Roadside Video Data Analysis, Softcover reprint of the original 1st ed. 2017 Deep Learning Studies in Computational Intelligence Series, Vol. 711
Auteurs : Verma Brijesh, Zhang Ligang, Stockwell David
1 Introduction
Background
Collection of Roadside Video Data
Industry Data
Benchmark Data
Applications Using Roadside Video Data
Outline of the Book
2 Roadside Video Data Analysis Framework
Overview
Methodology
Preprocessing of Roadside Video Data
Segmentation of Roadside Video Data into Objects
Vegetation, Roads, Signs, Sky
Feature Extraction from Objects
Classification of Roadside Objects
Applications of Classified Roadside Objects
Algorithms and Pseudocodes
3 Learning and Impact on Roadside Video Data Analysis
Neural Network Learning
Support Vector Machine Learning
K-Nearest Neighbor Learning
Cluster Learning
Hierarchical Learning
Fuzzy C-Means Learning
Region Merging Learning
Probabilistic Learning
Ensemble Learning
Deep Learning
4 Applications in Roadside Fire Risk Assessment
Scene Labeling
Roadside Vegetation Classification
Vegetation Biomass Estimation
5 Conclusions and Future Insights
Recommendations
New Challenges
New Opportunities and Applications
Highlights deep learning, to better understand roadside video data segmentation
Provides learning techniques based on concepts for roadside video data processing
Discusses fire risk assessment based on roadside vegetation biomass estimation
Includes supplementary material: sn.pub/extras
Date de parution : 12-2018
Ouvrage de 189 p.
15.5x23.5 cm
Date de parution : 05-2017
Ouvrage de 189 p.
15.5x23.5 cm
Thème de Roadside Video Data Analysis :
Mots-clés :
Feature extraction; Classified roadside objects; Roadside Fire Risk Assessment; Neural Network Learning; Support Vector Machine Learning; K-Nearest Neighbor Learning; Scene labeling; Cluster Learning; Vegetation biomass estimation; Hierarchical Learning; Fuzzy C-Means Learning; Probabilistic Learning; Ensemble Learning