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

(a) Original image; (b) detection using RGB color; (c) detection using the alternative appearance components (RnGn/ ∇ s/).
© Copyright Policy
Related In: Results  -  Collection

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

f7-sensors-15-15159: (a) Original image; (b) detection using RGB color; (c) detection using the alternative appearance components (RnGn/ ∇ s/).

Mentions: On the one hand, TSLAB does not only allow the user to configure these methods to use the typical RGB color components, but it also allows one to select the set of appearance components proposed in [31], which has proven to be very robust to shadows cast by moving objects and to soft illumination changes. This set of components is composed by the red and green chromaticities (Rn = R/(R+G+B) and Gn = G/(R + G + B)) and by the modulus of the gradient of the brightness (/ ∇ s/, where s = R+G+B). Figure 7 shows some results using the typical RGB color and the alternative appearance components. It can be seen that, using this alternative, the shadows cast by the moving object have been drastically reduced, which will facilitate the labeling of the moving object.


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

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

(a) Original image; (b) detection using RGB color; (c) detection using the alternative appearance components (RnGn/ ∇ s/).
© Copyright Policy
Related In: Results  -  Collection

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

f7-sensors-15-15159: (a) Original image; (b) detection using RGB color; (c) detection using the alternative appearance components (RnGn/ ∇ s/).
Mentions: On the one hand, TSLAB does not only allow the user to configure these methods to use the typical RGB color components, but it also allows one to select the set of appearance components proposed in [31], which has proven to be very robust to shadows cast by moving objects and to soft illumination changes. This set of components is composed by the red and green chromaticities (Rn = R/(R+G+B) and Gn = G/(R + G + B)) and by the modulus of the gradient of the brightness (/ ∇ s/, where s = R+G+B). Figure 7 shows some results using the typical RGB color and the alternative appearance components. It can be seen that, using this alternative, the shadows cast by the moving object have been drastically reduced, which will facilitate the labeling 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