Efficient Hierarchical Multi-Object Segmentation in Layered Graphs

2021 ◽  
Vol 5 (1) ◽  
pp. 21-42
Author(s):  
Leissi M.C. Leon ◽  
Krzysztof C. Ciesielski ◽  
Paulo A.V. Miranda
Keyword(s):  
Object Segmentation ◽  
Structural Information ◽  
Hierarchical Segmentation ◽  
Image Objects ◽  
Hierarchical Relations ◽  
Flow Algorithm ◽  
Segmentation Of Images ◽  
High Level ◽  
Min Cut ◽  
Weighted Digraph

Abstract We propose a novel efficient seed-based method for the multi-object segmentation of images based on graphs, named Hierarchical Layered Oriented Image Foresting Transform (HLOIFT). It uses a tree of the relations between the image objects, with each node in the tree representing an object. Each tree node may contain different individual high-level priors of its corresponding object and defines a weighted digraph, named as layer. The layer graphs are then integrated into a hierarchical graph, considering the hierarchical relations of inclusion and exclusion. A single energy optimization is performed in the hierarchical layered weighted digraph leading to globally optimal results satisfying all the high-level priors. The experimental evaluations of HLOIFT, on medical, natural, and synthetic images, indicate promising results comparable to the related baseline methods that include structural information, but with lower computational complexity. Compared to the hierarchical segmentation by the min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios, and has a better running time.

scholarly journals An Efficient Hierarchical Layered Graph Approach for Multi-Region Segmentation

2019 ◽  
Author(s):  
Leissi M. Castañeda Leon ◽  
Krzysztof Chris Ciesielski ◽  
Paulo A. Vechiatto Miranda
Keyword(s):  
State Of The Art ◽  
Region Segmentation ◽  
Hierarchical Segmentation ◽  
Image Objects ◽  
Hierarchical Relations ◽  
Flow Algorithm ◽  
Segmentation Of Images ◽  
High Level ◽  
Layered Graph ◽  
Weighted Digraph

We proposed a novel efficient seed-based method for the multiple region segmentation of images based on graphs, named Hierarchical Layered Oriented Image Foresting Transform (HLOIFT). It uses a tree of the relations between the image objects, represented by a node. Each tree node may contain different individual high-level priors and defines a weighted digraph, named as layer. The layer graphs are then integrated into a hierarchical graph, considering the hierarchical relations of inclusion and exclusion. A single energy optimization is performed in the hierarchical layered weighted digraph leading to globally optimal results satisfying all the high-level priors. The experimental evaluations of HLOIFT and its extensions, on medical, natural and synthetic images, indicate promising results comparable to the state-of-the-art methods, but with lower computational complexity. Compared to hierarchical segmentation by the min-cut/max-flow algorithm, our approach is less restrictive, leading to globally optimal results in more general scenarios, and has a better running time.

scholarly journals Analysis of Occlusion Effects for Map-Based Self-Localization in Urban Areas

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5196
Author(s):  
Yuki Endo ◽  
Ehsan Javanmardi ◽  
Shunsuke Kamijo
Keyword(s):  
Urban Areas ◽  
Structural Information ◽  
Average Error ◽  
High Definition ◽  
Geometrical Structures ◽  
Real Environment ◽  
Surrounding Environment ◽  
Localization Errors ◽  
Stable Estimation ◽  
High Level

A high-definition (HD) map provides structural information for map-based self-localization, enabling stable estimation in real environments. In urban areas, there are many obstacles, such as buses, that occlude sensor observations, resulting in self-localization errors. However, most of the existing HD map-based self-localization evaluations do not consider sudden significant errors due to obstacles. Instead, they evaluate this in terms of average error over estimated trajectories in an environment with few occlusions. This study evaluated the effects of self-localization estimation on occlusion with synthetically generated obstacles in a real environment. Various patterns of synthetic occlusion enabled the analyses of the effects of self-localization error from various angles. Our experiments showed various characteristics that locations susceptible to obstacles have. For example, we found that occlusion in intersections tends to increase self-localization errors. In addition, we analyzed the geometrical structures of a surrounding environment in high-level error cases and low-level error cases with occlusions. As a result, we suggested the concept that the real environment should have to achieve robust self-localization under occlusion conditions.

Content Based Image Retrieval Using Active-Nets

2011 ◽  
pp. 85-114 ◽  
Author(s):  
David García Pérez ◽  
Antonio Mosquera ◽  
Stefano Berretti ◽  
Alberto Del Bimbo
Keyword(s):  
Image Retrieval ◽  
Structural Information ◽  
Similarity Measures ◽  
Research Area ◽  
Content Based Image Retrieval ◽  
Image Objects ◽  
Image Retrieval System ◽  
Deformable Structure ◽  
Retrieval Problem ◽  
Active Research

Content-based image retrieval has been an active research area in past years. Many different solutions have been proposed to improve performance of retrieval, but the large part of these works have focused on sub-parts of the retrieval problem, providing targeted solutions only for individual aspects (i.e., feature extraction, similarity measures, indexing, etc). In this chapter, we first shortly review some of the main practiced solutions for content-based image retrieval evidencing some of the main issues. Then, we propose an original approach for the extraction of relevant image objects and their matching for retrieval applications, and present a complete image retrieval system which uses this approach (including similarity measures and image indexing). In particular, image objects are represented by a two-dimensional deformable structure, referred to as “active net.” Active net is capable of adapting to relevant image regions according to chromatic and edge information. Extension of the active nets has been defined, which permits the nets to break themselves, thus increasing their capability to adapt to objects with complex topological structure. The resulting representation allows a joint description of color, shape, and structural information of extracted objects. A similarity measure between active nets has also been defined and used to combine the retrieval with an efficient indexing structure. The proposed system has been experimented on two large and publicly available objects databases, namely, the ETH-80 and the ALOI.

