
Computer Vision Systems
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The 72 papers presented were carefully reviewed and selected from 114 submissions. The papers are organized in the following topical sections; hardware accelerated and real time vision systems; robotic vision; vision systems applications; high-level and learning vision systems; cognitive vision systems; movement analytics and gesture recognition for human-machine collaboration in industry; cognitive and computer vision assisted systems for energy awareness and behavior analysis; and vision-enabled UAV and counter UAV technologies for surveillance and security of critical infrastructures.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents
- Hardware Accelerated and Real Time Vision Systems
- Hardware Accelerated Image Processing on an FPGA-SoC Based Vision System for Closed Loop Monitoring and Additive Manufacturing Process Control
- 1 Introduction
- 2 Design and Implementation
- 2.1 Processing on Programmable Logic Part
- 2.2 Processing on the ARM CPU Part
- 3 Conclusion
- References
- Real-Time Binocular Vision Implementation on an SoC TMS320C6678 DSP
- 1 Introduction
- 2 Algorithm Description
- 2.1 Cost Computation
- 2.2 Disparity Estimation
- 3 Notes on Implementation
- 3.1 Hardware Overview
- 3.2 Multi-core Processing
- 3.3 Implementation of Cost Computation
- 3.4 Post-processing
- 4 Experimental Results
- 5 Conclusion
- References
- Real-Time Lightweight CNN in Robots with Very Limited Computational Resources: Detecting Ball in NAO
- 1 Introduction
- 2 Related Works
- 3 Data Set
- 4 Network Design
- 4.1 Backbone
- 4.2 Using Depthwise Convolution
- 4.3 Using Weight Binarization
- 4.4 Boost Real Time Performance
- 5 Experimental Results
- 5.1 Comparison Among Proposed Networks
- 5.2 Comparison Among Typical CNN Models
- 6 Conclusion and Future Work
- References
- Reference-Free Adaptive Attitude Determination Method Using Low-Cost MARG Sensors
- 1 Introduction
- 2 Sensor Brief and Modeling
- 3 Sensor Fusion
- 3.1 Gyroscope Update Equation
- 4 Experiments and Results
- 4.1 Experimental Platform Configuration
- 4.2 Convergence Performance
- 4.3 Adaptive Performance
- 4.4 Magnetic Distortion
- 5 Conclusions
- References
- Feature-Agnostic Low-Cost Place Recognition for Appearance-Based Mapping
- 1 Introduction
- 2 Methodology
- 3 Image Descriptors
- 3.1 Gist Features
- 3.2 HOG Features
- 4 Experiments
- 4.1 Precision-Recall Performance: Gist vs. HOG
- 4.2 Space and Time Requirements
- 5 Conclusion
- References
- Robotic Vision
- Semi-semantic Line-Cluster Assisted Monocular SLAM for Indoor Environments
- 1 Introduction
- 2 Related Work
- 3 Proposed Method
- 3.1 Line Segment Detection
- 3.2 Building Line Segment Clusters
- 3.3 Graph Optimization of Line Segment Clusters
- 4 Experiments
- 4.1 Implementation
- 4.2 Datasets
- 4.3 Results
- 5 Conclusions
- References
- Appearance-Based Loop Closure Detection with Scale-Restrictive Visual Features
- 1 Introduction and Literature Review
- 2 Methodology
- 2.1 Scale-Restrictive Visual Features Projection
- 2.2 Nearest Neighbor Vote Assignment
- 2.3 Database Probabilistic Assignment
- 2.4 Candidate Selection and Geometrical Verification Approvement
- 3 Experimental Validation
- 3.1 Datasets
- 3.2 Visual Features Selection
