There are 1 repository under flann topic.
Match a cropped image to the original image with an efficient algorithm using Python and OpenCV.
Image key points Extraction, Description, Feature Matching
Feature Tracking and testing of various keypoint detector/descriptor combinations, keypoint matching using Brute Force and FLANN approach.
Object 2D Pose Estimation trained by RGB Data - Using Intel® RealSense D435
A vision-based nutrition management system (mobile + server) for users, where users can track the calorie and nutrient intake of the food products purchased, using the concepts of image processing, computer vision and machine learning to accurately predict names of cereal boxes, fruits, vegetables etc. The images are classified using the concept of “Bag of Words”. The information is shown in terms of graphs and charts which will be helpful for a novice user or a dietitian to understand. This was done as part of my B.E final year project.
Processing videos of digital electricity meter to extract readings using OpenCV and Python
6 DOF arm manipulation, utilizing knowledge-based reasoning, BDI and HTN planning
Project: 2D Feature Tracking || Udacity: Sensor Fusion Engineer Nanodegree
A package for registration of wide range astronomical images of stars, galaxies and clusters using SIFT, FLANN and RANSAC algorithms for extreme precision applications
Panorama Image Stitching Using SIFT and SURF Keypoint Descriptors
Tracking the preceding vehicle using Lidar and camera sensors to calculate the Time To Collision (TTC).
📽️🖥️ Track objects on your camera or on a video.
Example Image Recognition using OpenCV 3.0 (custom filters, flann & surf)
Here you can find some commonly used algorithms in 3D image processing (3D Bildverarbeitung).
Utilized OpenCV, ORBDescriptors, FLANN, Homography/Affine Transformations, and a multi-layer convolutional architecture to do direct image matching via feature and key-point matching for scale-variant images
Codes written during course Nature Inspired Computing
Testing various detector / descriptor combinations to see which ones perform best to be used in a collision detection system. Also 2 different approaches (FLANN vs. Brute-force with the descriptor distance ratio test) for keypoints matching are tested.
This is for my Computer Vision quiz practice, we only taught to match 2 images, though. So, I challenge myself to create an image matching program to detect more than 2 images from 2 different directories (the object & scene) using SURF & FLANN.