You can perform visual inspection, object detection and tracking, as well as feature detection, extraction, and matching. You can automate calibration workflows for single, stereo, and fisheye cameras. For 3D vision, the toolbox supports stereo vision, point cloud processing, structure from motion, and real-time visual and point cloud SLAM. Computer vision apps enable team-based ground truth labeling with automation, as well as camera calibration. You can use pretrained object detectors or train custom detectors using deep learning and machine learning algorithms such as YOLO, SSD, and ACF. For semantic and instance segmentation, you can use deep learning algorithms such as U-Net, SOLO, and Mask R-CNN. You can perform image classification using vision transformers such as ViT. Pretrained models let you detect faces and pedestrians, perform optical character recognition (OCR), and recognize other common objects.

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