What is the Single Shot MultiBox Detector (SSD)?

The Single Shot MultiBox Detector (SSD) is an object detection technique that uses a deep neural network to extract features and directly predict bounding boxes and classes in a single pass over the image (single shot), which makes it fast and efficient. SSD uses multiple feature maps at different scales to detect large and small objects at the same time, which gives it high accuracy with speed suitable for real-time applications such as smart surveillance and autonomous driving.