- 3.3 Loop Closure Performance Evaluation Protocol
- 3.4 Comparative Results
- 4 Conclusion
- References
- Grasping Unknown Objects by Exploiting Complementarity with Robot Hand Geometry
- 1 Introduction
- 2 Related Work
- 3 Problem Formulation
- 4 Shape Complementarity in Grasping
- 5 Local Shape Completion
- 5.1 Training
- 6 Grasp Optimization
- 7 Experimental Results
- 7.1 Shape Complementarity and Grasp Success
- 7.2 Performance with Local Shape Completion
- 7.3 Performance with Grasp Optimization
- 8 Conclusion
- References
- Grapes Visual Segmentation for Harvesting Robots Using Local Texture Descriptors
- 1 Introduction
- 2 Visual Computing for Harvesting Robots
- 3 Local Binary Patterns
- 4 LBP-Based Grapes Segmentation
- 5 Simulations
- 6 Discussions and Conclusions
- References
- Open Space Attraction Based Navigation in Dark Tunnels for MAVs
- 1 Introduction
- 1.1 Motivation and Related Works
- 1.2 Contributions
- 1.3 Outline
- 2 Methodology
- 2.1 Singe Image Depth Estimation
- 2.2 Open Area Centroid Extraction
- 3 Results
- 3.1 Simulation Results
- 3.2 Experimental Results
- 4 Conclusions
- References
- 6D Gripper Pose Estimation from RGB-D Image
- 1 Introduction
- 2 Dataset
- 3 CNN
- 4 Evaluation
- 5 Conclusions
- References
- Robust Rotation Interpolation Based on SO(n) Geodesic Distance
- 1 Introduction
- 2 Main Theory
- 3 Simulation Results
- 4 Conclusion
- References
- Estimation of Wildfire Size and Location Using a Monocular Camera on a Semi-autonomous Quadcopter
- 1 Introduction
- 1.1 Related Works
- 1.2 System Description
- 2 Proposed Method
- 3 Evaluation
- 3.1 Results
- 4 Conclusion
- References
- V-Disparity Based Obstacle Avoidance for Dynamic Path Planning of a Robot-Trailer
- 1 Introduction
- 2 Processing of Stereo Image Pairs
- 2.1 Disparity and V-Disparity Computation
- 2.2 Obstacle Extraction from V-Disparity
- 3 Dynamic Path Planning and Obstacle Avoidance
- 4 Experimental Evaluation
- 5 Conclusions
- References
- Intersection Recognition Using Results of Semantic Segmentation for Visual Navigation
- 1 Introduction
- 2 Related Work
- 2.1 Recent Advances in Semantic Segmentation
- 2.2 Visual Navigation Using a Topological Map
- 3 Intersection Recognition Using Results of Semantic Segmentation
- 3.1 Feature Extraction
- 3.2 Classification
- 4 Evaluation
- 4.1 A Dataset Used for Evaluation
- 4.2 Classification Accuracy
- 4.3 Running Experiment
- 5 Conclusion
- References
- Autonomous MAV Navigation in Underground Mines Using Darkness Contours Detection
- 1 Introduction
- 1.1 Background and Motivation
- 1.2 Contributions
- 1.3 Outline
- 2 System Architecture
- 3 Methodology
- 3.1 Step 1. Converts the RGB Image to a Binary Image Using Otsu's Threshold
- 3.2 Step 2. Finding Boundaries of the Darkness Using the Moore-Neighbor Tracing Algorithm
- 3.3 Step 3. Identify the Darkness in the Tunnel as the Background Object with the Largest Area
- 3.4 Step 4. Calculate the Heading Rate Correction Based on the Centroid of the Darkness
- 4 Results
- 4.1 Experimental Setup
- 4.2 Experimental Evaluations
- 5 Conclusions
- References
- Improving Traversability Estimation Through Autonomous Robot Experimentation
- 1 Introduction
- 2 Autonomous Data Collection
- 3 Adapting Traversability Estimation
