How pratikramdasi/computer-vision works
This repository is a collection of independent computer-vision demonstrations, not one integrated application. Its projects cover video transformation and I/O, background subtraction and motion evaluation, object classification, human-activity recognition, eigenfaces, and logo matching. The graph keeps these workflows separate; edges show only calls visible in the sampled source. Some documented project areas have unsampled implementation, so their nodes use exact enclosing directories and their internal links are omitted.
Main entry points: videoTransforms.py Video Transforms · main.py Motion Detection · edgeTemplateMatching_single.cpp Logo Matching · eignfaces.cpp Eigenface PCA
Components 15
Video Processing
- Video Transforms
01_Video_Transformations/videoTransforms.py - Video Read Write
03_Video_Read-Write
Motion Analysis
- MOG Subtraction
02_Background_Subtraction/MOG.cpp - MOG2 Subtraction
02_Background_Subtraction/mog2.cpp - ViBe Detection
02_Background_Subtraction/vibe.cpp - Motion Detection
04_Motion_Detection/main.py - Detection Accuracy
04_Motion_Detection/accuracy_measure.py
Object Classification
- Video Classification
05_object_classification/main.py - SVM Training
05_object_classification/svmTraining.py
Activity Recognition
- HOG Training
06_Human_Activity_Recognition/HOGFile.py - HOG Testing
06_Human_Activity_Recognition/HOGTest.py - PCA Video Matching
06_Human_Activity_Recognition/VideoMatching_PCA_SVD.py
Image Recognition
- Eigenface PCA
07_PCA_Eigenfaces/eignfaces.cpp - Logo Matching
08_Logo_Identification/edgeTemplateMatching_single.cpp
Other components
- User
Connections 20
- User → Video Transforms: provides video
01_Video_Transformations/videoTransforms.py - Video Transforms → Video Transforms: extracts frames
01_Video_Transformations/videoTransforms.py - Video Transforms → Video Transforms: dispatches transform
01_Video_Transformations/videoTransforms.py - User → MOG Subtraction: starts detection
02_Background_Subtraction/MOG.cpp - User → MOG2 Subtraction: starts detection
- User → ViBe Detection: starts detection
02_Background_Subtraction/vibe.cpp - User → Motion Detection: provides video
04_Motion_Detection/main.py - Motion Detection → Motion Detection: frames video
04_Motion_Detection/main.py - Motion Detection → Motion Detection: processes samples
04_Motion_Detection/main.py - User → Detection Accuracy: evaluates output
04_Motion_Detection/accuracy_measure.py - User → Video Classification: provides video
05_object_classification/main.py - User → SVM Training: trains classifier
05_object_classification/svmTraining.py - User → HOG Training: trains activity model
06_Human_Activity_Recognition/HOGFile.py - User → HOG Testing: tests activity model
- User → PCA Video Matching: matches video
06_Human_Activity_Recognition/VideoMatching_PCA_SVD.py - User → Eigenface PCA: generates eigenfaces
07_PCA_Eigenfaces/eignfaces.cpp - Eigenface PCA → Eigenface PCA: aligns faces
07_PCA_Eigenfaces/eignfaces.cpp - User → Logo Matching: provides images
08_Logo_Identification/edgeTemplateMatching_single.cpp - Logo Matching → Logo Matching: preprocesses images
08_Logo_Identification/edgeTemplateMatching_single.cpp - Logo Matching → Logo Matching: matches templates
08_Logo_Identification/edgeTemplateMatching_single.cpp