300 likes | 508 Views
Recognition and tracking of human body parts. Algirdas Beinaravičius Gediminas Mazrimas Salman Mosslem. Contents. Introduction Background subtraction techniques Image segmentation Color spaces Clustering Blobs Body part recognition Problems and conclusion. Introduction. Project tasks.
E N D
Recognition and tracking of human body parts AlgirdasBeinaravičius Gediminas Mazrimas Salman Mosslem
Contents • Introduction • Background subtraction techniques • Image segmentation • Color spaces • Clustering • Blobs • Body part recognition • Problems and conclusion
Introduction. Project tasks • Background subtraction/Foreground extraction • Color spaces and K-Means clustering • Blob-level introduction • Body part recognition
Background subtraction • What is background subtraction? • Background subtraction models: • Gaussian model • “Codebook” model
Background subtractionGaussian model • Learning the model • Gaussian parameters estimation • Thresholds - Foreground/Background determination
Background subtraction“Codebook” model • Non-parametric model
Background subtractionModel comparison Original image Background subtraction using Gaussian model Background subtraction using Codebook model
Image segmentation • Color spaces • RGB • HSI • I3 (Ohta) • YCC (LumaChroma) • Clustering • K-Means • Markov Random Field
Image segmentationColor space: RGB • RGB (Red Green Blue) • Classical color space • 3 color channels (0-255) • In this project: • Used in background subtraction
Image segmentationColor space: HSI • HSI (Hue Saturation Intensity/Lightness) • Similar to HSV (Hue Saturation Value) • 3 color channels: • Hue – color itself • Saturation – color pureness • Intensity – color brightness • Converted from normalized RGB values • Intensity significance minimized • In this project: • Used in clustering • Blob formation • Body part recognition
Image segmentationClustering • Image data (pixels) classification to distinct partitions (labeling problem) • Color space importance in clustering
Image segmentationClustering: K-Means • Clustering without any prior knowledge • Working only with foreground image • Totally Kclusters • Classification based on cluster centroid and pixel value comparison • Euclidean distance: • Mahalanobis distance:
Image segmentationClustering: K-Means Euclidean/Mahalanobis distance comparison Euclidean distance Mahalanobis distance
Image segmentationClustering: K-Means color space comparison RGB HSI
Image segmentationClustering: MRF • Probabilistic graphical model using prior knowledge • Usage: • Pixel-level • Blob level • Concepts from MRF: • Neighborhood system • Cliques
Image segmentationClustering: MRF Neighborhood system Cliques
Blobs • Higher level of abstraction • Ability to identify body parts • Faster processing
BlobsParameters • Label. • Set of area pixels. • Centroid. • Mean color value. • Set of pixels, forming convex hull. • Set of neighboring blobs. • Skin flag.
BlobsInitial creation • Input: K-means image/matrix. • Output: Set of blobs
BlobsSkin blobs • Particularly important in human body part recognition. • Can not be fused. • Technique to identify skin blobs: • Euclidean distance
BlobsFusion • Conditions: • Blobs have to be neighbors • Blobs have to share a large border ratio • Blobs have to be of similar color • Small blobs are fused to their largest neighbor • Neither of these conditions apply to skin blobs
Body part recognition (I) • Associate blobs to body parts
Body part recognition (II) • Skin blobs play the key role: • Head and Upper body: • Torso identification • Face and hands identification • Lower body: • Legs and feet identification
Problems (I) • Computational time • Background subtraction quality • Subject clothing • Subject position • Number of clusters in K-Means algorithm • Skin blobs
Conclusion and future work • Main tasks completed • Improvements are required for better results • Possible future work: • Multiple people tracking • Detailed body part recognition • Algorithm improvements with better computer hardware usage for live video images