Modeling Visual Saliency in Images and Videos

2011 ◽  
pp. 273-293
Author(s):  
Yiqun Hu ◽  
Viswanath Gopalakrishnan ◽  
Deepu Rajan
Keyword(s):  
Computer Vision ◽  
Visual Saliency ◽  
Multimedia Applications ◽  
The Other ◽  
Visual Content ◽  
Top Down ◽  
Future Directions ◽  
Reading Materials ◽  
Salient Regions ◽  
Computer Vision Applications

Visual saliency, which distinguishes “interesting” visual content from others, plays an important role in multimedia and computer vision applications. This chapter starts with a brief overview of visual saliency as well as the literature of some popular models to detect salient regions. We describe two methods to model visual saliency – one in images and the other in videos. Specifically, we introduce a graph-based method to model salient region in images in a bottom-up manner. For videos, we introduce a factorization based method to model attention object in motion, which utilizes the top-down knowledge of cameraman for model saliency. Finally, future directions for visual saliency modeling and additional reading materials are highlighted to familiarize readers with the research on visual saliency modeling for multimedia applications.

Modeling Visual Saliency in Images and Videos

2013 ◽  
pp. 79-100
Author(s):  
Yiqun Hu ◽  
Viswanath Gopalakrishnan ◽  
Deepu Rajan
Keyword(s):  
Computer Vision ◽  
Visual Saliency ◽  
Multimedia Applications ◽  
The Other ◽  
Visual Content ◽  
Top Down ◽  
Future Directions ◽  
Reading Materials ◽  
Salient Regions ◽  
Computer Vision Applications

Visual saliency, which distinguishes “interesting” visual content from others, plays an important role in multimedia and computer vision applications. This chapter starts with a brief overview of visual saliency as well as the literature of some popular models to detect salient regions. We describe two methods to model visual saliency – one in images and the other in videos. Specifically, we introduce a graph-based method to model salient region in images in a bottom-up manner. For videos, we introduce a factorization based method to model attention object in motion, which utilizes the top-down knowledge of cameraman for model saliency. Finally, future directions for visual saliency modeling and additional reading materials are highlighted to familiarize readers with the research on visual saliency modeling for multimedia applications.

Feature Engineering for Structural Health Monitoring (SHM)

2021 ◽  
pp. 138-163
Author(s):  
Esraa Elhariri ◽  
Nashwa El-Bendary ◽  
Shereen A. Taie
Keyword(s):  
Computer Vision ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Structural Damage ◽  
Emerging Technology ◽  
The Other ◽  
Feature Engineering ◽  
Future Directions ◽  
Structural Health ◽  
Computational Perspective

Feature engineering is a key component contributing to the performance of the computer vision pipeline. It is fundamental to several computer vision tasks such as object recognition, image retrieval, and image segmentation. On the other hand, the emerging technology of structural health monitoring (SHM) paved the way for spotting continuous tracking of structural damage. Damage detection and severity recognition in the structural buildings and constructions are issues of great importance as the various types of damages represent an essential indicator of building and construction durability. In this chapter, the authors connect the feature engineering with SHM processes through illustrating the concept of SHM from a computational perspective, with a focus on various types of data and feature engineering methods as well as applications and open venues for further research. Challenges to be addressed and future directions of research are presented and an extensive survey of state-of-the-art studies is also included.

A GRAPH-BASED ALGORITHM FOR CLUSTER DETECTION

2008 ◽  
Vol 22 (05) ◽  
pp. 843-860 ◽  
Author(s):  
PASQUALE FOGGIA ◽  
GENNARO PERCANNELLA ◽  
CARLO SANSONE ◽  
MARIO VENTO
Keyword(s):  
Computer Vision ◽  
State Of The Art ◽  
Cluster Detection ◽  
The Other ◽  
Actual Number ◽  
Number Of Clusters ◽  
Size And Shape ◽  
Computer Vision Applications

In some Computer Vision applications there is the need for grouping, in one or more clusters, only a part of the whole dataset. This happens, for example, when samples of interest for the application at hand are present together with several noisy samples. In this paper we present a graph-based algorithm for cluster detection that is particularly suited for detecting clusters of any size and shape, without the need of specifying either the actual number of clusters or the other parameters. The algorithm has been tested on data coming from two different computer vision applications. A comparison with other four state-of-the-art graph-based algorithms was also provided, demonstrating the effectiveness of the proposed approach.

