Point Cloud Processing

With the growing availability of depth cameras and lidar, the processing of the resulting point clouds has become its own sub-area of Computer Vision.

Illustration of the probabilistic modelling of point clouds using latent variables.Data from these sensors is usually sparse, thus requires densification. Also, the position and orientation are often only partly known and a registration of the measurements in a joint reference system is required.

Finally, the point cloud needs to be split into object-related measurements, i.e., 3D segmentation is needed. We approach these problems using novel deep learning methodology based on normalized CNNs and 3D fusion of deep 2D segmentations, as well as probabilistic modelling.

Researchers

Per-Erik Forssén

Senior Associate Professor

Fahad Khan

Associate Professor, Docent

Michael Felsberg

Professor, Head of Division

External partners

Centauro and Veoneer

Publications

A selection of three papers

Abdelrahman Eldesokey, Michael Felsberg, Fahad Shahbaz Khan (2019)

Propagating Confidences through CNNs for Sparse Data Regression

British Machine Vision Conference 2018, BMVC 2018 Continue to DOI

Felix Järemo-Lawin, Martin Danelljan, Patrik Tosteberg, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg (2017)

Deep Projective 3D Semantic Segmentation

Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I , s.95-107 Continue to DOI

Felix Järemo-Lawin, Martin Danelljan, Patrik Tosteberg, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg (2017)

Deep Projective 3D Semantic Segmentation

Computer Analysis of Images and Patterns: 17th International Conference, CAIP 2017, Ystad, Sweden, August 22-24, 2017, Proceedings, Part I , s.95-107 Continue to DOI

WASP research CVL

Visual Object Tracking

Visual Object Tracking is one of the principal challenges in Computer Vision, where the task is to locate a certain object in all frames of a video, given only its location in the first frame.

A Detailed Framework for Semantic Description of Humans

Semantic description of humans in images and videos is one of the fundamental problems in computer vision with applications such as visual surveillance, facial verification, health care, image and video search engines and human-computer interaction.

Machine Learning for Visual Navigation and Localization

Navigation and localization are principal challenges in Robot Vision, where the task is to estimate the geometric relation between a vehicle and its environment, either passively in a virtual model or actively through controlling the robot.

WASP Computer Vision Laboratory

The research covers a broad range of topics within artificial visual systems with a particular focus on machine learning for robot vision. The group has made major contributions in establishing the concept of computer vision in Sweden.