Skip to content
No description, website, or topics provided.
C++ Python Perl
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
CODE
HOG_DETECTOR
svm-models
LICENSE
README.md

README.md

Pedestrain-Detection-using-Histogram-of-Oriented-Gradients

HOG is a visual descriptor i.e., it describes the content of an image in a single feature vector. The idea behind HOG is that local object appearance and shape within an image can be described by the distribution of intensity gradients or edge directions.

Dataset

Training Set Test Set Total
Positive Samples 3977 442 4419
Negative Samples 4842 538 5380

Each sample is of dimension 64x128

SVM model

we train a soft-margin linear SVM classifier. We use svmlight to train the SVM model.

Accuracy on train and test set

Accuracy (%) Precision/Recall (%)
Training Set 99.07 99.67/98.27
Test Set 99.18 100/98.19

Dependency

OpenCV

Sample Detections

You can’t perform that action at this time.