How do I run the mentioned abandoned object detection code provided as example model in a .m file?

5 次查看（过去 30 天）
Mahim Alam Khan
Mahim Alam Khan 2017-12-27
回答： Mahim Alam Khan 2018-3-20
%%Abandoned Object Detection
% This demo tracks objects at a train station and determines which ones
% remain stationary. Abandoned objects in public areas concern authorities
% since they might pose a security risk. Algorithms, such as the one used
% in this demo, can be used to assist security officers monitoring live
% surveillance video by directing their attention to a potential area of
% interest.
%%Introduction
% This demo illustrates how to use the BlobAnalysis component to identify
% objects and track them. The demo implements this algorithm using the
% following steps:
  • Eliminate video areas that are unlikely to contain abandoned objects by extracting a region of interest (ROI).
  • Perform video segmentation using background subtraction.
  • Calculate object statistics using the BlobAnalysis component.
  • Track objects based on their area and centroid statistics.
  • Visualize the results.
status = viplibgetdemodata('viptrain.avi');
if ~status
displayEndOfDemoMessage(mfilename);
return;
end
%%Initialization
% Use these next sections of code to initialize the required variables and
% components.
%
% Rectangular ROI [Row coordinate of top-left corner, column coordinate of
% top-left corner, height, width]
roi = [80 100 240 360];
% Maximum number of objects to track
maxNumObj = 200;
% Number of frames that an object must remain stationary before an alarm is
% raised
alarmCount = 45;
% Maximum number of frames that an abandoned object can be hidden before it
% is no longer tracked
maxConsecutiveMiss = 4;
% Maximum allowable change in object area in percent
areaChangeFraction = 15;
% Maximum allowable change in object centroid in percent
centroidChangeFraction = 20;
% Minimum ratio between the number of frames in which an object is detected
% and the total number of frames, for that object to be tracked.
minPersistenceRatio = 0.7;
% Offsets for drawing bounding boxes in original input video
PtsOffset = int32(repmat([roi(1); roi(2); 0 ; 0],[1 maxNumObj]));
Create a FromMultimediaFile component to read video from a file.
hVideoSrc = viplib.MultimediaFileReader;
hVideoSrc.FileName = 'viptrain.avi';
hVideoSrc.VideoOutputMode = 'single';
Create a ColorSpaceConversion component to convert the RGB image to Y'CbCr format.
hColorConv = viplib.ColorSpaceConverter;
hColorConv.Conversion = 'R''G''B'' to Y''CbCr';
Create an AutoThreshold component to convert an intensity image to a binary image.
hAutothreshold = viplib.Autothresholder;
hAutothreshold.ScaleThresholdOption = ...
'Specify threshold scale factor via property';
hAutothreshold.ThresholdScaleFactor = 1.3;
Create a Closing component to fill in small gaps in the detected objects.
hClosing = viplib.MorphologicalClose;
hClosing.NeighborhoodOrStrel = strel('square',5);
Create a BlobAnalysis component to find the area, centroid, and bounding box of the objects in the video.
hBlob = viplib.BlobAnalysis;
hBlob.MaxNumBlobs = maxNumObj;
hBlob.ReturnNumBlobs = true;
hBlob.MinBlobAreaProperty = true;
hBlob.MinBlobArea = 100;
hBlob.MaxBlobAreaProperty = true;
hBlob.MaxBlobArea = 2500;
hBlob.ExcludeBorderBlobs = true;
Create a DrawShapes component to draw rectangles around the abandoned objects.
hDrawRectangles1 = viplib.ShapeInserter;
hDrawRectangles1.FillShapes = true;
hDrawRectangles1.FillValueOption = 'Specify via property';
hDrawRectangles1.Value = [1 0 0];
hDrawRectangles1.Opacity = 0.5;
Create an InsertText component to display the number of objects in the video.
hDisplayCount = viplib.TextInserter;
hDisplayCount.Text = '%4d';
hDisplayCount.ColorValue = [1 1 1];
hDisplayCount.Font = 'LucidaTypewriterRegular';
Create a movie player component to display the video with the abandoned objects highlighted.
hAbandonedObjects = viplib.VideoPlayer;
hAbandonedObjects.WindowCaption = 'Abandoned Objects';
hAbandonedObjects.WindowPosition = [10 300 roi(4)+25 roi(3)+25];
Create a DrawShapes component to draw rectangles around all the detected objects in the video.
hDrawRectangles2 = viplib.ShapeInserter;
hDrawRectangles2.BorderValueOption = 'Specify via property';
hDrawRectangles2.Value = [0 1 0];
Create a DrawShapes component to draw a rectangle around the region of interest.
hDrawBBox = viplib.ShapeInserter;
hDrawBBox.BorderValueOption = 'Specify via property';
hDrawBBox.Value = [1 1 0];
Create a movie player component to display the video with all the identified objects highlighted.
hAllObjects = viplib.VideoPlayer;
hAllObjects.WindowPosition = [45+roi(4) 300 roi(4)+25 roi(3)+25];
hAllObjects.WindowCaption = 'All Objects';
Create a DrawShapes component to draw rectangles around all the identified objects in the segmented video.
hDrawRectangles3 = viplib.ShapeInserter;
hDrawRectangles3.BorderValueOption = 'Specify via property';
hDrawRectangles3.Value = [0 1 0];
Create a movie player component to display the segmented video.
hThresholdDisplay = viplib.VideoPlayer;
hThresholdDisplay.WindowPosition = ...
[80+2*roi(4) 300 roi(4)-roi(2)+25 roi(3)-roi(1)+25];
hThresholdDisplay.WindowCaption = 'Threshold';
%%Stream processing loop
% Create a processing loop to perform abandoned object detection on the input
% video. This loop uses the components you instantiated above.
firsttime = true;
while ~isDone(hVideoSrc)
Im = run(hVideoSrc);
% Select the region of interest from the original video
OutIm = Im(roi(1):end, roi(2):end, :);
YCbCr = run(hColorConv, OutIm);
CbCr = complex(YCbCr(:,:,2), YCbCr(:,:,3));
% Store the first video frame as the background
if firsttime
firsttime = false;
BkgY = YCbCr(:,:,1);
BkgCbCr = CbCr;
end
SegY = run(hAutothreshold, abs(YCbCr(:,:,1)-BkgY));
SegCbCr = abs(CbCr-BkgCbCr) > 0.05;
% Fill in small gaps in the detected objects
Segmented = run(hClosing, SegY | SegCbCr);
% Perform blob analysis
[Area, Centroid, BBox, Count] = run(hBlob, Segmented);
% Call the helper function that tracks the identified objects and
% returns the bounding boxes and the number of the abandoned objects.
[OutCount, OutBBox] = viplibobjtracker(Area, Centroid, BBox, Count,...
areaChangeFraction, centroidChangeFraction, maxConsecutiveMiss, ...
minPersistenceRatio, alarmCount);
% Display the abandoned object detection results
Imr = run(hDrawRectangles1, Im, OutBBox+PtsOffset);
Imr(1:15,1:30,:) = 0;
Imr = run(hDisplayCount, Imr, OutCount);
run(hAbandonedObjects, Imr);
% Display all the detected objects
Imr = run(hDrawRectangles2, Im, BBox+PtsOffset);
Imr(1:15,1:30) = 0;
Imr = run(hDisplayCount, Imr, OutCount);
Imr = run(hDrawBBox, Imr, roi);
run(hAllObjects, Imr);
% Display the segmented video
SegIm = run(hDrawRectangles3, repmat(Segmented,[1 1 3]), BBox);
run(hThresholdDisplay, SegIm);
end
%%Close
% Here you call the close method on the components to close any open files
% and devices.
close(hVideoSrc);
%%Summary
% In the Abandoned Objects window, you can see that the demo detected the
% abandoned object located on the bench. It marks the location of this
% object with a red rectangle.
%%Appendix
% The following helper function is used in this demo.
%
% * <matlab:edit('viplibobjtracker.m') viplibobjtracker.m>
displayEndOfDemoMessage(mfilename)
Please help me out..!! I am getting errors while running the above toolbox example script from matlab. Maybe I need to do something else rather than pasting whole script and then running it. Maybe I need to do something else with this line in code- "Create a FromMultimediaFile component to read video from a file."

