Empower your devices to perceive and understand the world around us with powerful software that’s masterful, scalable, and tested.
NVIDIA software enables the end-to-end computer vision workflow—from model development to deployment—for individual developers, higher education and research, and enterprises.
Computer vision is a field of technology that enables devices like smart cameras to acquire, process, analyze, and interpret images and videos. For example, the driver assistance system on a vehicle designed with computer vision algorithms uses cameras and other sensors to not only display, but to perceive what’s in front of and behind it to identify and classify regions or points of interest within an image frame. In this case, computer vision has a safety application—helping the vehicle operator to navigate around road debris, other vehicles, animals, and people. Similarly, farmers might rely on computer vision-enabled devices to automatically identify weeds and where crops are growing well over a large field to increase yield. Today’s computer vision tasks like these are based on artificial intelligence and, more specifically, deep learning, a type of machine learning patterned after the brain. Deep learning-based computer vision models enable devices to perform and adapt like a human expert while requiring significantly less input.
Computer Vision Techniques
Most computer vision techniques begin with a model, or a mathematical algorithm, that has been trained with volumes of data to accomplish a specific task. Some of the common techniques include:
Classification involves determining and classifying what object is in an image or video frame. Classification models are usually trained with a large dataset to identify simple objects like dogs, cats, chairs, or very specific ones like the type of vehicles in a road scene. The quality of the classification output depends on the training data used. The more the quantity and diversity of the training data, the higher the degree of precision.
Detection involves locating and localizing an object or multiple objects within an image or a video frame. The algorithm outputs a rectangular bounding box around the detected object to indicate its location in the image. Object detectors may be trained to detect cars, road signs, people, or other objects of interest within an image or a video frame.
Segmentation involves locating objects or regions of interest precisely in an image by assigning a label to every pixel in an image. This way, pixels with the same label share similar characteristics, such as color, or texture. Segmentation models are very commonly used in medical imaging for performing tasks like automatically detecting tumors in Magnetic Resonance Imaging (MRI) scans.
Image Synthesis involves creating or artificially generating images containing certain desired objects or content. Generative Adversarial Networks, or GANs, are a type of neural network that are commonly used for synthesizing these images, or even frames of a video. A common application of image synthesis is text to image translation that involves using GANs to generate images based on a textual description.
Computer Vision Workflow
The computer vision workflow is highly dependent on the task, model, and data. A typical, simplified AI-based end-to-end CV workflow involves three (3) key stages— Model and Data Selection, Training and Testing/Evaluation, and Deployment and Execution.
Let’s look at these stages using the CV detection technique to identify a dog
(classification and segmentation-based techniques would follow an identical workflow).
Finding Fido: Developing an AI-Based, Object-Detection CV Workflow
Challenge: You want to build software for a monitoring system that automatically detects when your dog arrives at or leaves through the backdoor.
Three Stage Solution:
Model and Data Selection
Select an object-detection model.
Collect photos of your dog (let's call him Fido) that you can use to train and fine-tune your model to recognize Fido.
Training and Testing/Evaluation
Train and test your model using different photos of Fido to affirm the model's accuracy in detecting him.
Deployment and Execution
Deploy the trained model to hardware to monitor and detect the next time your dog leaves the house using an installed camera.
Below, a high-level diagram summarizes the AI-based CV solution.
NVIDIA enables the end-to-end CV workflow. NVIDIA not only provides AI-based pre-trained models, but also tools for Training and Testing/Evaluation and software application frameworks for Deployment and Execution. Learn more below about how NVIDIA enables every stage of CV development.
Get Started with NVIDIA’s Pre-Trained Models
for Computer Vision
Developing models for these techniques on your own would require a lot of training data, time, and expertise. Here’s the good news- you do not have to be an expert to get started. NVIDIA hosts a number of pre-trained models, already-built and ready-to-use, to start developing your own computer vision solutions. Start with NGC, our GPU-accelerated software hub, to learn about computer vision models and resources, as well as other deep learning-based speech and natural language processing use cases and application frameworks.
Develop the End-to-End Computer
Start with NVIDIA pre-trained models, TAO, and DeepStream to make the end-to-end computer vision AI development process easier.
