Unsupervised Object Discovery and Segmentation of RGBD-images

2017/10/18 by Johan Ekekrantz, Ekekrantz, Johan, Nils Bore +7
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Object Detection Techniques #Industrial Vision Systems and Defect Detection #Robotics (cs.RO) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.1710.06929

openalex publication_date 2017/10/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper we introduce a system for unsupervised object discovery and segmentation of RGBD-images. The system models the sensor noise directly from data, allowing accurate segmentation without sensor specific hand tuning of measurement noise models making use of the recently introduced Statistical Inlier Estimation (SIE) method. Through a fully probabilistic formulation, the system is able to apply probabilistic inference, enabling reliable segmentation in previously challenging scenarios. In addition, we introduce new methods for filtering out false positives, significantly improving the signal to noise ratio. We show that the system significantly outperform state-of-the-art in on a challenging real-world dataset.

Citations

• Random sample consensus

Related

• Dealing with sequences in the RGBDT space
• Incremental Class Discovery for Semantic Segmentation with RGBD Sensing
• RGB-D image-based Object Detection: from Traditional Methods to Deep Learning Techniques
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
• Towards Building an RGBD-M Scanner