Building up a Bio-Inspired Visual Attention Model by Integrating Top-Down Shape Bias and Improved Mean Shift Adaptive Segmentation

2015 ◽  
Vol 29 (04) ◽  
pp. 1555005 ◽  
Author(s):  
Jiawei Xu ◽  
Shigang Yue
Keyword(s):  
Traffic Accidents ◽  
Road Traffic ◽  
Mean Shift ◽  
Visual Saliency ◽  
Ground Truth ◽  
Regions Of Interest ◽  
Natural Scenes ◽  
Top Down ◽  
Mean Shift Algorithm ◽  
Salient Regions

The driver-assistance system (DAS) becomes quite necessary in-vehicle equipment nowadays due to the large number of road traffic accidents worldwide. An efficient DAS detecting hazardous situations robustly is key to reduce road accidents. The core of a DAS is to identify salient regions or regions of interest relevant to visual attended objects in real visual scenes for further process. In order to achieve this goal, we present a method to locate regions of interest automatically based on a novel adaptive mean shift segmentation algorithm to obtain saliency objects. In the proposed mean shift algorithm, we use adaptive Bayesian bandwidth to find the convergence of all data points by iterations and the k-nearest neighborhood queries. Experiments showed that the proposed algorithm is efficient, and yields better visual salient regions comparing with ground-truth benchmark. The proposed algorithm continuously outperformed other known visual saliency methods, generated higher precision and better recall rates, when challenged with natural scenes collected locally and one of the largest publicly available data sets. The proposed algorithm can also be extended naturally to detect moving vehicles in dynamic scenes once integrated with top-down shape biased cues, as demonstrated in our experiments.

scholarly journals Vision-based human activity recognition: a survey

2020 ◽  
Vol 79 (41-42) ◽  
pp. 30509-30555 ◽  
Author(s):  
Djamila Romaissa Beddiar ◽  
Brahim Nini ◽  
Mohammad Sabokrou ◽  
Abdenour Hadid
Keyword(s):  
Computer Vision ◽  
Activity Recognition ◽  
Human Activity ◽  
Home Monitoring ◽  
Human Activity Recognition ◽  
Future Directions ◽  
Development Cycle ◽  
Current Survey ◽  
Computer Vision Applications ◽  
Highly Correlated

Abstract Human activity recognition (HAR) systems attempt to automatically identify and analyze human activities using acquired information from various types of sensors. Although several extensive review papers have already been published in the general HAR topics, the growing technologies in the field as well as the multi-disciplinary nature of HAR prompt the need for constant updates in the field. In this respect, this paper attempts to review and summarize the progress of HAR systems from the computer vision perspective. Indeed, most computer vision applications such as human computer interaction, virtual reality, security, video surveillance and home monitoring are highly correlated to HAR tasks. This establishes new trend and milestone in the development cycle of HAR systems. Therefore, the current survey aims to provide the reader with an up to date analysis of vision-based HAR related literature and recent progress in the field. At the same time, it will highlight the main challenges and future directions.

scholarly journals Language Family Engineering with Product Lines of Multi-level Models

2021 ◽  
Author(s):  
Juan de Lara ◽  
Esther Guerra
Keyword(s):  
Software Engineering ◽  
Arbitrary Number ◽  
Formal Theory ◽  
The Other ◽  
Language Family ◽  
Top Down ◽  
Product Lines ◽  
Modelling Languages ◽  
Multi Level ◽  
Definition Of

AbstractModelling is an essential activity in software engineering. It typically involves two meta-levels: one includes meta-models that describe modelling languages, and the other contains models built by instantiating those meta-models. Multi-level modelling generalizes this approach by allowing models to span an arbitrary number of meta-levels. A scenario that profits from multi-level modelling is the definition of language families that can be specialized (e.g., for different domains) by successive refinements at subsequent meta-levels, hence promoting language reuse. This enables an open set of variability options given by all possible specializations of the language family. However, multi-level modelling lacks the ability to express closed variability regarding the availability of language primitives or the possibility to opt between alternative primitive realizations. This limits the reuse opportunities of a language family. To improve this situation, we propose a novel combination of product lines with multi-level modelling to cover both open and closed variability. Our proposal is backed by a formal theory that guarantees correctness, enables top-down and bottom-up language variability design, and is implemented atop the MetaDepth multi-level modelling tool.

Computer Vision and robotics in postal automation

1999 ◽  
Vol 18 (3-4) ◽  
pp. 265-273
Author(s):  
Giovanni B. Garibotto
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Pattern Recognition ◽  
Material Handling ◽  
State Of The Art ◽  
Short Description ◽  
The Other ◽  
Functional Requirements ◽  
Postal Automation ◽  
And Robotics

The paper is intended to provide an overview of advanced robotic technologies within the context of Postal Automation services. The main functional requirements of the application are briefly referred, as well as the state of the art and new emerging solutions. Image Processing and Pattern Recognition have always played a fundamental role in Address Interpretation and Mail sorting and the new challenging objective is now off-line handwritten cursive recognition, in order to be able to handle all kind of addresses in a uniform way. On the other hand, advanced electromechanical and robotic solutions are extremely important to solve the problems of mail storage, transportation and distribution, as well as for material handling and logistics. Finally a short description of new services of Postal Automation is referred, by considering new emerging services of hybrid mail and paper to electronic conversion.