- 4 Experimental Results and Discussion
- 4.1 Data Acquisition
- 4.2 Baseline
- 4.3 Training
- 4.4 Results
- 4.5 Error Analysis
- 5 Conclusion and Future Work
- References
- Towards Automated Order Picking Robots for Warehouses and Retail
- 1 Introduction
- 2 Related Work
- 2.1 Object Perception and Localization
- 2.2 Motion Planning
- 3 System
- 4 Object Detection and Pose Estimation
- 4.1 Method
- 4.2 Evaluation
- 5 Motion Planning
- 5.1 Method
- 5.2 Evaluation
- 6 System Evaluation
- 7 Conclusions and Future Work
- References
- Vision Systems Applications
- Tillage Machine Control Based on a Vision System for Soil Roughness and Soil Cover Estimation
- 1 Introduction
- 1.1 Related Work
- 1.2 Contribution
- 2 Online Machine Control
- 3 Roughness Estimation
- 3.1 Environmental Influence Handling
- 4 Residue and Soil Cover Detection
- 5 Experimental Results
- 5.1 Roughness Estimation
- 5.2 Soil Cover Detection
- 5.3 Machine Control
- 6 Conclusions and Future Work
- References
- Color Calibration on Human Skin Images
- 1 Introduction
- 1.1 Paper Structure
- 1.2 Light Absorption on Human Skin
- 1.3 Delta E Lg
- 1.4 CIE Illuminant
- 1.5 ColorChecker
- 1.6 Color Calibration
- Preliminaries and Related Works
- 2 Color Calibration Techniques and Results
- 2.1 Leave-One-Out Cross-validation Evaluation Method (EM)
- 2.2 Color Calibration Frameworks
- 3 Experimental Results
- 4 Conclusion
- References
- Hybrid Geometric Similarity and Local Consistency Measure for GPR Hyperbola Detection
- 1 Introduction
- 2 Method Description
- 2.1 Peak Detection and Segmentation
- 2.2 Discrete Wavelet Transform Decomposition
- 2.3 Generation of Hyperbolic Templates
- 2.4 Hybrid Measure for Hyperbola Hypotheses
- 3 Evaluation
- 4 Conclusions
- References
- Towards a Professional Gesture Recognition with RGB-D from Smartphone
- 1 Introduction
- 2 State of Art
- 2.1 Qualitative Comparison Between Pose Estimation Frameworks
- 2.2 Machine and Deep Learning Frameworks for Mobile Devices
- 2.3 Gesture Recognition Methods
- 3 Objectives
- 4 Overall Pipeline
- 4.1 Video Recording Using the Smartphone
- 4.2 Pose Estimation
- 4.3 Gesture Recognition
- 4.4 Smartphone Application
- 5 Datasets
- 6 Results
- 6.1 Pose Estimation Comparison Using the TVA and SW Datasets
- 6.2 Gesture Recognition Comparisons Using the TVA Dataset: 2D vs 3D and 2 vs 7 Joints
- 6.3 Gesture Recognition Comparison Using Three Different Camera Positions from the SW Dataset
- 6.4 Comparison Mixing Gestures and Data from the TVA and the SW Datasets
- 7 Conclusions and Future Work
- References
- Data Anonymization for Data Protection on Publicly Recorded Data
- 1 Introduction
- 2 Data Protection on Publicly Recorded Data
- 3 Data Anonymization
- 3.1 Face Anonymization
- 3.2 License Plate Anonymization
- 4 Anonymization of Image Regions
- 5 Datasets
- 6 Evaluation
- 6.1 Face Anonymization
- 6.2 License Plate Anonymization
- 6.3 Overall Evaluation
- 6.4 Runtime
- 7 Conclusion
- References
- Water Streak Detection with Convolutional Neural Networks for Scrubber Dryers
- 1 Introduction
- 2 Related Work
- 3 Development Process
- 3.1 Requirements Analysis
- 3.2 Electromechanic Measurement System
- 3.3 Vision System
- 4 Vision-Based Water Streak Detection System
- 4.1 Hardware
- 4.2 Software
- 5 Evaluation
