Installation Guide

1. Prerequisites

Before installing Turka Vision, ensure you have the following prerequisites:

Linux distribution (Ubuntu 20.04+ recommended) or Windows 10/11
Administrative/root access to the system
Stable internet connection for downloading packages
Basic knowledge of command line operations
Network access to camera devices (if installing on dedicated server)

2. System Requirements

Minimum Requirements

CPU: Intel i5 or AMD Ryzen 5 (4 cores minimum)
RAM: 8 GB (16 GB recommended for >10 cameras)
Storage: 100 GB free space (SSD recommended)
GPU: Integrated graphics (Dedicated GPU recommended for AI features)
Network: Gigabit Ethernet

Recommended for Production

CPU: Intel i7/Xeon or AMD Ryzen 7/EPYC (8+ cores)
RAM: 32 GB or higher
Storage: 1 TB+ NVMe SSD for system, separate storage for recordings
GPU: NVIDIA GTX 1060+ or RTX series for AI acceleration
Network: Dedicated network interface for camera traffic

3. Dependencies Installation

Ubuntu/Debian

# Update package list
sudo apt update && sudo apt upgrade -y

# Install Python 3.8+ and development tools
sudo apt install python3 python3-pip python3-dev build-essential -y

# Install multimedia libraries
sudo apt install ffmpeg libavformat-dev libavcodec-dev libavutil-dev -y
sudo apt install libswscale-dev libavfilter-dev libavdevice-dev -y

# Install OpenCV dependencies
sudo apt install libopencv-dev python3-opencv -y

# Install additional libraries
sudo apt install libx11-dev mesa-utils -y
sudo apt install git cmake pkg-config -y

Python Dependencies

# Install Python packages
pip3 install --user numpy opencv-python
pip3 install --user imutils requests
pip3 install --user flask flask-cors
pip3 install --user psutil netifaces

4. VALKKA Installation

Note: VALKKA requires compilation from source. This process may take 15-30 minutes depending on your system.

Download and Compile VALKKA

# Clone VALKKA repository
git clone https://github.com/elsampsa/valkka-core.git
cd valkka-core

# Create build directory
mkdir build && cd build

# Configure build with CMake
cmake .. -DCMAKE_BUILD_TYPE=Release

# Compile (use -j4 for 4 cores, adjust based on your CPU)
make -j$(nproc)

# Install system-wide
sudo make install

# Update library cache
sudo ldconfig

Install Python Bindings

# Navigate back to project root
cd ..

# Install Python bindings
python3 setup.py build_ext --inplace
pip3 install --user .

5. Turka Vision Setup

Download Turka Vision

# Create installation directory
sudo mkdir -p /opt/turka-vision
cd /opt/turka-vision

# Download Turka Vision package (replace with actual download link)
wget https://releases.turkavi.net/turka-vision-latest.tar.gz

# Extract package
tar -xzf turka-vision-latest.tar.gz
cd turka-vision

Initial Configuration

# Copy default configuration
cp config/default.conf config/turka-vision.conf

# Create directories for logs and recordings
sudo mkdir -p /var/log/turka-vision
sudo mkdir -p /var/lib/turka-vision/recordings

# Set permissions
sudo chown -R $USER:$USER /var/log/turka-vision
sudo chown -R $USER:$USER /var/lib/turka-vision

Install Service (Optional)

# Copy systemd service file
sudo cp scripts/turka-vision.service /etc/systemd/system/

# Reload systemd and enable service
sudo systemctl daemon-reload
sudo systemctl enable turka-vision.service

6. Installation Verification

Test VALKKA Installation

# Test VALKKA Python import
python3 -c "import valkka; print('VALKKA version:', valkka.VERSION_MAJOR, valkka.VERSION_MINOR, valkka.VERSION_PATCH)"

# Test basic functionality
python3 -c "from valkka import core; print('VALKKA core loaded successfully')"

Start Turka Vision

# Start Turka Vision manually
cd /opt/turka-vision
python3 main.py --config config/turka-vision.conf

# Or start as service
sudo systemctl start turka-vision.service
sudo systemctl status turka-vision.service

Access Web Interface

Open your web browser and navigate to:

http://localhost:8080

Default credentials: admin / admin (change immediately after first login)

Table of Contents