All Projects → stereolabs → zed-matlab

stereolabs / zed-matlab

Licence: MIT license
ZED SDK interface sample for Matlab

Programming Languages

C++
36643 projects - #6 most used programming language
matlab
3953 projects
CMake
9771 projects

Projects that are alternatives of or similar to zed-matlab

zed-oculus
ZED Viewer for Oculus Rift
Stars: ✭ 27 (+17.39%)
Mutual labels:  stereo-vision, zed-camera
zed-openpose
Real-time 3D multi-person with OpenPose and the ZED
Stars: ✭ 37 (+60.87%)
Mutual labels:  stereo-vision, zed-camera
zed-ros2-wrapper
ROS 2 wrapper beta for the ZED SDK
Stars: ✭ 61 (+165.22%)
Mutual labels:  stereo-vision, zed-camera
zed-pytorch
3D Object detection using the ZED and Pytorch
Stars: ✭ 41 (+78.26%)
Mutual labels:  stereo-vision, zed-camera
semi-global-matching
Semi-Global Matching
Stars: ✭ 122 (+430.43%)
Mutual labels:  stereo-vision
StereoVisionforADAS
Stereo vision based object detection for ADAS, autonomous vehicle
Stars: ✭ 137 (+495.65%)
Mutual labels:  stereo-vision
jpp
Joint Perception and Planning For Efficient Obstacle Avoidance Using Stereo Vision
Stars: ✭ 42 (+82.61%)
Mutual labels:  stereo-vision
stereo-vision-fpga
Real-time binocular stereo vision FPGA system with OV5640 cameras
Stars: ✭ 20 (-13.04%)
Mutual labels:  stereo-vision
edlsm pytorch
Pytorch implementation for stereo matching described in the paper: Efficient Deep learning for stereo matching
Stars: ✭ 16 (-30.43%)
Mutual labels:  stereo-vision
DispNet-TensorFlow
TensorFlow implementation of DispNet by Zhijian Jiang.
Stars: ✭ 55 (+139.13%)
Mutual labels:  stereo-vision
Awesome 3dreconstruction list
A curated list of papers & resources linked to 3D reconstruction from images.
Stars: ✭ 3,151 (+13600%)
Mutual labels:  stereo-vision
ONNX-HITNET-Stereo-Depth-estimation
Python scripts form performing stereo depth estimation using the HITNET model in ONNX.
Stars: ✭ 21 (-8.7%)
Mutual labels:  stereo-vision
dispflownet-tf
Tensorflow implementation of https://lmb.informatik.uni-freiburg.de/Publications/2016/MIFDB16 + pretrained weights + implementation of "Unsupervised Adaptation for Deep Stereo" (ICCV 2017)
Stars: ✭ 18 (-21.74%)
Mutual labels:  stereo-vision
mobilestereonet
Lightweight stereo matching network based on MobileNet blocks
Stars: ✭ 92 (+300%)
Mutual labels:  stereo-vision
RealtimeStereo
Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
Stars: ✭ 110 (+378.26%)
Mutual labels:  stereo-vision
Pandora
A stereo matching framework that will help you design your stereo matching pipeline with state of the art performances.
Stars: ✭ 31 (+34.78%)
Mutual labels:  stereo-vision
IRONSIDES
Trifo Ironsides SDK
Stars: ✭ 17 (-26.09%)
Mutual labels:  stereo-vision
RoboVision
Attempting to create a program capable of combining stereo video input , with motors and other sensors on a PC running linux , the target is embedded linux for use in a robot!
Stars: ✭ 21 (-8.7%)
Mutual labels:  stereo-vision
SASensorProcessing
ROS node to create pointcloud out of stereo images from the KITTI Vision Benchmark Suite
Stars: ✭ 26 (+13.04%)
Mutual labels:  stereo-vision
Openmvs
open Multi-View Stereo reconstruction library
Stars: ✭ 1,842 (+7908.7%)
Mutual labels:  stereo-vision

Stereolabs ZED - Matlab Integration

This sample shows how to use the ZED SDK functionalities within Matlab.

Getting started

Prerequisites

  • Windows 10 64bits or later, Ubuntu 16.04 or higher.
  • Matlab with MEX compiler installed
  • ZED SDK and its dependency (CUDA)

Build the program

Build for Windows

For detailed installation instructions, check out our documentation.

Build for Linux

Download the sample and execute the following command in a terminal:

export MATLAB_ROOT=/usr/local/MATLAB/R2012b # Put your actual Matlab path here
mkdir build
cd build
cmake ../src
make
make install

Run the program

In the Matlab directory, open the file ZED_DepthSensing.m with Matlab and press run. Press any key to exit the program.

Features

This sample is split into 6 scripts, each of them shows a specific feature of the ZED SDK in Matlab.

  1. ZED_DepthSensing.m :

    In this part, we first initialize the ZED Camera and then retrieve both stereo images (Left and Right) as well as the depth data (32-bits float buffer) and the depth image normalized to 8-bits (grayscale). Then, with Matlab, we compute the depth histogram from the depth data values and display it.

    Drawing
  2. ZED_Tracking.m :

    This part shows how to get the positional tracking information. First, we initialize the ZED camera and the tracking, then we display the current left image as well as all the positions of the camera.

    Drawing
  3. ZED_PointCloud.m :

    This part shows how to initialize the ZED camera and retrieve for each frame the current point cloud (X,Y,Z) of the scene. Then we use the mesh function of Matlab to display it.

    Drawing
  4. ZED_Recording.m :

    This script shows how to record a video sequence into 'svo' format which can be playback with the ZED SDK.

  5. ZED_ObjectDetection.m :

    This script use the ability of the ZED2 to detect objects, a video window shows the results.

  6. ZED_CameraControl.m :

    This script shows how to control the video settings of the ZED camera.

Limitations

This sample application is not designed to run in real time

Troubleshooting

On Linux, If you get the following error :

 /usr/local/MATLAB/R2014a/bin/glnxa64/../../sys/os/glnxa64/libstdc++.so.6: version `GLIBCXX_3.4.21` not found

Launch matlab with LD_PRELOAD:

LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libstdc++.so.6.0.21:/usr/lib/x86_64-linux-gnu/libfreetype.so.6 matlab&

You can also create an alias in a bash terminal (just once) to simplify the launch:

echo "alias matlab=LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libstdc++.so.6.0.21:/usr/lib/x86_64-linux-gnu/libfreetype.so.6 matlab&" >> ~/.bashrc

Then just launch the application by typing:

matlab

Support

If you need assistance go to our Community site at https://community.stereolabs.com/

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].