- 5.1 Water Streak Data Set
- 5.2 Experimental Setup
- 5.3 Results
- 6 Conclusions and Future Work
- References
- Segmenting and Detecting Nematode in Coffee Crops Using Aerial Images
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Data Collect
- 3.2 Pre-processing
- 3.3 Feature Extraction
- 3.4 Training and Test Sets
- 3.5 Supervised Learning
- 4 Experimental Results
- 5 Conclusions
- References
- Automatic Detection of Obstacles in Railway Tracks Using Monocular Camera
- 1 Introduction
- 2 Problem Statement
- 3 Algorithm Breakdown
- 3.1 Preprocessing the Image
- 3.2 Rail Segmentation
- 3.3 Obstacle Detection
- 4 Validation
- 5 Conclusion
- References
- A Sequential Approach for Pain Recognition Based on Facial Representations
- 1 Introduction
- 2 Related Work
- 3 Dataset Description
- 4 Methodology
- 4.1 Preprocessing
- 4.2 Data Balancing
- 4.3 Frame-by-Frame Analysis
- 4.4 Temporal Analysis
- 5 Experiments and Results
- 5.1 Balancing Results
- 5.2 Testing
- 6 Conclusions and Future Works
- References
- A Computer Vision System Supporting Blind People - The Supermarket Case
- 1 Introduction
- 2 Related Work
- 3 The Concept of the Proposed Supermarket Application
- 4 Onsite Visits Dataset and Annotation
- 5 Methodology
- 5.1 Distinguishing Between Product, Shelf, Trail and Other
- 5.2 Detecting Text in Food Packages
- 6 Experiments
- 6.1 Distinguishing Between Abstraction Levels
- 6.2 Classifying Trail, Shelf and Product Images
- 6.3 Evaluating the System as a Whole
- 7 The Implementation of the Proposed Supermarket Application
- 8 Conclusions
- References
- High-Level and Learning Vision Systems
- Comparing Ellipse Detection and Deep Neural Networks for the Identification of Drinking Glasses in Images
- 1 Introduction
- 2 Methodology and Experimental Setup
- 2.1 Test Data Set
- 2.2 Ellipse Detection
- 2.3 Deep Learning
- 3 Results
- 3.1 Ellipse Detection
- 3.2 Deep Learning
- 4 Discussion and Conclusion
- References
- Detecting Video Anomaly with a Stacked Convolutional LSTM Framework
- 1 Introduction
- 2 Related Work
- 2.1 Anomaly Detection with Hand-Crafted Features
- 2.2 Anomaly Detection with Deep Learning
- 3 Our Approach
- 3.1 Network Architecture
- 3.2 Convolutional LSTM
- 3.3 Anomaly Detection
- 4 Experiments
- 4.1 Datasets
- 4.2 Data Preprocessing
- 4.3 Implementation Details
- 4.4 Evaluation with Real-World Anomaly Detection Datasets
- 5 Conclusions
- References
- Multi-scale Relation Network for Few-Shot Learning Based on Meta-learning
- 1 Introduction
- 2 Related Work
- 3 Model
- 3.1 Problem Definition
- 3.2 Model
- 4 Experiments
- 4.1 Omniglot
- 4.2 MiniImageNet
- 5 Conclusion and Future Work
- References
- Planar Pose Estimation Using Object Detection and Reinforcement Learning
- 1 Introduction
- 2 Related Work
- 3 Proposed System Architecture
- 3.1 Model
- 4 Experimental Setup and Data Generation
- 4.1 Object Detector
- 4.2 Reinforcement Learning
- 5 Experimental Evaluation
- 6 Conclusion
- References
- A Two-Stage Approach for Commonality-Based Temporal Localization of Periodic Motions
- 1 Introduction
- 2 Related Work
- 3 P-MUCOS-S2: Commonality-Based Periodicity Detection
- 4 Experimental Results
- 5 Conclusions
- References
- Deep Residual Temporal Convolutional Networks for Skeleton-Based Human Action Recognition