Design Resource Reusable Model Based on Function Surface for DFMC

2011 ◽  
Vol 215 ◽  
pp. 379-383
Author(s):  
J.Y. Yang ◽  
Z.H. Cheng ◽  
Zhong Kai Li
Keyword(s):  
Mass Customization ◽  
Structural Information ◽  
Optimization Method ◽  
Product Layer ◽  
Concept Design ◽  
Model Based ◽  
Customer Order ◽  
Core Technology ◽  
High Level ◽  
And Function

The rationality of design resource reusable model is the key to judging whether a mass customization system has adequate flexibility and agility or not. Based on the demand of the Design for Mass Customization (DFMC), design resource reusable model should not only include high-level feature information such as demands, functions, principles and constraints, but also include the underlying structural information such as geometry features and assembly relationship. Function Surface is the media between the function and the structure in concept design progress, which is processed to solve the uncertainty when the function maps directly to the structure. Based on Function Surface theory, the multi-layer design resource reusable model including the entity product layer, entity module layer, shell part layer, Function Pattern layer and Function Surface layer is proposed. The designer can browse and find the reusable model based on the different position of the decoupling point of the customer order in the production process. According to the model and the statistical data of the management, the reuse rate curve of design resource is drawn, and the overall optimization method of the design resource reusable standard model and the evolution method of the core technology are proposed.

Using Molecular Fingerprinting to Infer Functional Similarity in Engineered Systems

2015 ◽  
Author(s):  
Ryan Arlitt ◽  
Charles Manion ◽  
Robert Stone ◽  
Matthew Campbell ◽  
Irem Tumer
Keyword(s):  
Drug Design ◽  
Product Design ◽  
Structural Information ◽  
Functional Similarity ◽  
Advanced Materials ◽  
Molecular Fingerprinting ◽  
Electromechanical Products ◽  
Product Design Process ◽  
Engineered Systems ◽  
High Level

Design of new and advanced materials with shape-shifting or origami-like capabilities is an area that bears a strong similarity to the design of electromechanical products yet has not leveraged such systematic approaches. In this paper, computational methods to design Metal Organic Responsive Frameworks (MORFs) — which are a theoretical type of material that can change their shape and porosity in response to light — are investigated. However, it is a significant challenge to computationally identify MORFs that are both feasible and useful, i.e., systemic invention (as opposed to discovery) of new MORFs. The proposed framework utilizes the typical product design process to iteratively generate new candidates, evaluate their properties, and then guide the generation of the next set of candidates. A materials designer could then leverage this knowledge to generate structures or substructures with specific functional goals in mind. In this paper an approach to inferring functional similarity of systems using structural information — based on both drug design and database-driven product design — is evaluated. The results demonstrate an observable correlation between structural fingerprints of electromechanical products and electromechanical function. This evidence, combined with the well-established similar property principle in drug design, supports the usage of molecular fingerprinting for providing high-level functional guidance in a MORF design framework based on purely structural information.

Topology cuts: A novel min-cut/max-flow algorithm for topology preserving segmentation in N–D images

2008 ◽  
Vol 112 (1) ◽  
pp. 81-90 ◽  
Author(s):  
Yun Zeng ◽  
Dimitris Samaras ◽  
Wei Chen ◽  
Qunsheng Peng
Keyword(s):  
Flow Algorithm ◽  
Min Cut

A Competitive Study of Graph Reduction Methods for Min S-T Cut Image Segmentation

2014 ◽  
Vol 19 (2-3) ◽  
pp. 97-105
Author(s):  
Tomasz Węgliński ◽  
Anna Fabijańska ◽  
Jarosław Goclawski
Keyword(s):  
Graph Cut ◽  
Size Reduction ◽  
Practical Application ◽  
Graph Reduction ◽  
Segmentation Algorithms ◽  
Flow Algorithm ◽  
Graph Size ◽  
Reduction Methods ◽  
Graph Cut Segmentation ◽  
Min Cut

Abstract When applied to the segmentation of 3D medical images, graph-cut segmentation algorithms require an extreme amount of memory and time resources in order to represent the image graph and to perform the necessary processing on the graph. These requirements actually exclude the graph-cut based approaches from their practical application. Hence, there is a need to develop the dedicated graph size reduction methods. In this paper, several techniques for the graph size reduction are proposed. These apply the idea of superpixels. In particular, two methods for superpixel creation are introduced. The results of applying the proposed methods to the segmentation of CT datasets using min-cut/max-flow algorithm are presented, compared and discussed.

Sign in / Sign up

Export Citation Format

Share Document