You are previewing Computer Vision and Pattern Recognition in Environmental Informatics.
O'Reilly logo
Computer Vision and Pattern Recognition in Environmental Informatics

Book Description

Computer Vision and Pattern Recognition (CVPR) together play an important role in the processes involved in environmental informatics due to their pervasive, non-destructive, effective, and efficient natures. As a result, CVPR has made significant contributions to the field of environmental informatics by enabling multi-modal data fusion and feature extraction, supporting fast and reliable object detection and classification, and mining the intrinsic relationship between different aspects of environmental data. Computer Vision and Pattern Recognition in Environmental Informatics describes a number of methods and tools for image interpretation and analysis, which enables observation, modelling, and understanding of environmental targets. In addition to case studies on monitoring and modeling plant, soil, insect, and aquatic animals, this publication includes discussions on innovative new ideas related to environmental monitoring, automatic fish segmentation and recognition, real-time motion tracking systems, sparse coding and decision fusion, and cell phone image-based classification and provides useful references for professionals, researchers, engineers, and students with various backgrounds within a multitude of communities.

Table of Contents

  1. Cover
  2. Title Page
  3. Copyright Page
  4. Book Series
    1. Mission
    2. Coverage
  5. Editorial Advisory Board
  6. Foreword
  7. Preface
    1. SECTION 1: COMPUTER VISION AND PATTERN RECOGNITION METHODS FOR AQUATIC ANIMAL DETECTION AND MONITORING
    2. SECTION 2: COMPUTER VISION AND PATTERN RECOGNITION METHODS FOR INSECT RECOGNITION AND MODELLING
    3. SECTION 3: COMPUTER VISION AND PATTERN RECOGNITION METHODS FOR PLANT AND SOIL ANALYSIS
    4. ENDNOTES
  8. Acknowledgment
  9. Section 1: Computer Vision and Pattern Recognition Methods for Aquatic Animal Detection and Monitoring
    1. Chapter 1: Hierarchal Decomposition for Unusual Fish Trajectory Detection
      1. ABSTRACT
      2. HIERARCHAL DECOMPOSITION FOR UNUSUAL FISH TRAJECTORY DETECTION
      3. RECENT WORKS
      4. PROPOSED METHOD
      5. EXPERIMENTS AND RESULTS
      6. CONCLUSION AND FUTURE WORKS
      7. REFERENCES
    2. Chapter 2: Machine Learning for Detecting Scallops in AUV Benthic Images
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. MAIN FOCUS OF THE CHAPTER
      5. SOLUTIONS AND RECOMMENDATIONS
      6. RESULTS AND DISCUSSION
      7. FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. ACKNOWLEDGMENT
      10. REFERENCES
      11. KEY TERMS AND DEFINITIONS
    3. Chapter 3: Fish Counting and Measurement
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. FRAMEWORK
      5. FUTURE RESEARCH DIRECTIONS
      6. CONCLUSION
      7. ACKNOWLEDGEMENT
      8. REFERENCES
    4. Chapter 4: Automated Whale Blow Detection in Infrared Video
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. CHARACTERISTICS OF WHALE BLOWS IN INFRARED VIDEO
      5. SOLUTION BASED ON NEURAL NETWORKS (MULTI-LAYER PERCEPTRON)
      6. SOLUTION BASED ON LOCAL RELATIVE VARIANCE AND FRACTAL FEATURES
      7. SOLUTION BASED ON CONVOLUTIONAL NEURAL NETWORKS
      8. FUTURE RESEARCH DIRECTIONS
      9. CONCLUSION
      10. REFERENCES
    5. Chapter 5: Automatic Fish Segmentation and Recognition for Trawl-Based Cameras
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. THE CAM-TRAWL SYSTEM
      5. FISH SEGMENTATION
      6. FISH SPECIES RECOGNITION
      7. EXPERIMENTAL RESULTS
      8. DISCUSSION
      9. FUTURE RESEARCH DIRECTIONS
      10. CONCLUSION
      11. REFERENCES
    6. Chapter 6: Visual Tracking of Box Jellyfish
      1. ABSTRACT
      2. INTRODUCTION
      3. EXPERIMENTAL SETUP
      4. SYSTEM OVERVIEW
