Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/

Person Retrieval in Video Surveillance using Semantic Description

Learn how to change background efficiently and easily by just using 3-4 lines of code using Python's Pixellib library that uses Deeplab's pre-trained Deep Learning model.

Implementation of our IEEE AVSS 2018 paper "Person Retrieval in Surveillance Video using Height, Color, and Gender".

Track-assisted, automatic, instant cattle identity cataloger and cattle-recognition system. (Datasets included.)

Training a model for Instance segmentation and object detection with MaskRCNN with TensorFlow on a custom selected dataset from the open image.

Animation of the 3D Ken Burns effect for still images based on stereo image input

The project is about fence inspection for breach detection using drones autonomously

A PyTorch implementation of AffordanceNet

Autonomous Vehicles: Computer Vision Implementation

A deep learning project utilizing Mask R-CNN for building instance segmentation, openings detection, and building type classification.

using deep learning and opencv for car palte location

Deep learning final project, combining Mask R-CNN into Cycle-GAN to achieve better accuracy in style transfer.

This project demonstrates image segmentation using the Mask R-CNN model.

Build an algorithm that automatically detects potential pneumonia cases

Deep-learning pipeline for shadow-casting object segmentation in aerial images of urban landscape. This repository combines U-Net, YOLO, and Mask R-CNN to handle both object detection, pixel-level instance and semantic segmentation, featuring automated YOLO dataset processing and advanced GPU memory management.

Object Detection implementation with Mask R-CNN architecture.