---
title: "Visualize object detections"
description: "Draw bounding boxes on images to visualize object detection results."
url: "https://www.pixeltable.com/notebooks/img-visualize-detections"
updated: "2026-10-13"
---

# Visualize object detections

Draw bounding boxes on images to visualize object detection results.

- **Type:** Notebook
- **Group:** Images

## How it works

You create a pipeline that detects objects and then draws the results on the original image.

## What it covers

- Run object detection with YOLOX
- Draw bounding boxes on images
- Color-code by object class

## What it uses

- **Install:** `pip install pixeltable pixeltable-yolox`
- **Pixeltable calls:** `yolox.yolox()`, `vision.bboxes_draw()`, `pxt.create_table()`, `add_computed_column()`, `insert()`

## A look at the code

```python
# Step 1: Run object detection
images.add_computed_column(
    detections=yolox(images.image, model_id='yolox_m', threshold=0.5)
)
```

## Open it

- **Open in Colab:** https://colab.research.google.com/github/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/images/img-visualize-detections.ipynb
- **Docs page:** https://docs.pixeltable.com/howto/cookbooks/images/img-visualize-detections
- **Source on GitHub:** https://github.com/pixeltable/pixeltable/blob/release/docs/release/howto/cookbooks/images/img-visualize-detections.ipynb