# Object Detection

> AI finds each thing in a photo and draws a box around it.

**Field:** Artificial Intelligence  
**Category:** Robotics & Vision  
**Also known as:** Object Recognition, Bounding Box Detection

## Think of it like

It is like a game of I spy. You point at each thing you see and say what it is.

## Definition

Object detection is when an AI model finds each thing in a picture and draws a box around it. Each box has a label, such as car or person, and a score for how sure the model is. So it says where things are, and how many. Fast models can do this on live video many times a second. It is used in self-driving cars, shop cameras, wildlife counts and photo apps.

## Example

A city counts bikes on a busy road. A camera runs object detection on the live video, boxes each bike as it passes, and logs 2,140 in one day.

## Why it matters

Most real tasks need to know where things are, not just what the picture is. Detection gives both.

## Common mistake

Trusting every box. Small, far-off or half-hidden things are often missed, so set the score cut-off with care.

## Three principles

- **A box for each thing.** Where it is.
- **Label and score.** What it is.
- **Counts too.** How many.

## Related terms

- [Image Classification](https://learn.benibix.com/term/ai/image-classification)
- [Image Segmentation](https://learn.benibix.com/term/ai/image-segmentation)
- [Computer Vision](https://learn.benibix.com/term/ai/computer-vision)
- [Autonomous Vehicle](https://learn.benibix.com/term/ai/autonomous-vehicle)
- [Visual Grounding](https://learn.benibix.com/term/ai/visual-grounding)
- [You Only Look Once (YOLO)](https://learn.benibix.com/term/ai/yolo)
- [Object Tracking](https://learn.benibix.com/term/ai/object-tracking)

## Told apart from

- [Image Classification vs Object Detection](https://learn.benibix.com/compare/image-classification-vs-object-detection): People often think image classification and object detection do the same job. Classification gives the whole picture one label, such as cat. It does not say where the cat is. Detection finds each thing in the picture and draws a box around it, with a label for each. Use the first to sort pictures, and the second to find, count or follow things in them.
- [Object Detection vs Image Segmentation](https://learn.benibix.com/compare/object-detection-vs-image-segmentation): People often think object detection and image segmentation give the same answer. Detection draws a box around each thing, and the box takes in some of the background too. Segmentation labels each pixel, so it gives the exact shape. A box is cheaper and faster. The exact shape is worth the cost when edges matter, as in a scan or a photo edit.
- [Visual Grounding vs Object Detection](https://learn.benibix.com/compare/visual-grounding-vs-object-detection): People think visual grounding is the same as object detection. Both draw boxes on a picture, but they answer different asks. Object detection finds every thing of a known kind, like every cup on the table. Visual grounding reads a phrase, such as the red cup on the left, and finds the one thing it points to.
- [Object Detection vs Object Tracking](https://learn.benibix.com/compare/object-detection-vs-object-tracking): People think tracking is just detection run on every frame, and it is not. Detection finds the cars in one frame and forgets them. Tracking links each box to the one before, so car 7 stays car 7. Only then can you count cars, measure speed or guess where one is going next.

![A street photo with a box drawn around each car and each person, and a label and score on every box.](https://learn.benibix.com/diagrams/rb-object-detection.svg)

---

Source: https://learn.benibix.com/term/ai/object-detection
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
