Efficient Hierarchical Graph-Based Segmentation of RGBD Videos

@article{Hickson2014EfficientHG,
  title={Efficient Hierarchical Graph-Based Segmentation of RGBD Videos},
  author={Steven Hickson and Stan Birchfield and Irfan Essa and Henrik I. Christensen},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={344-351}
}
We present an efficient and scalable algorithm for segmenting 3D RGBD point clouds by combining depth, color, and temporal information using a multistage, hierarchical graph-based approach. Our algorithm processes a moving window over several point clouds to group similar regions over a graph, resulting in an initial over-segmentation. These regions are then merged to yield a dendrogram using agglomerative clustering via a minimum spanning tree algorithm. Bipartite graph matching at a given… 

Figures from this paper

Efficient Multi-scale Plane Extraction Based RGBD Video Segmentation

TLDR
The qualitative and quantitative results of plane extraction and RGBD scene video segmentation show the effectiveness of proposed methods.

Efficient, dense, object-based segmentation from RGBD video

TLDR
This work presents a novel framework for spatio-temporal segmentation from RGBD video, and proposes a novel context-aware aggregation method that uses a deformable parts model to group the detected parts of the object as a single segment with an accurate boundary.

3D Point Cloud Video Segmentation Based on Interaction Analysis

TLDR
A hierarchical representation of the input point cloud is proposed to efficiently segment point clouds at the finer level, and to temporally establish the correspondence between segments while dynamically managing the object split and merge at the coarser level.

Normal distribution transform graph-based point cloud segmentation

  • W. R. GreenHans Grobler
  • Computer Science
    2015 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech)
  • 2015
TLDR
A graph-based algorithm for segmenting point cloud scenes using criteria based on the combination of spatial, geometric, and appearance features and has the ability to combine multiple features into a single edge weight without the need to find an appropriate normalization scheme.

Temporally Coherent 3D Point Cloud Video Segmentation in Generic Scenes

TLDR
A novel generic segmentation approach for 3D point cloud video (stream data) thoroughly exploiting the explicit geometry in RGBD, based on low level features, such as connectivity and compactness.

3D point cloud segmentation using a fully connected conditional random field

TLDR
This paper presents a novel point cloud segmentation approach for segmenting interacting objects in a stream of point clouds by exploiting spatio-temporal coherence in a fully connected conditional random field with the energy function defined based on both current and previous information.

3 D Point Cloud Segmentation Using a Fully Connected Conditional Random Field

TLDR
This paper presents a novel point cloud segmentation approach for segmenting interacting objects in a stream of point clouds by exploiting spatio-temporal coherence in a fully connected conditional random field with the energy function defined based on both current and previous information.

A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time

TLDR
This work compute the main cluster of object segmentation in video using a novel and fast 3D filtering technique that finds the spectral clustering solution, namely the principal eigenvector of the graph's adjacency matrix, without building the matrix explicitly - which would be intractable.

Object-Based Multiple Foreground Segmentation in RGBD Video

TLDR
An RGB and Depth (RGBD) video segmentation method that takes advantage of depth data and can extract multiple foregrounds in the scene and provides performance comparable to the state-of-the-art RGB video segmentations techniques on regular RGB videos with estimated depth maps.

A pr 2 01 9 Graph based Dynamic Segmentation of Generic Objects in 3 D ∗

TLDR
A robust spatio-temporal segmentation of the point clouds is produced, analyzing their connectivity to define the objects according to the evidence observed up to a given temporal point.
...

References

SHOWING 1-10 OF 25 REFERENCES

Efficient hierarchical graph-based video segmentation

TLDR
An efficient and scalable technique for spatiotemporal segmentation of long video sequences using a hierarchical graph-based algorithm that generates high quality segmentations, which are temporally coherent with stable region boundaries, and allows subsequent applications to choose from varying levels of granularity.

Graph-based segmentation for colored 3D laser point clouds

TLDR
This work presents an efficient graph-theoretic algorithm for segmenting a colored laser point cloud derived from a laser scanner and camera that enables combination of color information from a wide field of view camera with a 3D LIDAR point cloud from an actuated planar laser scanner.

Efficient Graph-Based Image Segmentation

TLDR
An efficient segmentation algorithm is developed based on a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image and it is shown that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties.

A Topological Approach to Hierarchical Segmentation using Mean Shift

TLDR
The use of Morse theory is introduced to interpret mean shift as a topological decomposition of the feature space into density modes, which allows for a new algorithm to compute mean-shift segmentations of images and videos.

Depth-adaptive supervoxels for RGB-D video segmentation

TLDR
A method for automatic video segmentation of RGB-D video streams provided by combined colour and depth sensors like the Microsoft Kinect by combining position and normal information from the depth sensor with colour information to compute temporally stable, depth-adaptive superpixels and combine them into a graph of strand-like spatiotemporal, Depth- Adaptive supervoxels.

Depth-supported real-time video segmentation with the Kinect

TLDR
The Metropolis framework provides an inexpensive visual front end for visual preprocessing of videos in industrial settings and robot labs which can potentially be used in various applications.

Streaming Hierarchical Video Segmentation

TLDR
This work proposes an approximation framework for streaming hierarchical video segmentation motivated by data stream algorithms: each video frame is processed only once and does not change the segmentation of previous frames.

Evaluation of super-voxel methods for early video processing

TLDR
Five supervoxel algorithms are studied in the context of what is considered to be a good supervoxels: namely, spatiotemporal uniformity, object/region boundary detection, region compression and parsimony, leading to conclusive evidence that the hierarchical graph-based and segmentation by weighted aggregation methods perform best and almost equally-well on nearly all the metrics.

Towards Scene Understanding – Object Segmentation Using RGBD-Images

TLDR
A framework for detecting unknown 3D objects in RGBD-images and extracting representations suitable for robotics tasks such as grasping is presented and preliminary results demonstrating that the approach can segment objects of various shapes in cluttered table top scenes are shown.

Learning to Segment and Track in RGBD

TLDR
It is shown that it is possible to achieve an order of magnitude speedup and thus real-time performance on a laptop computer by applying simple algorithmic optimizations to the original work, which makes this approach applicable to a broader range of tasks.