'/'+imgs[])
imgh=image.shape[]
imgw=image.shape[] for j in range(len(imgs)): # pdb.set_trace() x=preds[j][]
y=preds[j][]
w=preds[j][]
h=preds[j][] ## results relative to original image size.
x1=x/imgw
x2=(x+w)/imgw
y1=y/imgh
y2=(y+h)/imgh x1=round(x1,)
x2=round(x2,)
y1=round(y1,)
y2=round(y2,) frame=imgs[j][:] if(frame==''):
frame_num=
else:
frame_num=frame.lstrip('') xmin.append(x1)
xmax.append(x2)
ymin.append(y1)
ymax.append(y2)
video_ids.append(video_id)
obj_ids.append(obj_id)
frame_nums.append(frame_num)
presents.append(present)
scores.append(score) # pdb.set_trace() dataframe=pd.DataFrame({'video_id':video_ids,'object_id':obj_ids,'frame_num':frame_nums,'present':presents,\
'score':scores,'xmin':xmin,'xmax':xmax,'ymin':ymin,'ymax':ymax})
savepath='./oxuva_csv_results/' +videos[i][:]+'_'+obj_id+'.csv'
columns=['video_id','object_id','frame_num','present','score','xmin','xmax','ymin','ymax'] dataframe.to_csv(savepath,index=False,columns=columns,header=None) # pdb.set_trace()
========= Results
==
save tracking results into csv file for oxuva long-term tracking dataset (from txt to csv)的更多相关文章
- 关于视觉跟踪中评价标准的相关记录(The Evaluation of Visual Tracking Results on OTB-100 Dataset)
关于视觉跟踪中评价标准的相关记录(The Evaluation of Visual Tracking Results on OTB-100 Dataset) 2018-01-22 21:49:17 ...
- ogr2ogr: Export Well Known Text (WKT) for one feature to a CSV file
Perhaps you’re looking for this? ogr2ogr -f “CSV” “E:\4_GIS\NorthArkCartoData\UnitedStates\MO_wkt” “ ...
- C# - CSV file reader
// ------------------------------------------------------------------------------------------------- ...
- SQL SERVER – Import CSV File Into SQL Server Using Bulk Insert – Load Comma Delimited File Into SQL Server
CSV stands for Comma Separated Values, sometimes also called Comma Delimited Values. Create TestTabl ...
- Matlab Code for Visualize the Tracking Results of OTB100 dataset
Matlab Code for Visualize the Tracking Results of OTB100 dataset 2018-11-12 17:06:21 %把所有tracker的结果画 ...
- [PowerShell Utils] Create a list of virtual machines based on configuration read from a CSV file in Hyper-V
Hello everyone, this is the third post of the series. . Background =============== In my solution, ...
- Qt Read and Write Csv File
This page discusses various available options for working with csv documents in your Qt application. ...
- HBase import tsv,csv File
一,HBase中创建table 表(liupeng:test)并创建 info ,contect 列簇 hbase(main):258:0> create "liupeng:Test& ...
- Python: Write UTF-8 characters to csv file
To use codecs, we can write UTF-8 characters into csv file import codecs with open('ExcelUtf8.csv', ...
随机推荐
- powershell 远程下载并执行
远程下载文件到本地并执行cmd.exe /c powershell.exe -ExecutionPolicy bypass -noprofile -windowstyle hidden (new-ob ...
- 为什么MES系统要定制化?看这三家汽车供应商的苦恼
很多企业对于为什么要对MES系统进行选择和定制化很不理解,今天,小编通过一个故事给大家进行阐述—— 故事背景: 汽车电子行业的三家企业A,B,C. A是整车厂一级供应商,主要产品为汽车电子配电盒. B ...
- 面试题:什么叫B树
B是balanced的意思 是在二叉查找树 树的基础上增加了平衡的性质 导致它不是 二叉树了,变成了多叉树,但是叉几路又有了限制 否则怎么平衡呢 一棵m阶B树(balanced tree o ...
- CSS 样式的使用方式、选择器
在html中使用css的三种方式: 1.行内样式:同过元素的style属性来设置 <p style="font-size:20px; color:red">hello& ...
- java list map在初始化的时候添加元素
List<String> list = new ArrayList<String>(){{ add("First Object"); add("S ...
- Prometheus学习笔记(4)什么是pushgateway???
目录 一.pushgateway介绍 二.pushgateway的安装运行和配置 三.自定义脚本发送pushgateway 四.使用pushgateway的优缺点 一.pushgateway介绍 pu ...
- windows10安装redis
下载 github上下载最新(或者你需要的版本)的redis安装包,下载地址如下: https://github.com/microsoftarchive/redis/releases 打开点击版本号 ...
- 源码查看Thread.interrupted()和Thread.currentThread().isInterrupted()区别
JAVA线程状态.线程START方法源码.多线程.JAVA线程池.如何停止一个线程等多线程问题 这两个方法有点容易记混,这里就记录一下源码. Thread.interrupted()和Thread.c ...
- GC线程是不是守护线程
是 线程的话分为守护线程和非守护线程(即用户线程) 只要当前JVM实例中尚存在任何一个非守护线程没有结束,守护线程就全部工作; 只有当最后一个非守护线程结束时,守护线程随着JVM一同结束工作,守护线程 ...
- 201671010426 孙锦喆 实验十四 团队项目评审&课程学习总结
徐明锦 徐明锦 2 95 2019-06-30T14:54:00Z 2019-06-30T14:54:00Z 9 608 3472 28 8 4072 14.00 Clean Clean false ...