      5. DETECTION
      6. CLUSTERING
      7. TRACKING
      8. EXPERIMENTAL RESULTS
      9. CONCLUSION
      10. ACKNOWLEDGEMENT
      11. REFERENCES
  10. Section 2: Computer Vision and Pattern Recognition Methods for Insect Recognition and Modelling
    1. Chapter 7: Insect Recognition Using Sparse Coding and Decision Fusion
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. DISCRIMINATIVE CODING METHODS
      5. DECISION FUSION
      6. APPLICATION TO INSECT RECOGNITION
      7. CONCLUSION
      8. ACKNOWLEDGMENT
      9. REFERENCES
      10. KEY TERMS AND DEFINITIONS
    2. Chapter 8: Skeletonization of Edges Extracted by Natural Images
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. A SKELETONIZATION METHOD BASED ON DIVERGENCE FLOW
      5. FUTURE RESEARCH DIRECTIONS
      6. CONCLUSION
      7. REFERENCES
      8. KEY TERMS AND DEFINITIONS
      9. APPENDIX 1
      10. APPENDIX 2
    3. Chapter 9: Categorization of Plant and Insect Species via Shape Analysis
      1. ABSTRACT
      2. INTRODUCTION
      3. RELATED WORK
      4. METHOD OVERVIEW
      5. THE CLIQUE HISTOGRAM
      6. THE GRAPH VECTOR
      7. THE PHOW FEATURES
      8. FEATURE FUSION
      9. SYSTEM IMPLEMENTATION
      10. EXPERIMENTS
      11. LEAF CATEGORIZATION
      12. BUTTERFLY RECOGNITION
      13. CONCLUSION
      14. REFERENCES
    4. Chapter 10: 3D Modeling for Environmental Informatics
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. PARAMETRIC POSE MANIFOLD
      5. EXPERIMENTS
      6. CONCLUSION
      7. REFERENCES
  11. Section 3: Computer Vision and Pattern Recognition Methods for Plant and Soil Analysis
    1. Chapter 11: Automatic Estimation of Soil Biochar Quantity via Hyperspectral Imaging
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND KNOWLEDGE
      4. HYPERSPECTRAL UNMIXING FOR SOIL BIOCHAR QUANTIFICATION
      5. SOIL DATA ANALYSIS
      6. CONCLUSION
      7. REFERENCES
    2. Chapter 12: Plant Classification for Field Robots
      1. ABSTRACT
      2. INTRODUCTION
      3. RELATED WORK
      4. ROBOT HARDWARE AND FIELD SITUATION
      5. PLANT CLASSIFICATION FRAMEWORK
      6. EXPERIMENTS AND RESULTS
      7. DISCUSSION AND FUTURE RESEARCH DIRECTIONS
      8. CONCLUSION
      9. ACKNOWLEDGMENT
      10. REFERENCES
      11. KEY TERMS AND DEFINITIONS
      12. APPENDIX
    3. Chapter 13: 3D Plant Modelling Using Spectral Data from Visible to Near Infrared Range
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. HYPERSPECTRAL DATA
      5. IMAGE PREPROCESSING
      6. OVERVIEW OF STRUCTURE FROM MOTION APPROACH
      7. REGISTERING 3D HYPERSPECTRAL MODELS
      8. EXPERIMENTS
      9. COMPARISON OF 3D REGISTRATION METHODS ON SYNTHETIC DATA
      10. CONCLUSION
      11. REFERENCES
    4. Chapter 14: Cell Phone Image-Based Plant Disease Classification
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. PATTERN RECOGNITION PIPELINE FOR PLANT DISEASE CLASSIFICATION
      5. CLASSIFICATION OF WHEAT DISEASE SYMPTOMS
      6. CLASSIFICATION OF SUGAR BEET DISEASE SYMPTOMS
      7. SOLUTIONS AND RECOMMENDATIONS
      8. FUTURE RESEARCH DIRECTIONS
      9. CONCLUSION
      10. ACKNOWLEDGMENT
      11. REFERENCES
      12. KEY TERMS AND DEFINITIONS
    5. Chapter 15: A Large Margin Learning Method for Matching Images of Natural Objects with Different Dimensions
      1. ABSTRACT
      2. INTRODUCTION
      3. RELATED WORK
      4. PROPOSED METHOD
      5. EXPERIMENTS
      6. CONCLUSION
      7. REFERENCES
    6. Chapter 16: An Overview of Tree Species Identification from T-LiDAR Data
      1. ABSTRACT
      2. TREE SPECIES IDENTIFICATION FROM T-LIDAR DATA: AN OVERVIEW
      3. FOREST INVENTORY
      4. IDENTIFICATION OF TREE SPECIES FOR FOREST INVENTORY: FROM THE NATURE TO THE COMPUTER
      5. CONCLUSION AND PERSPECTIVES
      6. REFERENCES
  12. Compilation of References
  13. About the Contributors