Object Detector using HOG as descriptor and Linear SVM as classifier. | Video

I have created a single python script that can be used to test the code. To test the code, run the lines below in your terminal.

git clone https://github.com/bikz05/object-detector.git
cd object-detector/bin
test-object-detector

The test-object-detector will download the UIUC Image Database for Car Detection and train a classifier to detect cars in an image. The SVM model files will be stored in data/models, so that they can be resused later on.

All the configurations are in the data/config/config.cfg configuration files. You can change it as per your need. Here is what the default configuration file looks like (which I have set for Car Detector)-

[hog]
min_wdw_sz: [100, 40]
step_size: [10, 10]
orientations: 9
pixels_per_cell: [8, 8]
cells_per_block: [3, 3]
visualize: False
normalize: True

[nms]
threshold: .3

[paths]
pos_feat_ph: ../data/features/pos
neg_feat_ph: ../data/features/neg
model_path: ../data/models/svm.model

• extract-features.py -- This module is used to extract HOG features of the training images.
• train-classifier.py -- This module is used to train the classifier.
• nms.py -- This module performs Non Maxima Suppression.
• test-classifier.py -- This module is used to test the classifier using a test image.
• config.py -- Imports the configuration variables from config.cfg.

Detections before NMS

Detections after NMS

Detections before NMS

Detections after NMS

Detections before NMS

Detections after NMS

Detections before NMS

Detections after NMS

Here is list of tasks that I am planning to implement in the future -

• Optimize code to use more numpy vectorized codes.
• Faster NMS code.
• Add bootstrapping (Hard Negative Mining) code.

1. Histogram of Oriented Gradients and Object Detection
2. Image Pyramids with Python and OpenCV
3. Sliding Windows for Object Detection with Python and OpenCV
4. Non-Maximum Suppression for Object Detection in Python
5. (Faster) Non-Maximum Suppression in Python
6. Texture Matching using Local Binary Patterns (LBP), OpenCV, scikit-learn and Python
7. Detección de objetos Course by Coursera