Computer Vision Toolbox

Design and test computer vision, 3D vision, and video processing systems


Computer Vision Toolbox™ provides algorithms, functions, and apps for designing and testing computer vision, 3D vision, and video processing systems. You can perform object detection and tracking, as well as feature detection, extraction, and matching. For 3D vision, the toolbox supports single, stereo, and fisheye camera calibration; stereo vision; 3D reconstruction; and lidar and 3D point cloud processing. Computer vision apps automate ground truth labeling and camera calibration workflows.

You can train custom object detectors using deep learning and machine learning algorithms such as YOLO v2, Faster R-CNN, and ACF. For semantic segmentation you can use deep learning algorithms such as SegNet, U-Net, and DeepLab. Pretrained models let you detect faces, pedestrians, and other common objects.

You can accelerate your algorithms by running them on multicore processors and GPUs. Most toolbox algorithms support C/C++ code generation for integrating with existing code, desktop prototyping, and embedded vision system deployment.

Get Started:

Deep Learning and Machine Learning

Detect, recognize, and segment objects using deep learning and machine learning.

Object Detection and Recognition

Frameworks to train, evaluate, and deploy object detectors such as YOLO v2, Faster R-CNN, ACF, and Viola-Jones. Object recognition capability includes bag of visual words and OCR. Pretrained models detect faces, pedestrians, and other common objects.

Object detection using Faster R-CNN. 

Semantic Segmentation

Segment images and 3D volumes by classifying individual pixels and voxels using networks such as SegNet, FCN, U-Net, and DeepLab v3+.

Ground Truth Labeling

Automate labeling for object detection, semantic segmentation, and scene classification using the Video Labeler and Image Labeler apps.

Ground truth labeling with the Video Labeler app.

Lidar and 3D Point Cloud Processing

Segment, cluster, downsample, denoise, register, and fit geometrical shapes with lidar or 3D point cloud data.

Lidar and Point Cloud I/O

Read, write, and display point clouds from files, lidar, and RGB-D sensors.

Point Cloud Registration

Register 3D point clouds using Normal-Distributions Transform (NDT), Iterative Closest Point (ICP), and Coherent Point Drift (CPD) algorithms.

Registration of and stitching a series of point clouds.

Segmentation and Shape Fitting

Segment point clouds into clusters and fit geometric shapes to point clouds. Segment ground plane in lidar data for automated driving and robotics applications.

Segmented lidar point cloud.

Camera Calibration

Estimate intrinsic, extrinsic, and lens-distortion parameters of cameras.

Single Camera Calibration

Automate checkerboard detection and calibrate pinhole and fisheye cameras using the Camera Calibrator app.

Stereo Camera Calibration

Calibrate a stereo pair to compute depth and reconstruct 3D scenes.

Stereo camera calibrator app.

3D Vision and Stereo Vision

Extract the 3D structure of a scene from multiple 2D views. Estimate camera motion and pose using visual odometry.

Stereo Vision

Estimate depth and reconstruct a 3D scene using a stereo camera pair.

Stereo disparity map representing relative depths.

Feature Detection, Extraction, and Matching

Feature-based workflows for object detection, image registration, and object recognition.

Detecting an object in a cluttered scene using point feature detection, extraction, and matching.

Feature-Based Image Registration

Match features across multiple images to estimate geometric transforms between images and register image sequences.

Panorama created with feature-based registration.

Object Tracking and Motion Estimation

Estimate motion and track objects in video and image sequences.

Detecting moving objects with a stationary camera.

OpenCV Interface

Interface MATLAB and Simulink with OpenCV-based projects and functions

Code Generation

Integrate algorithm development with rapid prototyping, implementation, and verification workflows.

Latest Features

Point Cloud Deep Learning

Detect and classify objects in 3-D point clouds

Deep Learning with Big Images

Train and use deep learning object detectors and semantic segmentation networks on very large images

Simultaneous Localization and Mapping (SLAM)

Perform point cloud and camera SLAM

Bar Code Reader

Detect and decode 1-D and 2-D barcodes

SSD Object Detection

Detect objects in images using a single shot multibox object detector (SSD)

See release notes for details on any of these features and corresponding functions.