请先登录，再回答此问题。

回答（4 个）

hemant vyas
hemant vyas 2018-1-5
the error in this this code is "Undefined function 'viplibgetdemodata' for input arguments of type 'char'.
Error in Abandoned (line 23) status = viplibgetdemodata('viptrain.mp4');"Now can anyone help me to solve this error.
  2 个评论
Dhaarani Singaravelu
Dhaarani Singaravelu 2018-1-5
the error in this this code is "Undefined function 'viplibgetdemodata' for input arguments of type 'char'.
Error in Abandoned (line 23) status = viplibgetdemodata('viptrain.mp4');"Now can anyone help me to solve this error.
How to solve this error??

请先登录，再进行评论。

Walter Roberson
Walter Roberson 2018-1-30
Add a file viplibgetdemodata.m with content
function foundit = viplibgetdemodata(filename)
foundit = true;
This will get you past this first problem.
hemant vyas
hemant vyas 2018-3-20
sir i am getting same error till now can you please provide me the correct code for abandoned object detection
  1 个评论
Walter Roberson
Walter Roberson 2018-3-20
That code dates from about 2006 and relies upon a number of routines that have changed a fair bit in MATLAB. It is unlikely that anyone will volunteer to rewrite the code. You should write your own code or use an old version of MATLAB.

请先登录，再进行评论。

Mahim Alam Khan
Mahim Alam Khan 2018-3-20
@Hemant Vyas reach me out at 9khanmahim@gmail.com

类别

在 Help Center 和 File Exchange 中查找有关 Computer Vision with Simulink 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by