104 Open source projects that are alternatives of or similar to Optical-Flow-based-Obstacle-Avoidance

Optical Flow Prediction with TensorFlow. Implements "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume," by Deqing Sun et al. (CVPR 2018)

Cool Vision projects

pytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Fork and OpenCV wrapper of the optical flow I/O and visualization code provided as part of the Sintel dataset [1].

The official PyTorch implementation of the paper "Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation".

TOFlow: Video Enhancement with Task-Oriented Flow

Extract TVL1 optical flows in python (multi-process && multi-server)

No description or website provided.

The py version of toflow → https://github.com/anchen1011/toflow

Example code for the ADNS-3080 optical flow sensor

Compute dense optical flow using TV-L1 algorithm with NVIDIA GPU acceleration.

Dockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)

Fast, accurate and easy to run dense optical flow with python wrapper

ROS-based framework and RPi image to control PX4-powered drones 🍀

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Dense Matching Benchmark

(ECCV 2020) RANSAC-Flow: generic two-stage image alignment

Python-based optical flow toolkit for existing popular dataset

Google Colab notebook for running Nvidia flownet2-pytorch

DDFlow: Learning Optical Flow with Unlabeled Data Distillation

Multi-stream CNN architectures for action detection with actor-centric filtering

Spatial Pyramid Network for Optical Flow

Shallow Optical Flow Three-Stream CNN For Macro and Micro-Expression Spotting From Long Videos

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

Optical Flow estimation in pure Python

Vision-based Robot 3D Pose and Velocities Estimations

Collection of papers, datasets, code and other resources for object tracking and detection using deep learning

An implementation of several tracking algorithms based on Lucas Kanade algorithms

Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge

Video++, a C++14 high performance video and image processing library.

Easily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

Depth and Flow for Visual Odometry

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Repository for different network models related to flow/disparity (ECCV 18)

SelFlow: Self-Supervised Learning of Optical Flow

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

High-performance multiple object tracking based on YOLO, Deep SORT, and optical flow

Volumetric Correspondence Networks for Optical Flow, NeurIPS 2019.

Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

[CVPR 2020, Oral] MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask

The main abnormal behaviors that this project can detect are: Violence, covering camera, Choking, lying down, Running, Motion in restricted areas. It provides much flexibility by allowing users to choose the abnormal behaviors they want to be detected and keeps track of every abnormal event to be reviewed. We used three methods to detect abnorma…

Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

BriefMatch real-time GPU optical flow

Python framework for short-term ensemble prediction systems.

PWC-Network with TensorFlow

🎮 [IJCAI'20][ICLR'19 Workshop] Flow-based Intrinsic Curiosity Module. Playing SuperMario with RL agent and FICM!

Visual odometry using optical flow and neural networks

A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020

A method about optimizing the facial landmark detection based on Kalman Filter, Optical Flow and Dlib

Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)

CUDA implementation of the paper "Fast Edge-Preserving PatchMatch for Large Displacement Optical Flow" in CVPR 2014.

Frame-Recurrent Video Super-Resolution (official repository)

ROS Error-State Kalman Filter based on PX4/ecl. Performs GPS/Magnetometer/Vision Pose/Optical Flow/RangeFinder fusion with IMU

[MICCAI'18] Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

[ECCV 2018] DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency

Semi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segmentation (NIPS 2017)* as part of the NIPS Paper Implementation Challenge.

Unsupervised Learning for Image Registration