Object detection is the process of finding instances of real-world objects such as faces, bicycles, and buildings in images or videos. Object detection algorithms typically use extracted features and learning algorithms to recognize instances of an object category. It is commonly used in applications such as image retrieval, security, surveillance, and automated vehicle parking systems.

You can detect objects using a variety of models, including:

• Feature-based object detection

Detecting a reference object (left) in a cluttered scene (right) using feature extraction and matching. RANSAC is used to estimate the location of the object in the test image.

• Viola-Jones object detection

Face detection (left) and stop sign detection (right) using the Viola-Jones Object Detector.

• SVM classification with histograms of oriented gradients (HOG) features

Human detection using pretrained SVM with HOG features.

• Image segmentation and blob analysis

Moving cars are detected using blob analysis.

Image segmented using background subtraction. The moving pixels (foreground) detected from the video frame above are shown in white.

Other methods for detecting objects with computer vision include using gradient-based, derivative-based, and template matching approaches.

For more information, see MATLAB^®, Computer Vision System Toolbox™, and Image Processing Toolbox™.