Search

International audience; This book constitutes the refereed proceedings of the 19th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2018, held in Poitiers, France, in September 2018. The 52 full papers presented in this volume were carefully reviewed and selected from 91 submissions. They were organized in topical sections named: video analysis; segmentation and classification; remote sending; biometrics; deep learning; coding and compression; and image restauration and reconstruction.

Noise Reduction and Restoration.- Directional Filtering for Upsampling According to Direction Information of the Base Layer in the JVT/SVC Codec.- A New Fuzzy-Based Wavelet Shrinkage Image Denoising Technique.- Mathematical Models for Restoration of Baroque Paintings.- Motion Blur Concealment of Digital Video Using Invariant Features.- Hybrid Sigma Filter for Processing Images Corrupted by Multiplicative Noise.- Automatic Restoration of Old Motion Picture Films Using Spatiotemporal Exemplar-Based Inpainting.- Dedicated Hardware for Real-Time Computation of Second-Order Statistical Features for High Resolution Images.- Greyscale Image Interpolation Using Mathematical Morphology.- Dilation Matrices for Nonseparable Bidimensional Wavelets.- Evolutionary Tree-Structured Filter for Impulse Noise Removal.- Perceived Image Quality Measurement of State-of-the-Art Noise Reduction Schemes.- Multiway Filtering Applied on Hyperspectral Images.- Segmentation.- A Linear-Time Approach for Image Segmentation Using Graph-Cut Measures.- The RIM Framework for Image Processing.- A Proposal Method for Corner Detection with an Orthogonal Three-Direction Chain Code.- A Charged Active Contour Based on Electrostatics.- Comparison of Statistical and Shape-Based Approaches for Non-rigid Motion Tracking with Missing Data Using a Particle Filter.- An Active Contour Model Guided by LBP Distributions.- Characterizing the Lacunarity of Objects and Image Sets and Its Use as a Technique for the Analysis of Textural Patterns.- Adaptive Vision Leveraging Digital Retinas: Extracting Meaningful Segments.- A Fast Dynamic Border Linking Algorithm for Region Merging.- Motion Estimation and Tracking.- Fast Sub-pixel Motion Estimation for H.264.- Temporal Error Concealment Based on Optical Flow in the H.264/AVC Standard.- Foreground-to-Ghost Discrimination in Single-Difference Pre-processing.- Moving Object Removal Based on Global Feature Registration.- Object Tracking Using Discriminative Feature Selection.- Color-Based Multiple Agent Tracking for Wireless Image Sensor Networks.- A Fast Motion Vector Search Algorithm for Variable Blocks.- Video Processing and Coding.- Constrained Region-Growing and Edge Enhancement Towards Automated Semantic Video Object Segmentation.- Spatio-temporal Composite-Features for Motion Analysis and Segmentation.- New Intra Luma Prediction Mode in H.264/AVC Using Collocated Weighted Chroma Pixel Value.- Fast Mode Decision for H.264/AVC Using Mode Prediction.- Performing Deblocking in Video Coding Based on Spatial-Domain Motion-Compensated Temporal Filtering.- Improving DCT-Based Coders Through Block Oriented Transforms.- Improvement of Conventional Deinterlacing Methods with Extrema Detection and Interpolation.- Adaptive Macroblock Mode Selection for Reducing the Encoder Complexity in H.264.- Dynamic Light Field Compression Using Shared Fields and Region Blocks for Streaming Service.- Complexity Scalability in Motion-Compensated Wavelet-Based Video Coding.- Spatial Error Concealment with Low Complexity in the H.264 Standard.- A Real-Time Content Adaptation Framework for Exploiting ROI Scalability in H.264/AVC.- Complexity Reduction Algorithm for Intra Mode Selection in H.264/AVC Video Coding.- Simple and Effective Filter to Remove Corner Outlier Artifacts in Highly Compressed Video.- Content-Based Model Template Adaptation and Real-Time System for Behavior Interpretation in Sports Video.- New Approach to Wireless Video Compression with Low Complexity.- Fast Multi-view Disparity Estimation for Multi-view Video Systems.- AddCanny: Edge Detector for Video Processing.- Video-Based Facial Expression Hallucination: A Two- Level Hierarchical Fusion Approach.- Blue Sky Detection for Picture Quality Enhancement.- Requantization Transcoding in Pixel and Frequency Domain for Intra 16x16 in H.264/AVC.- Motion-Compensated Deinterlacing Using Edge Information.- Video Enhancement for Underwater Exploration Using Forward Looking Sonar.- Camera Calibration, Image Registration and Stereo Matching.- Optimal Parameters Selection for Non-parametric Image Registration Methods.