The use of polygonal meshes for the representation of highly complex geometric objects has become the de facto standard in most computer graphics applications. Especially triangle...
Classifying objects in computer vision, we are faced with a great many features one can use. This paper argues that diagrammatic representations help to comprehend properties of fe...
This paper introduces a new way to apply boosting to a joint feature pool from different sensors, namely 3D range data and color vision. The combination of sensors strengthens the ...
Dominik Alexander Klein, Dirk Schulz, Simone Frint...
This paper presents a novel classification strategy for 3D objects. Our technique is based on using a Global Geodesic Function to intrinsically describe the surface ofan object. T...
Abstract. A convolutional network architecture termed sparse convolutional neural network (SCNN) is proposed and tested on a real-world classification task (car classification). In...