scholarly journals A Survey on Contrastive Self-Supervised Learning

Technologies ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 2
Author(s):  
Ashish Jaiswal ◽  
Ashwin Ramesh Babu ◽  
Mohammad Zaki Zadeh ◽  
Debapriya Banerjee ◽  
Fillia Makedon
Keyword(s):  
Computer Vision ◽  
Supervised Learning ◽  
Language Processing ◽  
Large Scale ◽  
Performance Comparison ◽  
Extensive Review ◽  
Future Directions ◽  
Dominant Component ◽  
Supervised Methods ◽  
The Cost

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several downstream tasks. Specifically, contrastive learning has recently become a dominant component in self-supervised learning for computer vision, natural language processing (NLP), and other domains. It aims at embedding augmented versions of the same sample close to each other while trying to push away embeddings from different samples. This paper provides an extensive review of self-supervised methods that follow the contrastive approach. The work explains commonly used pretext tasks in a contrastive learning setup, followed by different architectures that have been proposed so far. Next, we present a performance comparison of different methods for multiple downstream tasks such as image classification, object detection, and action recognition. Finally, we conclude with the limitations of the current methods and the need for further techniques and future directions to make meaningful progress.

scholarly journals Different Roles of Top-Down and Bottom-Up Processes in the Distribution of Size-Fractionated Phytoplankton in Gwangyang Bay

Water ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 1682
Author(s):  
Yoonja Kang ◽  
Yeongji Oh
Keyword(s):  
Nutrient Availability ◽  
Fast Response ◽  
Nutrient Addition ◽  
The Other ◽  
Zooplankton Grazing ◽  
Top Down ◽  
Bottom Up ◽  
Phytoplankton Distribution ◽  
Summer Bloom ◽  
Gwangyang Bay

The interactive roles of zooplankton grazing (top-down) and nutrient (bottom-up) processes on phytoplankton distribution in a temperate estuary were investigated via dilution and nutrient addition experiments. The responses of size-fractionated phytoplankton and major phytoplankton groups, as determined by flow cytometry, were examined in association with zooplankton grazing and nutrient availability. The summer bloom was attributed to nanoplankton, and microplankton was largely responsible for the winter bloom, whereas the picoplankton biomass was relatively consistent throughout the sampling periods, except for the fall. The nutrient addition experiments illustrated that nanoplankton responded more quickly to phosphate than the other groups in the summer, whereas microplankton had a faster response to most nutrients in the winter. The dilution experiments ascribed that the grazing mortality rates of eukaryotes were low compared to those of the other groups, whereas autotrophic cyanobacteria were more palatable to zooplankton than cryptophytes and eukaryotes. Our experimental results indicate that efficient escape from zooplankton grazing and fast response to nutrient availability synergistically caused the microplankton to bloom in the winter, whereas the bottom-up process (i.e., the phosphate effect) largely governed the nanoplankton bloom in the summer.

scholarly journals Flying Free: A Research Overview of Deep Learning in Drone Navigation Autonomy

Drones ◽  
2021 ◽  
Vol 5 (2) ◽  
pp. 52
Author(s):  
Thomas Lee ◽  
Susan Mckeever ◽  
Jane Courtney
Keyword(s):  
Deep Learning ◽  
Research Work ◽  
Learning Approaches ◽  
Clear Definition ◽  
Top Down ◽  
Research Activity ◽  
Comprehensive Overview ◽  
The Past ◽  
Computer Vision Applications ◽  
Definition Of

With the rise of Deep Learning approaches in computer vision applications, significant strides have been made towards vehicular autonomy. Research activity in autonomous drone navigation has increased rapidly in the past five years, and drones are moving fast towards the ultimate goal of near-complete autonomy. However, while much work in the area focuses on specific tasks in drone navigation, the contribution to the overall goal of autonomy is often not assessed, and a comprehensive overview is needed. In this work, a taxonomy of drone navigation autonomy is established by mapping the definitions of vehicular autonomy levels, as defined by the Society of Automotive Engineers, to specific drone tasks in order to create a clear definition of autonomy when applied to drones. A top–down examination of research work in the area is conducted, focusing on drone navigation tasks, in order to understand the extent of research activity in each area. Autonomy levels are cross-checked against the drone navigation tasks addressed in each work to provide a framework for understanding the trajectory of current research. This work serves as a guide to research in drone autonomy with a particular focus on Deep Learning-based solutions, indicating key works and areas of opportunity for development of this area in the future.

Sign in / Sign up

Export Citation Format

Share Document