- 1 Introduction
- 2 Related Work
- 3 Methods
- 4 Results
- 5 Discussion
- References
- Monte Carlo Tree Search on Directed Acyclic Graphs for Object Pose Verification
- 1 Introduction
- 2 Related Work
- 3 6D Object Pose Verification
- 3.1 Generation of the Hypotheses Pool
- 3.2 Generation of Candidate Solutions and Verification
- 4 Results
- 4.1 YCB-VIDEO
- 4.2 Convergence and Run Time
- 4.3 Discussion
- 5 Conclusion
- References
- Leveraging Symmetries to Improve Object Detection and Pose Estimation from Range Data
- 1 Introduction
- 2 PPF Overview
- 2.1 Building Blocks
- 2.2 Pipeline
- 3 Our Approach
- 3.1 Symmetry Classes and Notation
- 3.2 Modifications of Model Description and Voting Space
- 3.3 Pose Clustering
- 4 Automatic Symmetry Extraction
- 5 Experimental Evaluation
- 5.1 Feature Matching Performance
- 5.2 Pose Estimation Performance
- 5.3 Computation Time
- 6 Conclusion
- References
- Towards Meaningful Uncertainty Information for CNN Based 6D Pose Estimates
- 1 Introduction
- 1.1 Motivation
- 1.2 Contribution
- 2 Related Work
- 2.1 CNN Based Pose Estimation
- 2.2 PnP and Variants
- 2.3 Gaussian Distributions and Gauss-Newton on SE(3)
- 3 Approach
- 4 CNN Details
- 4.1 Loss Function and Learning Procedure
- 4.2 Depth Sensor Uncertainty CNN
- 5 Pragmatic gPnP Algorithm
- 5.1 Perspective Measurements
- 5.2 Depth Measurements
- 5.3 Gauss-Newton Iteration
- 5.4 Calculation of the Initial Guess
- 6 Experimental Results
- 7 Conclusion and Future Work
- References
- QuiltGAN: An Adversarially Trained, Procedural Algorithm for Texture Generation
- 1 Introduction
- 1.1 Motivation
- 1.2 Related Work
- 1.3 Problem Definition
- 1.4 Proposed Method
- 1.5 Adversarial Loss
- 1.6 Image Quilting
- 2 Experimental Results
- 3 Conclusion
- References
- Automated Mechanical Multi-sensorial Scanning
- 1 Introduction
- 2 Related Work
- 3 Motivation and Contribution
- 4 System Implementation
- 4.1 Acquisition Setup
- 4.2 3D Model Reconstruction Module
- 4.3 Automatic Sensor Acquisition
- 5 Experimental Results
- 6 Conclusions
- References
- Cognitive Vision Systems
- Point Pair Feature Matching: Evaluating Methods to Detect Simple Shapes
- 1 Introduction
- 2 Point Pair Feature Matching
- 3 Related Works
- 3.1 Planar Surfaces and Rotational Symmetries
- 3.2 Noisy Scenes
- 3.3 Computational Complexity
- 3.4 Post-processing
- 4 Methodology
- 4.1 Augmented Feature
- 4.2 Model Creation
- 4.3 Matching
- 4.4 Pose Clustering
- 4.5 Post-processing
- 5 Experiments
- 5.1 Datasets
- 5.2 Metrics
- 5.3 Results
- 6 Conclusion
- References
- Multi-DisNet: Machine Learning-Based Object Distance Estimation from Multiple Cameras
- 1 Introduction
- 2 Related Work
- 3 Machine Learning Based Object Distance Estimation from Multi-sensory System
- 3.1 Multi-DisNet - Dataset
- 3.2 Multi-DisNet - Architecture
- 4 Evaluation
- 5 Conclusion
- References
- Hierarchical Image Inpainting by a Deep Context Encoder Exploiting Structural Similarity and Saliency Criteria
- 1 Introduction
- 2 Context Encoder
- 2.1 Network Architecture
- 2.2 Saliency Map
- 2.3 Influence Map
- 3 Loss Function
- 3.1 Reconstruction Loss
- 3.2 Adversarial Loss
- 4 Results and Future Work
- References
- Online Information Augmented SiamRPN
- 1 Introduction
- 2 SiamRPN
- 3 Proposed Method
