Explore projects
-
2D object detection in cluttered scene
Updated -
3D object detection in cluttered scene
Updated -
3D single object detection
Updated -
This project develops video analytics towards anomaly detection on edge for smart cities under low light conditions: https://iotgarage.net/projects/VideoAnalyticstowardsAnomalyDetectionontheEdge.html
Updated -
This project deals with training of convolutional neural network for licence plate detection in video. Darknet technology was used for detection, specifically the YOLOv3-tiny neural network model.
Updated -
This repository contains the codebase for the analysis performed in Premier Badminton League (2019).
Updated -
IRAFM AI / BB refinement
MIT LicenseA simple NN that can increase the accuracy of existing object detectors.
Updated -
-
Train YOLOv5 for breed classification on Oxford Pets III dataset from scratch on Google Colab, and serve through Dockerized implementation of a flask-based HTML/JS frontend and an asynchronous API service on FastAPI. Use of MLFlow for logging.
Updated -
Candidate Extraction in Two-stage Localization Models - implementation of RPN (Region Proposal Network), localization model proposed in Faster R-CNN. Implementation is in PyTorch deep learning framework. My undergraduate thesis computer vision project.
Updated -
satelligence / classifier
Apache License 2.0A landcover classification tool based for humans. Classifier does "traditional" supervised and unsupervised learning. Image segmentation and soon also object detection
Updated -
Converting MS-COCO annotations to Pascal VOC format
Updated -
a brief guide to making a custom YOLOv3 detector, from image annotation to model training
Updated -
AlexeyAB darknet version with improvements with test/demo
Updated -
-
This repository contains all my work related to the study of effectiveness of wavelet feature extraction on: Pose estimation Human segmentation Object detection Image Processing
Updated -
Gutenberg is a pipeline for training a neural network in segmenting and recognising frequent words in early printed books, in particular we focus on Gutenberg’s Bible.
Updated -
-
✭ MAGNETRON ™ ✭: This is a Google Colab/Jupyter Notebook for developing an OBJECT DETECTION proxia when working with ARTIFICIAL INTELLIGENCE 2.0 ™ (ARTIFICIAL INTELLIGENCE 2.0™ is part of MAGNETRON ™ TECHNOLOGY).
Updated -
✭ MAGNETRON ™ ✭: This is a Google Colab/Jupyter Notebook for developing an OBJECT DETECTION proxia when working with ARTIFICIAL INTELLIGENCE 2.0 ™ (ARTIFICIAL INTELLIGENCE 2.0™ is part of MAGNETRON ™ TECHNOLOGY).
Updated