AI Model Adaptation Framework
Fine-tune pre-trained models with custom data to produce highly accurate computer vision and conversational AI models in hours rather than months.LEARN MORE
Streaming Analytics Toolkit
NVIDIA DeepStream SDK
Build real-time vision AI applications for multi-sensor processing, video, audio and image understanding.
Explore Computer Vision Across NVIDIA Software
Learn how to develop computer vision applications using NVIDIA's industry-specific software products and platforms.
Develop computer vision models for gesture recognition, heart rate monitoring, mask detection, and body pose estimation in a hospital room to detect falls. Build, manage, and deploy workflows in medical imaging, medical devices with streaming video, and smart hospitals.Learn More
Develop end-to-end (E2E) computer vision solutions for the autonomous vehicle (AV) and the intelligent cockpit (IX). Collect and generate computer vision data, train DNN models using the E2E simulation platform (DRIVE Sim).Learn More
Create virtual collaboration and content creation applications with video effects, audio effects and augmented reality.Learn More
Envision Next-Generation Computer Vision
Discover new technologies and innovative research work on computer vision at NVIDIA
Learn what problems our computer vision research engineers and data scientists have been solving. Read our latest publications.
Explore NVIDIA’s GPU-Accelerated Libraries and Optimization Platform
Learn how NVIDIA’s libraries and optimization platform accelerate computer vision on GPUs.
Data Pipeline Accelerator
Data Loading Library (DALI)
Load and process computer vision and audio data using GPUs. Use directly in TensorFlow, PyTorch, MXNet, and PaddlePaddle models.Learn More
3D Deep Learning Research Library
NVIDIA KAOLIN Library
Generate synthetic data. Render and visualize 3D training datasets.
Image and Signal-Processing Library
NVIDIA Performance Primitives (NPP)
Deploy ready-to-use, domain-specific, high-performance functions for image, video, and signal processing.Learn More
Image Decoding Libraries
nvJPEG and nvJPEG2000
Accelerate processing of JPEG and JPEG2000 images.
Motion Flow Generation
Optical Flow SDK
Recognize, classify, and track objects and actions in a video stream by enhancing flow-vector computation between frames using GPUs.
Your World, Powered by NVIDIA Computer Vision
Get Started With Frequently Asked Questions
Computer vision is more than research. It delivers practical, real-world solutions that change lives. NVIDIA’s deep expertise in artificial intelligence and high-performance computing provides endless opportunities to meaningfully impact the world.
Learn the Fundamentals of Computer Vision
New to computer vision? Want a primer before jumping in? Learn the Fundamentals of Deep Learning with hands-on exercises for CV in this eight-hour course offered by the Deep Learning Institute . You’ll learn how to train deep learning models from scratch and use pre-trained models, experiment with different model architectures, explore deep learning tools and techniques, and work with datasets to improve model accuracy. You’ll also earn a certification to show your accomplishment.
What’s New in Computer Vision
AI Research Holds the Key to Affordable and Accessible Drug Development
Published in Nature Machine Intelligence, a panel of experts shares a vision for the future of biopharma featuring collaboration between ML and drug discovery powered by GPUs.
How to Evaluate AI in Your Vendor’s Cybersecurity Solution
Considering new security software? AI and security experts Bartley Richardson and Daniel Rohrer from NVIDIA have advice: Ask a lot of questions.
Just Released: nvCOMP v2.3
The CUDA library, nvCOMP, now offers support for zStandard and Deflate standards, as well as modified-CRC32 checksum support and improved ANS performance.
Computer Vision: Real-World Applications
No challenge is too small and no company too big for computer vision. See innovative solutions in action—from startups to global manufacturers.
Improving Mobility for People with Low Vision (Biel Glasses) impaired
Increasing Vehicle Quality Using Computer Vision and AI (Audi)
Deploying NGC Models with Maximo Visual Inspection (IBM)
Partnering for Success
Global challenges take a community. We support you in tackling challenges with powerful solutions to meet your exact needs.
The World of Computer Vision Solutions is Powered by NVIDIA.