EECS 274 Computer Vision

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 gradients

• 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

Results

Observations

• 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 DatasetA large annoated dataset with performance evaluation

Performance evaluation

Results (cont’d)

Results (cont’d)

Results (cont’d)

Results (cont’d)

Summary

• HOG, MultiFtr, FtrMine outperform others

• VJ and Shaplet perform poorly• LatSvm trained on PASCAL dataset• HOG poerforms best on near,

unoccluded pedestrians• 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

Results

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

?