- Camera Calibration from a Single Frame of Planar Pattern.- Stereo Matching Using Scanline Disparity Discontinuity Optimization.- A New Stereo Matching Model Using Visibility Constraint Based on Disparity Consistency.- Refine Stereo Correspondence Using Bayesian Network and Dynamic Programming on a Color Based Minimal Span Tree.- Estimation of Rotation Parameters from Blurred Image.- Hierarchical Stereo Matching: From Foreground to Background.- Biometrics and Security.- Gabor Feature Based Face Recognition Using Supervised Locality Preserving Projection.- Alternative Fuzzy Clustering Algorithms with L1-Norm and Covariance Matrix.- A Statistical Approach for Ownership Identification of Digital Images.- Rigid and Non-rigid Face Motion Tracking by Aligning Texture Maps and Stereo-Based 3D Models.- Curve Mapping Based Illumination Adjustment for Face Detection.- Common Image Method(Null Space + 2DPCAs) for Face Recognition.- Discrete Choice Models for Static Facial Expression Recognition.- Scalable and Channel-Adaptive Unequal Error Protection of Images with LDPC Codes.- Robust Analysis of Silhouettes by Morphological Size Distributions.- Enhanced Watermarking Scheme Based on Texture Analysis.- A Robust Watermarking Algorithm Using Attack Pattern Analysis.- Probability Approximation Using Best-Tree Distribution for Skin Detection.- Fusion Method of Fingerprint Quality Evaluation: From the Local Gabor Feature to the Global Spatial-Frequency Structures.- 3D Face Recognition Based on Non-iterative Registration and Single B-Spline Patch Modelling Techniques.- Automatic Denoising of 2D Color Face Images Using Recursive PCA Reconstruction.- Facial Analysis and Synthesis Scheme.- Medical Imaging.- Detection of Pathological Cells in Phase Contrast Cytological Images.- Water Flow Based Complex Feature Extraction.- Seeded Region Merging Based on Gradient Vector Flow for Image Segmentation.- System for Reading Braille Embossed on Beverage Can Lids for Authentication.- Leukocyte Segmentation in Blood Smear Images Using Region-Based Active Contours.- Multiresolution Lossy-to-Lossless Coding of MRI Objects.- A Novel Fuzzy Segmentation Approach for Brain MRI.- Extrema Temporal Chaining: A New Method for Computing the 2D-Displacement Field of the Heart from Tagged MRI.- Data Fusion and Fuzzy Spatial Relationships for Locating Deep Brain Stimulation Targets in Magnetic Resonance Images.- Robust Tracking of Migrating Cells Using Four-Color Level Set Segmentation.- Image Retrieval and Image Understanding.- Robust Visual Identifier for Cropped Natural Photos.- Affine Epipolar Direction from Two Views of a Planar Contour.- Toward Visually Inferring the Underlying Causal Mechanism in a Traffic-Light-Controlled Crossroads.- Computer Vision Based Travel Aid for the Blind Crossing Roads.- A Novel Stochastic Attributed Relational Graph Matching Based on Relation Vector Space Analysis.- A New Similarity Measure for Random Signatures: Perceptually Modified Hausdorff Distance.- Tracking of Linear Appearance Models Using Second Order Minimization.- Visibility of Point Clouds and Mapping of Unknown Environments.- Adjustment for Discrepancies Between ALS Data Strips Using a Contour Tree Algorithm.- Visual Bootstrapping for Unsupervised Symbol Grounding.- A 3D Model Acquisition System Based on a Sequence of Projected Level Curves.- Scale Invariant Robust Registration of 3D-Point Data and a Triangle Mesh by Global Optimization.- Fast Hough Transform Based on 3D Image Space Division.- Context-Based Scene Recognition Using Bayesian Networks with Scale-Invariant Feature Transform.- A Portable and Low-Cost E-Learning Video Capture System.- On Building Omnidirectional Image Signatures Using Haar Invariant Features: Application to the Localization of Robots.- Accurate 3D Structure Measurements from Two Uncalibrated Views.- A Fast Offline Building Recognition Application on a Mobile Telephone.- Adaptive Learning Procedure for a Network of Spiking Neurons and Visual Pattern Recognition.- Interactive Learning of Scene Context Extractor Using Combination of Bayesian Network and Logic Network.- Classification and Recognition.- Adaptative Road Lanes Detection and Classification.- An Approach to the Recognition of Informational Traffic Signs Based on 2-D Homography and SVMs.- On Using a Dissimilarity Representation Method to Solve the Small Sample Size Problem for Face Recognition.- A Comparison of Nearest Neighbor Search Algorithms for Generic Object Recognition.- Non Orthogonal Component Analysis: Application to Anomaly Detection.- A Rough Set Approach to Video Genre Classification.

