Limits...
Tool for Semiautomatic Labeling of Moving Objects in Video Sequences: TSLAB.

Cuevas C, Yáñez EM, García N - Sensors (Basel) (2015)

Bottom Line: An advanced and user-friendly tool for fast labeling of moving objects captured with surveillance sensors is proposed, which is available to the public.The labeling can be performed easily and quickly thanks to a very friendly graphical user interface that allows one to automatize many common operations.This interface also includes some semiautomatic advanced tools that simplify the labeling tasks and drastically reduce the time required to obtain high-quality results.

View Article: PubMed Central - PubMed

Affiliation: Grupo de Tratamiento de Imágenes, Universidad Politécnica de Madrid (UPM), E-28040 Madrid, Spain. ccr@gti.ssr.upm.es.

ABSTRACT
An advanced and user-friendly tool for fast labeling of moving objects captured with surveillance sensors is proposed, which is available to the public. This tool allows the creation of three kinds of labels: moving objects, shadows and occlusions. These labels are created at both the pixel level and object level, which makes them suitable to assess the quality of both moving object detection strategies and tracking algorithms. The labeling can be performed easily and quickly thanks to a very friendly graphical user interface that allows one to automatize many common operations. This interface also includes some semiautomatic advanced tools that simplify the labeling tasks and drastically reduce the time required to obtain high-quality results.

No MeSH data available.


Related in: MedlinePlus

Example of using the intelligent mode combined with the motion detection tool. The difference mask is shown in semitransparent purple. The contour drawn by the user with the intelligent mode is shown in red. The contour resultant from the combination of the motion mask and the contour manually drawn is shown in red.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541825&req=5

f8-sensors-15-15159: Example of using the intelligent mode combined with the motion detection tool. The difference mask is shown in semitransparent purple. The contour drawn by the user with the intelligent mode is shown in red. The contour resultant from the combination of the motion mask and the contour manually drawn is shown in red.

Mentions: If the mode “Intelligent” is selected in the labeling window, it is possible to select (by drawing on the display area) what parts of the mask of differences will become part of the label. Figure 8 illustrates an example where the combination of the motion detection tool and the intelligent mode provides a satisfactory labeling. As shown in this example, the mask resulting from the application of the motion detection tool (depicted in purple in the image) contains many unwanted regions (dynamic background areas and shadows). However, the intelligent mode allows one to easily select the area that we want to include as part of the label (area inside the green contour): the resulting region is the intersection between the area obtained by the motion detection strategy and the area inside the contour drawn with the intelligent pencil. After carrying out this selection, it is seen that a very good approximation to the target contour has been obtained (red contour in the image). In this example, to complete the labeling, it is only necessary to manually refine the area around the head of the moving object.


Tool for Semiautomatic Labeling of Moving Objects in Video Sequences: TSLAB.

Cuevas C, Yáñez EM, García N - Sensors (Basel) (2015)

Example of using the intelligent mode combined with the motion detection tool. The difference mask is shown in semitransparent purple. The contour drawn by the user with the intelligent mode is shown in red. The contour resultant from the combination of the motion mask and the contour manually drawn is shown in red.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541825&req=5

f8-sensors-15-15159: Example of using the intelligent mode combined with the motion detection tool. The difference mask is shown in semitransparent purple. The contour drawn by the user with the intelligent mode is shown in red. The contour resultant from the combination of the motion mask and the contour manually drawn is shown in red.
Mentions: If the mode “Intelligent” is selected in the labeling window, it is possible to select (by drawing on the display area) what parts of the mask of differences will become part of the label. Figure 8 illustrates an example where the combination of the motion detection tool and the intelligent mode provides a satisfactory labeling. As shown in this example, the mask resulting from the application of the motion detection tool (depicted in purple in the image) contains many unwanted regions (dynamic background areas and shadows). However, the intelligent mode allows one to easily select the area that we want to include as part of the label (area inside the green contour): the resulting region is the intersection between the area obtained by the motion detection strategy and the area inside the contour drawn with the intelligent pencil. After carrying out this selection, it is seen that a very good approximation to the target contour has been obtained (red contour in the image). In this example, to complete the labeling, it is only necessary to manually refine the area around the head of the moving object.

Bottom Line: An advanced and user-friendly tool for fast labeling of moving objects captured with surveillance sensors is proposed, which is available to the public.The labeling can be performed easily and quickly thanks to a very friendly graphical user interface that allows one to automatize many common operations.This interface also includes some semiautomatic advanced tools that simplify the labeling tasks and drastically reduce the time required to obtain high-quality results.

View Article: PubMed Central - PubMed

Affiliation: Grupo de Tratamiento de Imágenes, Universidad Politécnica de Madrid (UPM), E-28040 Madrid, Spain. ccr@gti.ssr.upm.es.

ABSTRACT
An advanced and user-friendly tool for fast labeling of moving objects captured with surveillance sensors is proposed, which is available to the public. This tool allows the creation of three kinds of labels: moving objects, shadows and occlusions. These labels are created at both the pixel level and object level, which makes them suitable to assess the quality of both moving object detection strategies and tracking algorithms. The labeling can be performed easily and quickly thanks to a very friendly graphical user interface that allows one to automatize many common operations. This interface also includes some semiautomatic advanced tools that simplify the labeling tasks and drastically reduce the time required to obtain high-quality results.

No MeSH data available.


Related in: MedlinePlus