Search Results for "optical flow"
Sort By:
Showing 20 open source projects for "optical flow"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
1
DeepSeek-OCR 2
Visual Causal Flow
DeepSeek-OCR-2 is the second-generation optical character recognition system developed to improve document understanding by introducing a “visual causal flow” mechanism, enabling the encoder to reorder visual tokens in a way that better reflects semantic structure rather than strict raster scan order. It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents with rich spatial structure. ... -
2
Computer Vision in Action
A computer vision closed-loop learning platform
...It serves as a hands-on companion for learners and engineers who want to understand not just the theory, but how computer vision is actually implemented for tasks like object detection, image classification, feature tracking, optical flow, and image segmentation. The repository includes structured code examples, scripts, and notebooks that cover pipeline construction, preprocessing, model inference, and visual output rendering, making it easy for newcomers or intermediate practitioners to adapt patterns to their own projects. It also explores how to combine classical computer vision techniques with modern neural network-based models, offering insight into when each approach is most effective. -
3
KLT-IV v1.0 has been designed to offer a user-friendly graphical user interface for the determination of river flow velocity and river discharge using videos acquired using a variety of fixed and moving platforms. KLT-IV employs optical flow and computer vision techniques for the tracking of features present on the river surface with pixel displacements being converted to real-world velocities using an optimised camera model approach. Movement of the platform can be accounted for when ground control points and/or stable features are present, or where the platform is equipped with GPS and IMU sensors. ...
-
4
I3D models trained on Kinetics
Convolutional neural network model for video classification
...The I3D model extends the 2D convolutional structure of Inception-v1 into 3D, allowing it to capture spatial and temporal information from videos for action recognition. This repository includes pretrained I3D models on the Kinetics dataset, with both RGB and optical flow input streams. The models have achieved state-of-the-art results on benchmark datasets such as UCF101 and HMDB51, and also won first place in the CVPR 2017 Charades Challenge. The project provides TensorFlow and Sonnet-based implementations, pretrained checkpoints, and example scripts for evaluating or fine-tuning models. It also offers sample data, including preprocessed video frames and optical flow arrays, to demonstrate how to run inference and visualize outputs. -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
cocolib / light field suite
CUDA library for continuous optimization and light field analysis
Library for continuous convex optimization in image analysis, together with a command line tool and Matlab interface. Implements several recent algorithms for inverse problems and image segmentation with total variation regularizers and vectorial multilabel transition costs. Also included is a suite for variational light field analysis, which ties into the HCI light field benchmark set and givens reference implementations for a number of our recently published algorithms. *** NOTE: ... -
6
JPIV
Particle Image Velocimetry
JPIV is a platform independent, graphical stand-alone application for Particle Image Velocimetry (PIV) written in Java. PIV is an optical technique for measuring fluid flow velocities. JPIV moved to GitHub. Please visit us at: https://eguvep.github.io/jpiv/ -
7
Five video classification methods
Code that accompanies my blog post outlining five video classification
...While this additional information provides us more to work with, it also requires different network architectures and, often, adds larger memory and computational demands.We won’t use any optical flow images. This reduces model complexity, training time, and a whole whack load of hyperparameters we don’t have to worry about. Every video will be subsampled down to 40 frames. So a 41-frame video and a 500-frame video will both be reduced to 40 frames, with the 500-frame video essentially being fast-forwarded. We won’t do much preprocessing. ... -
8
CvMob is an Open Source tool to automatic visual analysis of human movement. The software calculates the optical flow to generate data about trajectory, velocity and acceleration using low-quality videos. For more informations, please visit our website: http://www.cvmob.ufba.br/
-
9
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
kinflow
Optical flow interactively estimated on GPU with GUI.
PyCUDA/sdl user interface to interactively influence optical flow (2D motion) estimation from camera images. -
11
featured-object-tracking
Featured object tracking
project includes work with - optical flow for object tracking - SIFT homography RANSAC to initialize then optical flow tracking -
12
TwoD-Pose-Estimation-for-Grasping
using optical flow to match and determine local motion
using optical flow to find local motion and therefore derives pose estimation of 2D pattern -
13
movieAlignment
align TEM movies
movie alignment using optical flow -
14
pivonvideo
Toolchain automating PIV analysis of video
Particle image velocimetry (PIV) is an optical method of flow visualization. pivonvideo combine together several tools to automatize PIV analysis of whole video extracts, performing image extraction, transformation, analysis and result visualization. -
15
NavigationAssistant
Lane and Moving Vehicle Detection
C++ implementation of optical flow estimation, lane detection and the detection of moving vehicle in traffic scenarios. DEPENDENCIES: * OpenCV (v2.4.9) * cvBlobsLib -
16
LS-PIV Supplemental Material
Line-scanning particle image velocimetry for analyzing blood flow data
Line-scanning particle image velocimetry (LS-PIV) is an analytical method to quantify blood velocity data generated by many confocal and two-photon excited fluorescence microscopes. We hope that this method will be of use to the research community! The associated files include Matlab code for LS-PIV and example data-sets of measured blood flow in the cerebral cortex of mouse. For additional information, please see the manuscript "Line-Scanning Particle Image Velocimetry: an Optical Approach for Quantifying a Wide Range of Blood Flow Speeds in Live Animals" by Tyson N. Kim, Patrick W. Goodwill, Yeni Chen, Steven M. Conolly, Chris B. Schaffer, Dorian Liepmann, Rong A. Wang. -
17
EMGU Kalman Filter
Kalman Filter for EMGU Image Processing Applications
...In these examples the signal processes is the movement of the mouse and random data. While a simple application the algorithm can have numerous applications including image smoothing, edge tracking and optical flow to name a few. -
18
BayesianCortex
simple algorithm for a realtime interactive visual cortex for painting
A paint program where the canvas is the visual cortex of a simple kind of artificial intelligence. You paint with the mouse into its dreams and it responds by changing what you painted gradually. There will also be an API for using it with other programs as a general high-dimensional space. Each pixel's brightness is its own dimension. Bayesian nodes have exactly 3 childs because that is all thats needed to do NAND in a fuzzy way as Bayes' Rule which is NAND at certain extremes. NAND can be... -
19
An implementation of Bruhn et al.'s fast variational optical flow algorithm using the OpenCV image processing library. The code calculates dense flow fields with a user-specified level of precision.
-
20
This project contains both tools and data for Optical Flow evaluation purposes. It offers: many ground truth optical flow sequences; a tool for generating optical flow data from real sequences; implementations of some optical flow algorithms.
- Previous
- You're on page 1
- Next
