How to Install OpenCV 4.5 on NVIDIA Jetson Nano and Set Up a Camera
If you have a NVIDIA Jetson Nano and want to use OpenCV 4.5 for computer vision projects, you’re in the right place. In this tutorial, we’ll show you how to install OpenCV 4.5 on your Jetson Nano and set up a camera for capturing images and videos.
Step 1: Install OpenCV 4.5 on NVIDIA Jetson Nano
To install OpenCV 4.5 on your Jetson Nano, you’ll need to follow these steps:
- Update your Jetson Nano’s package list:
sudo apt update - Install required packages:
sudo apt install build-essential cmake git libgtk2.0-dev pkg-config libswscale-dev libtbb2 libtbb-dev libjpeg-dev libtiff-dev libpng-dev libavcodec-dev libavformat-dev libv4l-dev libxvidcore-dev libx264-dev libxine2-dev libatlas-base-dev gfortran - Clone OpenCV 4.5 GitHub repository:
git clone https://github.com/opencv/opencv.git - Go to the OpenCV directory:
cd opencv - Create a build directory:
mkdir build - Go to the build directory:
cd build - Run CMake to configure OpenCV:
cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D WITH_CUDA=ON -D ENABLE_FAST_MATH=1 -D CUDA_FAST_MATH=1 -D WITH_CUBLAS=1 .. - Compile and install OpenCV:
make -j4andsudo make install
Step 2: Set Up a Camera for NVIDIA Jetson Nano
To set up a camera for your Jetson Nano, you can use a USB camera or a Raspberry Pi Camera Module. Here’s how to connect and configure a USB camera:
- Connect the USB camera to your Jetson Nano.
- Check if the camera is detected:
ls /dev/video* - If the camera is detected, you can use it with OpenCV in your Python scripts.
That’s it! You’ve successfully installed OpenCV 4.5 on your NVIDIA Jetson Nano and set up a camera for capturing images and videos. You’re now ready to start working on computer vision projects with your Jetson Nano.
List of commands:
sudo apt-get install python3-pip
pip3 install virtualenv
python3 -m virtualenv -p python3 env –system-site-packages
source env/bin/activate
python -c 'import cv2; print(cv2.__version__)'
Create SwapFile:
sudo fallocate -l 4G /var/swapfile
sudo chmod 600 /var/swapfile
sudo mkswap /var/swapfile
sudo swapon /var/swapfile
sudo bash -c 'echo "/var/swapfile swap swap defaults 0 0" >> /etc/fstab’
Reboot your PC: sudo reboot
After rebooting check swap space by using this command: free -h
Install these Dependencies before installing OpenCV:
sudo sh -c "echo '/usr/local/cuda/lib64' >> /etc/ld.so.conf.d/nvidia-tegra.conf“
sudo ldconfig
sudo apt-get install build-essential cmake git unzip pkg-config
sudo apt-get install libjpeg-dev libpng-dev libtiff-dev
sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev
sudo apt-get install libgtk2.0-dev libcanberra-gtk*
sudo apt-get install python3-dev python3-numpy python3-pip
sudo apt-get install libxvidcore-dev libx264-dev libgtk-3-dev
sudo apt-get install libtbb2 libtbb-dev libdc1394-22-dev
sudo apt-get install libv4l-dev v4l-utils
sudo apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev
sudo apt-get install libavresample-dev libvorbis-dev libxine2-dev
sudo apt-get install libfaac-dev libmp3lame-dev libtheora-dev
sudo apt-get install libopencore-amrnb-dev libopencore-amrwb-dev
sudo apt-get install libopenblas-dev libatlas-base-dev libblas-dev
sudo apt-get install liblapack-dev libeigen3-dev gfortran
sudo apt-get install libhdf5-dev protobuf-compiler
sudo apt-get install libprotobuf-dev libgoogle-glog-dev libgflags-dev
Download OpenCV:
cd ~
wget -O opencv.zip https://github.com/opencv/opencv/archive/4.5.1.zip
wget -O opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/4.5.1.zip
unzip opencv.zip
unzip opencv_contrib.zip
Now rename the directories. Type each command below, one after the other.
mv opencv-4.5.1 opencv
mv opencv_contrib-4.5.1 opencv_contrib
rm opencv.zip
rm opencv_contrib.zip
Lets build OpenCV now:
cd ~/opencv
mkdir build
cd build
copy and paste this entire block of commands below into your terminal.
cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr -D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib/modules -D EIGEN_INCLUDE_PATH=/usr/include/eigen3 -D WITH_OPENCL=OFF -D WITH_CUDA=ON -D CUDA_ARCH_BIN=5.3 -D CUDA_ARCH_PTX="" -D WITH_CUDNN=ON -D WITH_CUBLAS=ON -D ENABLE_FAST_MATH=ON -D CUDA_FAST_MATH=ON -D OPENCV_DNN_CUDA=ON -D ENABLE_NEON=ON -D WITH_QT=OFF -D WITH_OPENMP=ON -D WITH_OPENGL=ON -D BUILD_TIFF=ON -D WITH_FFMPEG=ON -D WITH_GSTREAMER=ON -D WITH_TBB=ON -D BUILD_TBB=ON -D BUILD_TESTS=OFF -D WITH_EIGEN=ON -D WITH_V4L=ON -D WITH_LIBV4L=ON -D OPENCV_ENABLE_NONFREE=ON -D INSTALL_C_EXAMPLES=OFF -D INSTALL_PYTHON_EXAMPLES=OFF -D BUILD_NEW_PYTHON_SUPPORT=ON -D BUILD_opencv_python3=TRUE -D OPENCV_GENERATE_PKGCONFIG=ON -D BUILD_EXAMPLES=OFF ..
Build OpenCV. This command below will take a long time (around 2 hours), make -j4 # (make then space single dash and then j4)
Finish the install:
cd ~
sudo rm -r /usr/include/opencv4/opencv2
cd ~/opencv/build
sudo make install
sudo ldconfig
make clean
sudo apt-get update
Verify OpenCV Installation
#open python3 shell
python3
import cv2
cv2._version_
Install jtop, a system monitoring software for Jetson Nano.
cd ~
sudo -H pip3 install -U jetson-stats
sudo reboot
jtop
Test Your Camera on Jetson Nano:
Turn on your Jetson Nano.
Open a new terminal window, and type:
ls /dev/video0 #csi camera
ls /dev/video* # show you a list of cameras
Take a Photo:
nvgstcapture-1.0 –orientation=2 # for testing CSI camera
# V4L2 USB camera
nvgstcapture-1.0 –camsrc=0 –cap-dev-node=1
Hello, I met some problem when I tried to install dependencies. It showed a message said, "configuring incomplete, errors occurred!". How can I fix this issue?
Lovely video content
Hello, on the file "info" of Jtop, i don't have the 4.5.1 version of OpenCV but the 4.1.1, and it's written "No" instead of "yes". Can you help me ? Maybe there is a step that i didn't do well, but which one ? Thanks
This tutorial was very helpful and I was able to compile opencv. However the problem I am facing is that opencv is installed for python2 and not for python3. Any method to solve this?
Hey @CodeWithAarohi, thank you for insightful video. I followed same steps. Unfortunately after it has completed i am getting an error of cv2 module being unavailable in my virtual ent. What fascinates me is that it was able to install the latest opencv for cuda. Do you have an idea how to go about this ?
thank you very much！！！
Hello, I have some problem. On my jetson, it doesn't find packages (like python3-pip for exemple). Do you know why ?
Marry me, you saved me years of pain trying to download opencv correctly, fr fr all of the old tutorials were so un-updated that most of the lib files wouldn't install correctly, so opencv would never be fully operational. THANK YOU!!!!
After reboot, the swapped memory gets reset and goes back to 1.9gb. I always need to run those 4 swap commands before starting. What's the solution to this?
Hello Mam, im getting an error cmake command the error is no cmake script
provided ,cmake error: problem processing arguments. aborting
what to do?
please help..
I am following your video series, my task was to install archiconda and yolov5. I installed archiconda but in phase of yolov5. At the end , I need to make some project with jetson nano. Can you give me some ideas? And any flow that how to do it…
My pip is not installing what might be the error?
Is this video in graphical mode or headless mode?
HI Aarohi.. did all the steps you mentioned, but my jtop says openCV: 4.5.1 with CUDA: No, please suggest what to do
after i completed all the steps when i run jtop open cv : 4.5 with cuda : No. and also my cuda version is 11.4.315. what can i do for this?
hi mam ,
I installed python 3.8 and made it default for python
in python3.6 cv2 module in present of version 4.1.1
when i created virtual environment of python3.8 with –system-packages like as you are mention their cv2 module is not found
please guide me where i am doing wrong
how to reset the system mam please tell me, i want to reset everything and i wanna follow your videos…please help me out..
Hi, I executed : sudo sh -c "echo '/usr/local/cuda/lib64' >> /etc/ld.so.conf.d/nvidia-tegra.conf“
then the prompt became like this : >
is this correct ? or I did something wrong …. thank you for your hard work
trying to increase swap file using your steps, now my Jetson Nano is not able to boot