Multi-view scene reconstruction from multiple uncalibrated images can be solved by two stages of processing: first, a sparse reconstruction using Structure From Motion (SFM), and second, a surface reconstruction using optimization of Markov random field (MRF). This paper focuses on the second step, assuming that a set of sparse feature points have been reconstructed and the cameras have been calibrated by SFM. The multi-view surface reconstruction is formulated as an image-based multi-labeling problem solved using MRF optimization via graph cut. First, we construct a 2D triangular mesh on the reference image, based on the image segmentation results provided by an existing segmentation process. By doing this, we expect that each triangle in the mesh is well aligned with the object boundaries, and a minimum number of triangles are generated to represent the 3D surface. Second, various objective and heuristic depth cues such as the slanting cue, are combined to define the local penalty and interaction energies. Third, these local energies are adapted to the local image content, based on the results from some simple content analysis techniques. The experimental results show that the proposed method is able to well the preserve the depth discontinuity because of the image content adaptive local energies.

International audience

Acquisition, Pre-processing and Coding.- Efficient Low Complexity SVC Video Transrater with Spatial Scalability.- Visual Data Encryption for Privacy Enhancement in Surveillance Systems.- Distance Estimation with a Two or Three Aperture SLR Digital Camera.- Acquisition of Agronomic Images with Sufficient Quality by Automatic Exposure Time Control and Histogram Matching.- An Enhanced Weighted Median Filter for Noise Reduction in SAR Interferograms.- High Precision Restoration Method for Non-uniformly Warped Images.- Noise Robustness Analysis of Point Cloud Descriptors.- Restoration of Blurred Binary Images Using Discrete Tomography.- Minimum Memory Vectorisation of Wavelet Lifting.- Magnitude Type Preserving Similarity Measure for Complex Wavelet Based Image Registration.- Biometry.- Real-Time Face Pose Estimation in Challenging Environments.- Human Motion Capture Using Data Fusion of Multiple Skeleton Data.- Recognizing Conversational Interaction Based on 3D Human Pose.- Upper-Body Pose Estimation Using Geodesic Distances and Skin-Color.- A New Approach for Hand Augmentation Based on Patch Modelling.- Hidden Markov Models for Modeling Occurrence Order of Facial Temporal Dynamics.- Adaptive Two Phase Sparse Representation Classifier for Face Recognition.- Automatic User-Specific Avatar Parametrisation and Emotion Mapping .- Classification and Recognition.- Optimizing Contextual-Based Optimum-Forest Classification through Swarm Intelligence.- A Mobile Imaging System for Medical Diagnostics.- Fast Road Network Extraction from Remotely Sensed Images.- Partial Near-Duplicate Detection in Random Images by a Combination of Detectors.- Object Recognition and Modeling Using SIFT Features.- Painting Scene Recognition Using Homogenous Shapes.- A Novel Graph Based Clustering Technique for Hybrid Segmentation of Multi-spectral Remotely Sensed Images.- Depth, 3D and Tracking.- Planar Segmentation by Time-of-Flight Cameras.- An Efficient Normal-Error Iterative Algorithm for Line Triangulation.- Moving Object Detection System in Aerial Video Surveillance.- An Indoor RGB-D Dataset for the Evaluation of Robot Navigation Algorithms.- Real-Time Depth Map Based People Counting.- Tracking of a Handheld Ultrasonic Sensor for Corrosion Control on Pipe Segment Surfaces.- Extended GrabCut for 3D and RGB-D Point Clouds.- Efficient Implementations and Frameworks.- A Resource Allocation Framework for Adaptive Selection of Point Matching Strategies.- VTApi: An Efficient Framework for Computer Vision Data Management and Analytics.- Computational Methods for Selective Acquisition of Depth Measurements: An Experimental Evaluation.- A New Color Image Database TID2013: Innovations and Results.- Performance Evaluation of Video Analytics for Surveillance On-Board Trains.- GPU-Accelerated Human Motion Tracking Using Particle Filter Combined with PSO.- Low Level Image Analysis and Segmentation.- Modelling Line and Edge Features Using Higher-Order Riesz.- Transforms.- Semantic Approach in Image Change Detection.- Small Target Detection Improvement in Hyperspectral Image.- The Objective Evaluation of Image Object Segmentation Quality.- A Modification of Diffusion Distance for Clustering and Image Segmentation.- Flexible Multi-modal Graph-Based Segmentation.- The Divide and Segment Method for Parallel Image Segmentation.- Unsupervised Segmentation for Transmission Imaging of Carbon Black.- Tree Symbols Detection for Green Space Estimation.- Hierarchical Layered Mean Shift Methods.- Globally Segmentation Using Active Contours and Belief Function.- Video Analytics.- Automatic Monitoring of Pig Activity Using Image Analysis.- IMM-Based Tracking and Latency Control with Off-the-Shelf IP PTZ Camera.- Evaluation of Traffic Sign Recognition Methods Trained on Synthetically Generated Data.- Robust Multi-camera People Tracking Using Maximum Likelihood Estimation.- A Perception-Based Interpretation of the Kernel-Based Object Tracking.- Efficient Detection and Tracking of Road Signs Based on Vehicle Motion and Stereo Vision.- Incremental Principal Component Analysis-Based Sparse Representation for Face Pose Classification.- Person Detection with a Computation Time Weighted AdaBoost.- Perspective Multiscale Detection of Vehicles for Real-Time Forward Collision Avoidance Systems.- Learning and Propagation of Dominant Colors for Fast Video Segmentation.- A Key-Pose Similarity Algorithm for Motion Data Retrieval.- Training with Corrupted Labels to Reinforce a Probably Correct Teamsport Player Detector.- Spherical Center-Surround for Video Saliency Detection Using Sparse Sampling.- Semantic Concept Detection Using Dense Codeword Motion.

