Open-source alternatives to 3d Vehicle Tracking

C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON, SVE for ARM, HVX for Hexagon

Detectron2 is a PyTorch computer vision framework and visual recognition platform designed for training and deploying models for object detection, image segmentation, and visual recognition. It provides a research-oriented environment for training complex vision models with multi-GPU acceleration. The project includes a specialized object detection library for identifying and locating multiple objects via bounding boxes, as well as an image segmentation toolkit for creating pixel-level masks through instance, semantic, and panoptic segmentation. Additionally, it features a human pose estimati

EasyOCR is a deep learning-based computer vision library designed to perform optical character recognition on images and video frames. It functions as a comprehensive pipeline that automates the transformation of visual text into machine-readable strings, enabling the digitization of physical documents, forms, and receipts into searchable data. The engine distinguishes itself through a multi-stage processing workflow that combines convolutional neural networks for spatial feature extraction with sequence-based decoding mechanisms. This architecture allows the system to identify and interpret

Real-Time 3D Semantic Reconstruction from 2D data

Techniques for deep learning with satellite & aerial imagery

Fawkes is an adversarial image generator and facial recognition cloaking tool designed to protect privacy by obfuscating facial features in photos. It functions as an image privacy obfuscator that adds invisible pixel perturbations to images, preventing facial recognition models from accurately identifying a person while keeping the image visually clear to humans. The system employs adversarial perturbation mapping and feature-space obfuscation to mislead machine learning classifiers. By utilizing an iterative optimization loop and model-agnostic noise generation, it modifies facial represent

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

A Simple and Versatile Framework for Object Detection and Instance Recognition

imgaug is a Python library for machine learning data augmentation and computer vision dataset expansion. It provides tools to increase the volume and variety of training sets by applying random geometric, color, and noise transformations to images. The library ensures spatial consistency by synchronizing transformations across images and their associated annotations, such as bounding boxes, keypoints, and segmentation maps. It uses a compositional pipeline pattern to chain multiple augmentations into sequences and employs deterministic seed management to reproduce specific data samples. The

Yolact is a computer vision framework and real-time instance segmentation model. It utilizes a fully convolutional neural network to detect objects and generate pixel-level masks for images and video feeds. The system employs prototypical mask generation to create global mask prototypes that are linearly combined for instance-specific results. It incorporates deformable convolutional layers and deformable region-of-interest pooling to adapt spatial sampling to the irregular shapes of objects. The framework covers the full model development lifecycle, including training on custom datasets, ac

A collection of computer vision pre-trained models.

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

Find-Object project

Libvips is a C-based image processing library designed to manipulate large visual assets through a low-memory, parallel processing pipeline. It functions as a streaming image processor that avoids loading entire files into system memory, enabling the handling of massive images in resource-constrained environments. The library distinguishes itself through a demand-driven architecture that constructs a deferred execution plan, computing only the necessary pixels for a final output. By utilizing a cache-friendly tiled processing model and memory-mapped file access, it minimizes latency and redun

Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds

3D Computer Vision Framework

Python package for earth-observing satellite data processing

Meshroom is a node-based photogrammetry software designed to transform collections of two-dimensional images into three-dimensional models and scene geometry. It provides a visual interface for constructing and managing modular data pipelines, allowing users to automate complex computer vision tasks such as feature extraction, depth map estimation, and mesh generation. The software distinguishes itself through a distributed computational framework that dispatches resource-intensive tasks across local hardware or remote render farms. By utilizing a directed acyclic graph execution model, it en

Earth observation processing framework for machine learning in Python

pysot is a computer vision framework designed for single object tracking. It provides a platform for implementing and evaluating algorithms that locate and follow specific target objects across sequences of video frames. The project includes implementations of the SiamRPN architecture for region proposal network based localization and the SiamMask model, which combines tracking with binary mask generation to provide pixel-level segmentation of objects. The framework also contains a visual tracking evaluation toolkit used to measure the accuracy and reliability of tracking algorithms against

Library for Fast and Flexible Human Pose Estimation

TRI-ML Monocular Depth Estimation Repository

A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.