Representations, Analysis and Recognition of Shape and Motion from Imaging Data

1. Front Matter

   Pages i-xii

   PDF

2. On Analyzing Motion Data

   1. Front Matter

      Pages 1-1

      PDF

   2. A Comparison of Scene Flow Estimation Paradigms

      • Iraklis Tsekourakis, Philippos Mordohai

      Pages 3-19

   3. On the Reliability of LSTM-MDL Models for Pedestrian Trajectory Prediction

      • Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens

      Pages 20-34

   4. Pedestrian Tracking in the Compressed Domain Using Thermal Images

      • Ichraf Lahouli, Robby Haelterman, Zied Chtourou, Geert De Cubber, Rabah Attia

      Pages 35-44

   5. An Image Processing Framework for Automatic Tracking of Wave Fronts and Estimation of Wave Front Velocity for a Gas Experiment

      • Samee Maharjan, Dag Bjerketvedt, Ola Marius Lysaker

      Pages 45-55

   6. The Algorithm and Software for Timber Batch Measurement by Using Image Analysis

      • Andrey V. Mehrentsev, Artem V. Kruglov

      Pages 56-65

3. Deep Learning on Image and Shape Data

   1. Front Matter

      Pages 67-67

      PDF

   2. Stereo Matching Confidence Learning Based on Multi-modal Convolution Neural Networks

      • Zehua Fu, Mohsen Ardabilian, Guillaume Stern

      Pages 69-81

   3. Multi-person Head Segmentation in Low Resolution Crowd Scenes Using Convolutional Encoder-Decoder Framework

      • Muhammad Shaban, Arif Mahmood, Somaya Al-maadeed, Nasir Rajpoot

      Pages 82-92

   4. CrossEncoder: Towards 3D-Free Depth Face Recovery and Fusion Scheme for Heterogeneous Face Recognition

      • Wuming Zhang, Liming Chen

      Pages 93-109

   5. Neural Approach for Context Scene Image Classification Based on Geometric, Texture and Color Information

      • Ameni Sassi, Wael Ouarda, Chokri Ben Amar, Serge Miguet

      Pages 110-120

   6. Self-learning Framework with Temporal Filtering for Robust Maritime Vessel Detection

      • Amir Ghahremani, Egor Bondarev, Peter H. N. de With

      Pages 121-135

4. 2D and 3D Pattern Classification

   1. Front Matter

      Pages 137-137

      PDF

   2. Rapid Urban 3D Modeling for Drone-Based Situational Awareness Assistance in Emergency Situations

      • Inge Coudron, Toon Goedemé

      Pages 139-150

   3. Defining Mesh-LBP Variants for 3D Relief Patterns Classification

      • Claudio Tortorici, Naoufel Werghi, Stefano Berretti

      Pages 151-166

   4. A Normalized Generalized Curvature Scale Space for 2D Contour Representation

      • Ameni Benkhlifa, Faouzi Ghorbel

      Pages 167-177

5. Watermarking, Segmentation and Deformations

   1. Front Matter

      Pages 179-179

      PDF

   2. A New Watermarking Method Based on Analytical Clifford Fourier Mellin Transform

      • Maroua Affes, Malek Sellami Meziou, Faouzi Ghorbel

      Pages 181-191

   3. Simultaneous Semi-supervised Segmentation of Category-Independent Objects from a Collection of Images

      • Hager Merdassi, Walid Barhoumi, Ezzeddine Zagrouba

      Pages 192-203

This book constitutes the refereed proceedings of the 7th International Workshop on Representations, Analysis and Recognition of Shape and Motion from Imaging Data, RFMI 2017, held in Savoi, France, in December 2017.
The 8 revised full papers and 9 revised short papers presented were carefully reviewed and selected from 23 submissions. The papers are organized in topical sections on analyzing motion data; deep learning on image and shape data; 2D and 3D pattern classification; watermarking, segmentation and deformations.

• 3D
• artificial intelligence
• computer graphics
• computer vision
• descriptors
• estimation
• image coding
• image processing
• image reconstruction
• image segmentation
• neural networks
• object recognition

• Ecole Centrale de Lyon/LIRIS, Lyon, France

  Liming Chen

• Cité Scientifique, IMT Lille Douai/CRIStAL, Villeneuve-d'Ascq Cedex, France

  Boulbaba Ben Amor

• Ecole Nationale des Sciences de l’Informatique de Tunisie/CRISTAL, Manouba, Tunisia

  Faouzi Ghorbel

Policies and ethics