- 4 Experimental Results
- 5 Conclusion
- References
- Deep-Learning-Based Computer Vision System for Surface-Defect Detection
- 1 Introduction
- 2 Related Work
- 3 Deep-Learning-Based Optical Inspection System
- 3.1 Hardware and Image Acquisition
- 3.2 Surface Inspection
- 4 Evaluation
- 4.1 Evaluation Setup
- 4.2 Results
- 4.3 Computational Cost
- 5 Discussion and Conclusion
- References
- Color-Guided Adaptive Support Weights for Active Stereo Systems
- 1 Introduction
- 2 Related Work
- 3 Proposed Method
- 3.1 Network Architecture
- 3.2 Color Information Preprocessing
- 3.3 Color-Guided Adaptive Support Weights
- 3.4 Loss Function
- 4 Experiments
- 5 Conclusions
- References
- Image Enhancing in Poorly Illuminated Subterranean Environments for MAV Applications: A Comparison Study
- 1 Introduction
- 2 Methodology
- 3 Dataset Overview
- 3.1 Description of Datasets
- 3.2 Evaluation Strategies
- 4 Evaluation
- 4.1 Future Directions
- 5 Conclusions
- References
- Robust Optical Flow Estimation Using the Monocular Epipolar Geometry
- 1 Introduction
- 2 Optical Flow Model
- 3 Enhancement of the Fundamental Matrix
- 4 Experiments
- 4.1 Comparison to the State-of-the-art Methods
- 4.2 Evaluation of the Fundamental Matrix Re-estimation
- 5 Conclusion
- References
- 3D Hand Tracking by Employing Probabilistic Principal Component Analysis to Model Action Priors
- 1 Introduction
- 1.1 Related Work
- 2 Method Description
- 2.1 Hand Model
- 2.2 Action PPCA Training
- 2.3 PPCA Hand Tracking
- 3 Experiments
- 4 Summary
- References
- Cross-Domain Interpolation for Unpaired Image-to-Image Translation
- 1 Introduction
- 2 Related Works
- 3 Background
- 3.1 Generative Adversarial Networks - GANs
- 4 Cross-Domain Architecture
- 4.1 Loss Function
- 5 Experiments and Results
- 5.1 Implementation Details
- 5.2 Metrics
- 6 Conclusions and Future Works
- References
- A Short-Term Biometric Based System for Accurate Personalized Tracking
- 1 Introduction
- 1.1 Current Approaches
- 1.2 Motivation
- 2 System Architecture
- 2.1 Preprocessing
- 3 3D Weighted Walkthroughs as Short-Term Biometric Feature
- 4 Experimental Results
- 4.1 Dataset
- 4.2 Results
- 5 Conclusion
- References
- Workshop on: Movement Analytics and Gesture Recognition for Human- Machine Collaboration in Industry 4.0
- Real-Time Gestural Control of Robot Manipulator Through Deep Learning Human-Pose Inference
- 1 Introduction
- 2 Pose Estimation
- 2.1 2D Pose Estimation
- 2.2 3D Pose Estimation
- 3 Real-Time Robot Control
- 3.1 Inverse Kinematics (IK)
- 3.2 Forward Kinematics (FK)
- 4 Experiments
- 5 Conclusions and Future Work
- References
- A Comparison of Computational Intelligence Techniques for Real-Time Discrete Multivariate Time Series Classification of Conducting Gestures
- 1 Introduction
- 2 Literature Review
- 2.1 Data Collection
- 2.2 Computational Intelligence (CI) Implementations
- 3 Methods
- 3.1 Data Collection
- 3.2 Pre-processing
- 3.3 Computational Intelligence Techniques
- 4 Results and Discussions
- 4.1 Individual Algorithms
- 4.2 Generative Vs Discriminative
- 4.3 Dynamic Vs Static
- 5 Conclusions
- References
- A Deep Network for Automatic Video-Based Food Bite Detection
- 1 Introduction
- 2 Related Work
- 3 Proposed Methodology
- 4 Experimental Evaluation
- 4.1 Dataset
