在MATLAB中从java类模型中提取数据

Question

我正在编写一个脚本，允许我使用 MIJI 和 TrackMate 插件在 MATLAB 中自动分析我的图像数据集。我能够成功运行分析，但无法从 java 类 fiji.plugin.trackmate.TrackMate 中获取跟踪数据

我使用下面的代码来运行分析；

imp = ij.ImagePlus('S:\Swinderen\Adam\B1R1 16000 Frames 405 561nm HILO.tif');
    imp.show()

%----------------------------
% Create the model object now
%----------------------------

% Some of the parameters we configure below need to have
% a reference to the model at creation. So we create an
% empty model now.
model = fiji.plugin.trackmate.Model();

% Send all messages to ImageJ log window.
model.setLogger(fiji.plugin.trackmate.Logger.IJ_LOGGER)

%------------------------
% Prepare settings object
%------------------------

settings = fiji.plugin.trackmate.Settings();
settings.setFrom(imp)

% Configure detector - We use a java map
settings.detectorFactory = fiji.plugin.trackmate.detection.LogDetectorFactory();
map = java.util.HashMap();
map.put('DO_SUBPIXEL_LOCALIZATION', true);
map.put('RADIUS', 1);
map.put('TARGET_CHANNEL', 1);
map.put('THRESHOLD', 20);
map.put('DO_MEDIAN_FILTERING', true);
settings.detectorSettings = map;

% Configure tracker - We want to allow splits and fusions
settings.trackerFactory  = fiji.plugin.trackmate.tracking.sparselap.SparseLAPTrackerFactory();
settings.trackerSettings = fiji.plugin.trackmate.tracking.LAPUtils.getDefaultLAPSettingsMap(); % almost good enough
settings.trackerSettings.put('LINKING_MAX_DISTANCE', 0.3);
settings.trackerSettings.put('GAP_CLOSING_MAX_DISTANCE', 0);
settings.trackerSettings.put('SPLITTING_MAX_DISTANCE', 0);
settings.trackerSettings.put('MERGING_MAX_DISTANCE', 0);
settings.trackerSettings.put('ALLOW_GAP_CLOSING', false);
settings.trackerSettings.put('ALLOW_TRACK_SPLITTING', false);
settings.trackerSettings.put('ALLOW_TRACK_MERGING', false);

% Configure track analyzers - Later on we want to filter out tracks 
% based on their displacement, so we need to state that we want 
% track displacement to be calculated. By default, out of the GUI, 
% not features are calculated. 

% The displacement feature is provided by the TrackDurationAnalyzer.
settings.addTrackAnalyzer(fiji.plugin.trackmate.features.track.TrackDurationAnalyzer())

% Configure track filters - We want to get rid of the two immobile spots at 
% the bottom right of the image. Track displacement must be above 10 pixels.
filter2 = fiji.plugin.trackmate.features.FeatureFilter('NUMBER_OF_SPOTS', 10.0, true);
settings.addTrackFilter(filter2)


%-------------------
% Instantiate plugin
%-------------------

trackmate = fiji.plugin.trackmate.TrackMate(model, settings);

%--------
% Process
%--------

ok = trackmate.checkInput();
if ~ok
    display(trackmate.getErrorMessage())
end

ok = trackmate.process();
if ~ok
    display(trackmate.getErrorMessage())
end

检查model 时，我得到以下输出为 1x1 模型

    val =


Contains 998348 spots in total.
Contains 998348 filtered spots.

Contains 203076 tracks in total.
Contains 203076 filtered tracks.

Physical units:
  space units: pixels
  time units: frames

Spot features declared:
   - QUALITY: Quality, 'Quality' (QUALITY) - double valued.
   - POSITION_X: X, 'X' (POSITION) - double valued.
   - POSITION_Y: Y, 'Y' (POSITION) - double valued.
   - POSITION_Z: Z, 'Z' (POSITION) - double valued.
   - POSITION_T: T, 'T' (TIME) - double valued.
   - FRAME: Frame, 'Frame' (NONE) - integer valued.
   - RADIUS: Radius, 'R' (LENGTH) - double valued.
   - VISIBILITY: Visibility, 'Visibility' (NONE) - integer valued.

Edge features declared:

Track features declared:
   - TRACK_DURATION: Duration of track, 'Duration' (TIME) - double valued.
   - TRACK_START: Track start, 'T start' (TIME) - double valued.
   - TRACK_STOP: Track stop, 'T stop' (TIME) - double valued.
   - TRACK_DISPLACEMENT: Track displacement, 'Displacement' (LENGTH) - double valued.

我不确定如何访问和存储“QUALITY”和“POSITION_X”等双值数据。尝试使用model.get('QUALITY') 会返回错误；

使用 get 时出错 名称“QUALITY”不是“fiji.plugin.trackmate.Model”类实例的可访问属性

感谢任何人提供的任何指导，如果需要任何额外信息，请告诉我。

更新：

我已经能够隔离FeatureModel，并可以通过执行以下操作输出TrackFeatures；

get(model,'FeatureModel')

返回

val =

Spot features declared:
   - QUALITY: Quality, 'Quality' (QUALITY) - double valued.
   - POSITION_X: X, 'X' (POSITION) - double valued.
   - POSITION_Y: Y, 'Y' (POSITION) - double valued.
   - POSITION_Z: Z, 'Z' (POSITION) - double valued.
   - POSITION_T: T, 'T' (TIME) - double valued.
   - FRAME: Frame, 'Frame' (NONE) - integer valued.
   - RADIUS: Radius, 'R' (LENGTH) - double valued.
   - VISIBILITY: Visibility, 'Visibility' (NONE) - integer valued.

Edge features declared:

Track features declared:
   - TRACK_DURATION: Duration of track, 'Duration' (TIME) - double valued.
   - TRACK_START: Track start, 'T start' (TIME) - double valued.
   - TRACK_STOP: Track stop, 'T stop' (TIME) - double valued.
   - TRACK_DISPLACEMENT: Track displacement, 'Displacement' (LENGTH) - double valued.

如果我通过 featureModel.echo() echo FeatureModel 只声明 Track 特征而不是 Spot 特征，这是我真正需要的。

Answer 1

我遇到了同样的问题，在图片论坛中由用户 emartini 解决 https://forum.image.sc/t/problem-exporting-xml-from-trackmate-in-matlab/27242/3

需要添加的代码

import fiji.plugin.trackmate.io.TmXmlWriter  %add this ipmort

outfile=java.io.File('F:\Projects\Matlab\Test_track_july25.xml'); %%or your file name
writer = fiji.plugin.trackmate.io.TmXmlWriter(outfile);
writer.appendModel( trackmate.getModel() ) %trackmate instantiate like this before trackmate = TrackMate(model, settings)
writer.appendSettings( trackmate.getSettings() )
writer.writeToFile()