Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...
In previous work we have presented a prototype of an assistant system for the blind that can be used for self-localization and interactive object identification of static objects ...
Object detection and recognition has achieved a significant progress in recent years. However robust 3D object detection and segmentation in noisy 3D data volumes remains a challen...
Le Lu, Adrian Barbu, Matthias Wolf, Jianming Liang...
In this paper we extend a method that uses image patch histograms and discriminative training to recognize objects in cluttered scenes. The method generalizes and performs well for...
We propose a novel solution to object detection, localization and pose estimation with applications in robot vision. The proposed method is especially applicable when the objects ...