EECS 274 Computer Vision - PowerPoint by qok10781


									EECS 274 Computer Vision

        Object detection
Human detection
•   HOG features
•   Cue integration
•   Ensemble of classifiers
•   ROC curve

• Reading: Assigned papers
Human detection with HOG
           • Histogram of oriented
           • Using local gradients to
             represent positive and
             negative examples
Histogram of oriented gradients
HOG descriptors
Results with MIT dataset
Results with INRIA dataset
Parameter sweeping
Block/cell size
• No gradient smoothing with [-1,0,1]
  derivative filter
• Use gradient magnitude (no thresholding)
• Orientation voting into fine bins
• Spatial voting into coarser bins
• Strong local normalization
• Overlapping normalization blocks
Cal Tech Pedestrian Dataset
A large annoated dataset with performance evaluation
Performance evaluation
Results (cont’d)
Results (cont’d)
Results (cont’d)
Results (cont’d)
• HOG, MultiFtr, FtrMine outperform others
• VJ and Shaplet perform poorly
• LatSvm trained on PASCAL dataset
• HOG poerforms best on near, unoccluded
• MultiFtr ties or outperforms HOG on
  difficult cases
• Much room for imporvment
Daimler dataset
• Recent survey in PAMI 09
• Observation
  – HOG/linSVM at higher image resolution
    performs well, with lower processing speed)
  – Wavelet-based Adaboost cascade at lower
    image resolution performs well, with higher
    processing speed
Neural network with receptive fields
Cue integration

 Multi-cue pedestrian detection and tracking from a moving vehicle, IJCV 06
  Classifier ensemble
  • Cascade of boosted classifiers
  • Variable-size blocks: 12 x 12, 64 x 128, etc. 
    5031 blocks in 64 x 128 image patch

Fast human detection using a cascade of histograms of oriented
gradients, CVPR 06
Classifier ensemble

    An HOG-LBP Human Detector with Partial Occlusion Handling, ICCV 09
Convert holistic classifier to local-classifier ensemble


      An HOG-LBP Human Detector with Partial Occlusion Handling, ICCV 09

To top