Research Project

1.MOTA: the multiple object tracking accuracy      paper(1)附公式：(2) 2.MOTP: thei multiple object tracking precision 3.FAF: 3.GT No. of groundtruth trajectories. 4.MT MT% Mostly tracked: Percentage of GT trajectories which are covered by tracker output for more than 80% in length. 5.ML 5.ML% Mostly lost: Percentage of GT trajectories which are covered by tracker output for less than 20% in length. The smaller the better. 5. PT% Partially tracked: 1.0-MT-ML. 6.FP: false postive 7.FN: false negtive 8.IDsw  IDS ID switches: The total of No. of times that a tracked trajectory changes its matched GT identity. The smaller the better. 9.Frag Frag Fragments: The total of No. of times that a groundtruth trajectory is interrupted in tracking result. The smaller the better. 10.IoU 12. Recall (Frame-based) correctly matched objects / total groundtruth objects. 13： Precision (Frame-based) correctly matched objects / total output objects. FA/Frm...

1. reference link: https://github.com/rbgirshick/py-faster-rcnn 2. need copy the 'makefile.config'  file to the directory ''/home/uni/projects/maskrcnn/fasterrcnn/py-faster-rcnn/caffe-fast-rcnn" 3. the 4th step:     when using command:  make -j8 && make pycaffe     lhdf5 error      solution is:  change 'Makefile' file as follows: 删除--- LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_hl hdf5 增加+++ LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial 4. Run the demo " cd $FRCN_ROOT ./tools/demo.py " error (1) lack easydict solution: $  sudo pip install easydict error(2) lack cv2 solution: $ sudo apt-get install python-opencv 5. Usage:   cd $FRCN_ROOT ./experiments/scripts/faster_rcnn_alt_opt.sh [GPU_ID] [NET] [--set ...]    ./experiments/scripts/faster_rcnn_alt_opt.sh 0 VGG16 pascal_voc 6. error  and...

1.常用命令：    clear   % 清空变量窗口    clc      %　清空命令窗口 2. 创建array  x=[1 2 3]    % 1行3列的数组  x=[1;2;3]    % 3行1列的数组    x=[1 2 3] 和 x=1:3  等价  x=1:0.5:2     % 输出1 1.5 2  x=linspace(1,2,3)  % 输出 1 1.5 2 ，注意函数的参数之间是逗号隔开  x=x'       %对行向量进行转置  x=(5:2:9)'   % 输入结果为列向量  5  7  9  x=rand(4)   % 生成一个4*4的随机矩阵  x=rand(2,3)  %生成一个2*3的随机矩阵  x=zeros(2,3)  %生成一个2*3的零矩阵 3. 文件操作   save foo x    % 将变量x存入到文件foo.mat中   load foo.mat  % 从文件夹加载（读取）文件foo.mat到工作区 4.导入.txt，.png等文件     直接点击菜单栏的“导入数据” 5. 操作array(矩阵）    x=data(3,5)    %取出矩阵data的第五行、第三列元素并赋值给变量x    x=data(end, 5)  %取出矩阵data最后一行、第三列元素并赋值给变量x    x=data(end-1, 5)  %取出矩阵data倒数第二行、第三列元素并赋值给变量x    row2=data(2,:)   %取出矩阵dat...

1.Key idea: Using siamese networt to learn the non-linear embeddings of supervoxels into a euclidean space. discriminative metric learning: to learn which segments should be fused.         2.related or based on: [27]VoxNet [23]ModelNet dataset: contains a lot of CAD models. 3.new concepts: discriminative metric learning. Steps: (1) Oversegmentation using supervoxels      [34] Voxel Cloud Connectivity Segmentation(VCCS) (2)Siamese Deep Network      [27]VoxeNet (get semantic non-linear embeddings) (3)Supervoxel Clusting and Postprocessing      [59]DBSCAN

1.从服务器上拷贝文件：   rsync -avze 'ssh' uni@roboticvision1.cs.adelaide.edu.au:/home/robotvision1/Datasets/nyu_depth_v2_labled.mat  /home/uni/Datasets/ 2. Check GPU and CPU status: $  watch nvidia-smi $ top 3.(1) update code in github:    1>update    git pull https://UniLau@bitbucket.org/UniLau/mot_scripts.git master    git commit -a  -m "message 1"    2> add(new)    git add file-a file-b    git commit  -m "message 2"    git push origin master    git status 4. watch the process: $ top | grep python3 $ top | grep python3.5 watch the history process: $htop 5.  transfer files: rsync -avze 'ssh' GTsegmask_coco_2014_train a1711327@phoenix.adelaide.edu.au:/fast/users/a1711327/dataset/MSCOCO/ --progress

1. 在roboticvision1服务器上创建用户： user:uni pass:804115906 (1) ssh -X robotvision1@robotvision1.cs.adelaide.edu.au Password for robotvision1: sudo adduser uni Password for robotvision1: follow steps... %根据提示操作 (2)连接到服务器以后，在桌面左下角可以到： Connect to Server: (3) Sever Address:  sftp//:roboticvision1.cs.adelaide.edu.au ctrl+L 能看到地址 ctrl+D 新建一个bookmark 2.在终端链接服务器 ssh -X uni@roboticvision1.cs.adelaide.edu.au password:804115906 nautilus    %打开文件夹浏览器 watch nvidia -smi    %查看GPU等信息 matlab %启动服务器上的matlab程序 matlab -nodesktop  %启动服务器上的matlab程序（在terminal下运行） 二.连接phoenix服务器 sftp://phoenix.adelaide.edu.au/ user:a1711327 pass:ly804115@ Ctrl+L % 查看目录 /data/acvt Directory: sftp://phoenix.adelaide.edu.au/fast/users

1.DIY 参考： http://nbviewer.jupyter.org/github/BVLC/caffe/blob/master/examples/00-classification.ipynb 2.安装matplotlib Debian / Ubuntu :  sudo   apt-get   install   python-matplotlib 3.