Aligning point cloud views using persistent feature histograms

Rusu, Radu Bogdan; Blodow, Nico; Márton, Zoltán-Csaba; Beetz, Michael

doi:10.1109/iros.2008.4650967

Cited by 812 publications

(443 citation statements)

References 16 publications

Supporting

Mentioning

398

Contrasting

Unclassified

Order By: Relevance

“…In this contribution, the latter methodology is implemented: for a single point cloud, the normals for all points are calculated. Then, for two randomly selected points in a cloud, the PFH metric is calculated [7,8]. This procedure is repeated for up to 5000 randomly selected point pairs extracted from the cloud.…”

Section: From Point Clouds To Network Inputmentioning

confidence: 99%

Dynamic Hand Gesture Recognition for Mobile Systems Using Deep LSTM

Sarkar

Gepperth

Handmann

et al. 2017

Intelligent Human Computer Interaction

View full text Add to dashboard Cite

Abstract. We present a pipeline for recognizing dynamic freehand gestures on mobile devices based on extracting depth information coming from a single Time-of-Flight sensor. Hand gestures are recorded with a mobile 3D sensor, transformed frame by frame into an appropriate 3D descriptor and fed into a deep LSTM network for recognition purposes. LSTM being a recurrent neural model, it is uniquely suited for classifying explicitly time-dependent data such as hand gestures. For training and testing purposes, we create a small database of four hand gesture classes, each comprising 40 × 150 3D frames. We conduct experiments concerning execution speed on a mobile device, generalization capability as a function of network topology, and classification ability 'ahead of time', i.e., when the gesture is not yet completed. Recognition rates are high (>95%) and maintainable in real-time as a single classification step requires less than 1 ms computation time, introducing freehand gestures for mobile systems.

show abstract

Section: From Point Clouds To Network Inputmentioning

confidence: 99%

Dynamic Hand Gesture Recognition for Mobile Systems Using Deep LSTM

Sarkar

Gepperth

Handmann

et al. 2017

Intelligent Human Computer Interaction

View full text Add to dashboard Cite

show abstract

“…3 and 4. The use of contextual or local descriptors is a well-established approach, which has been investigated thoroughly both for appearance-based keypoints in image data (see, e.g., [2,3,52]) and for 3D point clouds (see, e.g., [25,34,74]). …”

Section: Local Contextual Representationmentioning

confidence: 99%

Using surfaces and surface relations in an Early Cognitive Vision system

Kraft

Mustafa

Popovic

et al. 2015

Machine Vision and Applications

View full text Add to dashboard Cite

We present a deep hierarchical visual system with two parallel hierarchies for edge and surface information. In the two hierarchies, complementary visual information is represented on different levels of granularity together with the associated uncertainties and confidences. At all levels geometric and appearance information is coded explicitly in 2D and 3D allowing to access this information separately and to link between the different levels. We demonstrate the advantages of such hierarchies in three applications covering grasping, view-point independent object representation, and pose estimation.

show abstract

“…The first one is the Point Feature Histograms (PFH) [4]. This descriptor's goal is to generalize both the surface normals and the curvature estimates.…”

Section: Descriptorsmentioning

confidence: 99%

Set Distance Functions for 3D Object Recognition

Alexandre

2013

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. One of the key steps in 3D object recognition is the matching between an input cloud and a cloud in a database of known objects. This is usually done using a distance function between sets of descriptors. In this paper we propose to study how several distance functions (some already available and other new proposals) behave experimentally using a large freely available household object database containing 1421 point clouds from 48 objects and 10 categories. We present experiments illustrating the accuracy of the distances both for object and category recognition and find that simple distances give competitive results both in terms of accuracy and speed.

show abstract

Aligning point cloud views using persistent feature histograms

Cited by 812 publications

References 16 publications

Dynamic Hand Gesture Recognition for Mobile Systems Using Deep LSTM

Dynamic Hand Gesture Recognition for Mobile Systems Using Deep LSTM

Using surfaces and surface relations in an Early Cognitive Vision system

Set Distance Functions for 3D Object Recognition

Contact Info

Product

Resources

About