International audience; In this paper, we present various bathymetric filters, based on the well-known MF, AMF and ACE detectors, for underwater target detection from hyperspectral remote-sensing data. In the case of unknown water characteristics, we also propose the GBF, a GLRT-based filter that estimates these parameters and detects at the same time. The results of this estimation process, performed on both simulated and real data, are encouraging, since under regular conditions of depth, water quality and SNR, the accuracy is quite good. We show that these new detectors outperform the usual ones, obtained by detecting after correction of the water column effect by a classical method. We also show that the estimation errors do not impact much the detection performances, and therefore, this underwater target detection method is self-sufficient and can be implemented without any a priori knowledge on the water column.

The Hough transform is a commonly used algorithm to detect lines and other features in images. It is robust to noise and occlusion, but has a large computational cost. This paper introduces two new implementations of the Hough transform for lines on a GPU. One focuses on minimizing processing time, while the other has an input-data independent processing time. Our results show that optimizing the GPU code for speed can achieve a speed-up over naive GPU code of about 10×. The implementation which focuses on processing speed is the faster one for most images, but the implementation which achieves a constant processing time is quicker for about 20% of the images. Fulltext Preview

This paper presents the design and real-time implementation of a fall-detection system, aiming at detecting fall incidents in unobserved home situations. The setup employs two fixed, uncalibrated, perpendicular cameras. The foreground region is extracted from both cameras and for each object, principal component analysis is employed to determine the direction of the main axis of the body and the ratio of the variances in x and y direction. A Gaussian multi-frame classifier helps to recognize fall events using the above two features. The robustness of the system is increased by a head-tracking module, that can reject false positives. We evaluate both performance and efficiency of the system for a variety of scenes: unoccluded situations, cases where the person carries objects and occluded situations. Experiments show that our algorithm can operate at real-time speed with more than 85% fall-detection rate.

In the first part of this paper, an improved slope-intercept like representation is proposed for implementation of Standard Hough Transform (SHT) on SIMD (Single-Instruction, Multiple-Data) architectures with no local indirect addressing support. The real-time implementation is realized with high accuracy on our Wireless Smart Camera (WiCa) platform. The processing time of this approach is independent of the number of edge points or the number of detected lines. In the second part, we focus on analyzing the differences between the SHT implementations on 1-D SIMD architectures with and without local indirect addressing. Three aspects are compared: total operation number, memory access/ energy consumption, and memory area cost. When local indirect addressing is supported, the results show a considerable amount of reduction in total operations and energy consumption at the cost of extra chip area. The results also show that the focuses for further optimization of these two architectures are different.

International audience