- 4.2 Data Preprocessing and Augmentation
- 4.3 Hyper-parameter Optimization
- 4.4 Results on Continuous Bite Detection
- 5 Conclusions
- References
- Extracting the Inertia Properties of the Human Upper Body Using Computer Vision
- 1 Introduction
- 2 Methods
- 2.1 Data Collection
- 2.2 The Kinematic Model of the Human Body
- 2.3 Calculating the Tensors of Inertia
- 2.4 Experiment
- 3 Results and Discussion
- 4 Conclusions and Future Work
- References
- Single Fingertip Detection Using Simple Geometric Properties of the Hand Image: A Case Study for Augmented Reality in an Educational App
- 1 Introduction
- 2 Interacting with Real, Virtual and Augmented Space
- 3 Description of the Algorithm
- 4 Technology Necessities and the Proposed Algorithm
- 5 Conclusion
- References
- Leveraging Pre-trained CNN Models for Skeleton-Based Action Recognition
- 1 Introduction
- 2 Related Works
- 3 Background
- 3.1 Review of Convolutional Neural Networks (CNNs)
- 3.2 Data Representation
- 4 Experimental Results
- 4.1 Data Structure
- 4.2 Training the Deep Network
- 4.3 Models Evaluation: Results and Discussion
- 5 Conclusion
- References
- Workshop on: Cognitive and Computer Vision Assisted Systems for Energy Awareness and Behavior Analysis
- An Augmented Reality Game for Energy Awareness
- 1 Introduction
- 2 Related Work and Background
- 2.1 Games for Energy Awareness and Sustainability
- 2.2 Augmented Reality Applications for Consumers
- 3 The FunergyAR Augmented Reality Game
- 3.1 Game Mechanics
- 3.2 Game Implementation
- 3.3 Coupling FunergyAR with a Traditional Card Game
- 4 Experience, Discussion and Conclusions
- References
- Energy Consumption Patterns of Residential Users: A Study in Greece
- 1 Introduction
- 2 Smart Meters
- 2.1 Hardware and Software Infrastructure
- 3 Case Study: Greek Residential Houses
- 3.1 User Profiles
- 3.2 Climate in Thessaloniki
- 3.3 Use of Energy Related to the Outside Temperature
- 3.4 Energy Consumption Patterns
- 4 Conclusions
- References
- Overview of Legacy AC Automation for Energy-Efficient Thermal Comfort Preservation
- 1 Introduction
- 2 Sensor Equipment and Control Platform
- 2.1 Decoding Process
- 3 User Graphical Interface
- 4 Conclusions
- References
- Can I Shift My Load? Optimizing the Selection of the Best Electrical Tariff for Tertiary Buildings
- 1 Introduction
- 2 Tariff Model
- 3 Analytical Optimisation of the 6.1 Electric Tariff
- 4 Experimental Section
- 4.1 Datasets
- 5 Results and Discussion
- 5.1 Tariff Optimisation
- 5.2 Savings Forecasting
- 5.3 Convergence
- 6 Conclusions
- References
- Occupancy Inference Through Energy Consumption Data: A Smart Home Experiment
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 4 Experimental Results
- 4.1 Pilot Setup and Data Collection
- 4.2 Evaluation Metrics
- 4.3 Evaluation Results
- 5 Conclusions
- References
- A Dynamic Convergence Algorithm for Thermal Comfort Modelling
- 1 Introduction
- 2 Clothing Insulation and Metabolic Rate Estimation
- 2.1 Clothing Insulation and Metabolic Rate Estimation
- 2.2 Indoor Building Study
- 3 Results
- 4 Conclusions
- References
- Thermal Comfort Metabolic Rate and Clothing Inference
- 1 Introduction
- 2 Thermal Comfort Calculation
- 3 Metabolic Rate and Clothing Insulation Prediction from User Feedback
