Fig 3 - uploaded by Jon Azpiazu
Content may be subject to copyright.
Recovering after illumination change.

Recovering after illumination change.

Source publication
Article
Full-text available
Several works that use colour as the main cue for object de- tection often assume static colour models. However unless using a colour constancy approach, or working in well con- trolled environments, different lighting conditions can lead to high colour variability that may make the detector fail. This variation in lighting conditions is even more...

Context in source publication

Context 1
... all of the sequences tested, there is a significant im- provement of the detection ratio when using a dynamic colour model. Figure 3 is a good example for explaining the improvement. In the first frame, under artificial lighting, the face is detected correctly. ...

Similar publications

Article
Full-text available
Recently, Minimum Cost Multicut Formulations have been proposed and proven to be successful in both motion trajectory segmentation and multi-target tracking scenarios. Both tasks benefit from decomposing a graphical model into an optimal number of connected components based on attractive and repulsive pairwise terms. The two tasks are formulated on...
Article
Full-text available
Vision-based human face detection and recognition are widely used and have been shown to be effective in normal illumination conditions. Under severe illumination conditions, however, it is very challenging. In this paper, we address the effect of illumination on the face detection and the face recognition problem by introducing a novel illuminatio...
Article
Full-text available
We present an approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation. The approach extracts temporally consistent object tubes based on an off-the-shelf detector. Besides the class label for each tube, this provides a location prior that is independent of moti...