- 4 Experimental Results
- 5 Conclusions
- References
- User-Centered Visual Analytics Approach for Interactive and Explainable Energy Demand Analysis in Prosumer Scenarios
- 1 Introduction
- 2 Related Work
- 3 Identification of Needs and Requirements
- 4 Approach
- 5 System Design
- 6 Evaluation
- 7 Conclusions
- References
- Workshop on: Vision-Enabled UAV and Counter-UAV Technologies for Surveillance and Security of Critical Infrastructures
- Critical Infrastructure Security Against Drone Attacks Using Visual Analytics
- 1 Introduction
- 2 Literature Review
- 3 Conceptual Design of the Proposed Framework
- 4 Training Framework for Drone Detection
- 5 Tracking Interface with Raspberry Pi Sensing Equipment
- 6 Experimental Results
- 7 Conclusion and Future Work
- References
- Classification of Drones with a Surveillance Radar Signal
- 1 Introduction
- 2 Radar Signal Processing
- 2.1 Signal Processing and Available Pieces of Information
- 2.2 Features Definition
- 2.3 Radar Parameters and Configurations
- 2.4 Measurement Campaign
- 3 Classification Algorithm
- 3.1 Training Process
- 3.2 Performance Evaluation
- 4 Experimental Results
- 5 Conclusions
- References
- Minimal-Time Trajectories for Interception of Malicious Drones in Constrained Environments
- 1 Introduction
- 2 Interception Capability with Obstacles
- 3 Optimization Strategy
- 4 Obstacle Avoidance
- 5 Results
- 6 Conclusions
- References
- UAV Classification with Deep Learning Using Surveillance Radar Data
- 1 Introduction
- 2 Related Work
- 2.1 Tracking Radars
- 2.2 Surveillance Radars
- 3 Proposed Pipeline
- 3.1 Radar Parameters
- 3.2 Signal Processing
- 3.3 UAV Classification Pipeline and DNN Model
- 4 Experiments
- 4.1 Training and Testing Settings
- 4.2 Dataset Description
- 4.3 Evaluation
- 5 Conclusion
- References
- UAV Localization Using Panoramic Thermal Cameras
- 1 Introduction
- 2 Panoramic Thermal Camera Concept: Application to UAV Surveillance
- 2.1 Fixed Versus Rotating Camera
- 2.2 Image Definition
- 2.3 Existing Camera
- 3 Target Localization
- 3.1 Active Range Estimation
- 3.2 Passive Range Estimation
- 3.3 3D Localization Using Thermal Cameras
- 3.4 Object Pairing
- 3.5 Localization Estimations
- 3.6 Using More Than Two Cameras
- 4 Conclusion
- References
- Multimodal Deep Learning Framework for Enhanced Accuracy of UAV Detection
- 1 Introduction
- 2 Related Work
- 2.1 Multimodal Deep Learning
- 2.2 Multilayer Perceptron
- 3 Fusion Deep Learning Model
- 3.1 Fusion Model Architecture
- 3.2 Multilayer Perceptron Algorithm Initialization
- 3.3 Training Data
- 4 Experimental Results
- 5 Conclusion
- References
- Multi-scale Feature Fused Single Shot Detector for Small Object Detection in UAV Images
- 1 Introduction
- 2 System Overview
- 2.1 SSD
- 2.2 Deconvolution Module
- 2.3 Shallow Feature Concatenation Module
- 3 Experiments
- 3.1 Setup
- 3.2 Dataset
- 3.3 Results
- 4 Conclusion
- References
- Autonomous Swarm of Heterogeneous Robots for Surveillance Operations
- 1 Introduction
- 2 Detection Services and User-Interface Services of the Proposed Architecture
- 2.1 Detection Services
- 2.2 Navigational Services
- 3 Architecture and Pilot Use Cases
- 3.1 System Architecture
- 3.2 Use Cases
- 4 Conclusion
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.