# Image Tracking Specifications

## Overview

### Scene

* **AR Scene: Image AR**
* **Collection: Image AR**

### What is Image Tracking? 

Image tracking, in full, refers to Image Detection and Tracking (i.e., an Image AR scenario).

It consists of two components:

* Image Detection
* Image Tracking<br>

To evaluate the quality of the experience, both factors must be considered:

* Whether image detection is fast enough
* Whether the AR scene remains stable after detection

> ![](/files/mgodJcMPF1l3iTUYUIYg)![](/files/ZHexdCJjYePbWd9ivEw2)
>
> When using the Collection feature (multi-scene recognition entry), the cloud-based image recognition algorithm will be used.
>
> Therefore, the recognition images must comply with both the Image Tracking specifications and the Cloud Recognition Image specifications.

***

## Guidelines

<table><thead><tr><th width="164.58984375">Category</th><th>Descriptions and Examples </th></tr></thead><tbody><tr><td><strong>Valid Format</strong></td><td>jpg, jpeg</td></tr><tr><td><strong>Valid Color Mode</strong></td><td><p>Set the image to RGB to help detect any color deviation promptly.</p><div><figure><img src="/files/5LRAintPeaJwRG5Oo6rt" alt=""><figcaption></figcaption></figure></div><p><br>When exporting, check “Color Space → Convert to sRGB”, and verify after export to ensure no color deviation is present.<br></p></td></tr><tr><td><strong>Recommended Image Resolution</strong></td><td><p>The image resolution is recommended to be between 480×480 and 1280×1280, with around 800 being ideal.</p><div><figure><img src="/files/UIkdEgl9OCHaz1DyzXZw" alt=""><figcaption></figcaption></figure></div><p></p></td></tr><tr><td><p></p><p><strong>Recommended Image Aspect Ratio</strong></p></td><td><p>Landscape: 1:1 to 16:9 (Aspect Ratio 1 to 1.78)</p><p>Portrait: 9:16 to 1:1 (Aspect Ratio 0.56 to 1)<br></p><div><figure><img src="/files/Fvub6uhOuAZNTQDUCamO" alt=""><figcaption></figcaption></figure></div><div><figure><img src="/files/ERfVwCzzntxH7CccjyqC" alt=""><figcaption></figcaption></figure><figure><img src="/files/kczsia0QERiXZ8GQ58vP" alt=""><figcaption></figcaption></figure><figure><img src="/files/OnjzAtRKvXBGcvm6KsPF" alt=""><figcaption></figcaption></figure></div><div><figure><img src="/files/tc6q1NHoyT9PisJIi97g" alt=""><figcaption></figcaption></figure></div><div><figure><img src="/files/2JUteHCAK9h8h4GUOuWm" alt=""><figcaption></figcaption></figure></div><div><figure><img src="/files/av1UTg3qEWn7FZ73R9bk" alt=""><figcaption></figcaption></figure></div><p></p></td></tr><tr><td><strong>Rich Detail</strong></td><td><p></p><p>The following are examples of poor-quality images:</p><div><figure><img src="/files/9Y6oHVvuuipVrZegYFQ2" alt=""><figcaption></figcaption></figure><figure><img src="/files/Ubrdi0xxg9M1lEHJB4yX" alt=""><figcaption></figcaption></figure><figure><img src="/files/CItDr6CRdqFmnNc28WYS" alt=""><figcaption></figcaption></figure><figure><img src="/files/2MRySBMHh9ZTVEO9evw4" alt="" width="375"><figcaption></figcaption></figure></div><p><br></p></td></tr><tr><td><p></p><p><strong>Avoid extensive whitespace</strong></p></td><td><div><figure><img src="/files/M5WpltHiYYpWYV7Ar3bP" alt=""><figcaption></figcaption></figure><figure><img src="/files/h4ZFTC8IfBQieT9EGysx" alt=""><figcaption></figcaption></figure><figure><img src="/files/viyKo7WaYGTUGwRomP7S" alt=""><figcaption></figcaption></figure></div><p></p><div><figure><img src="/files/84dhjFCosETaLnkAXbYh" alt=""><figcaption></figcaption></figure></div><p></p><p>Too much empty space can reduce tracking stability. Minimize blank regions and ensure the main subject is clearly emphasized.</p></td></tr><tr><td><strong>Avoid repeatitive patterns /</strong> <strong>Symmetrical images</strong></td><td><p>Symmetrical images tend to be unstable:<br><img src="/files/H41rvPygsM0se06UqpGg" alt=""><br><img src="/files/6okZVSncMtpnURum7PM5" alt=""><br></p><p>For images that are not perfectly symmetrical, the final assessment should be based on actual tracking performance.</p><div><figure><img src="/files/4XmK7orLiTUiVvaq9D8m" alt="" width="375"><figcaption></figcaption></figure></div><div><figure><img src="/files/23hSUVSUs5mETnytpLbl" alt=""><figcaption></figcaption></figure></div><p></p><p><br>Repetitive Patterns Can Lead to Detection Difficulties:<br></p><div><figure><img src="/files/pelLY1UXws6VnrZjn7Rr" alt=""><figcaption></figcaption></figure><figure><img src="/files/rsHNfrGp9dgT6TH3ChAT" alt=""><figcaption></figcaption></figure><figure><img src="/files/tI9SItxsZmrV26HCS4U3" alt=""><figcaption></figcaption></figure></div></td></tr><tr><td><p></p><p><strong>Uniform Distribution of Feature Points</strong></p></td><td><p>Try to avoid large Single-color region around the borders. <br>Add appropriate details to achieve a more uniform distribution of feature points.<br></p><div><figure><img src="/files/tfQeoTPDHmihHRqpdUDj" alt=""><figcaption></figcaption></figure><figure><img src="/files/4ZXuV0YefyvOrog5fmp5" alt=""><figcaption></figcaption></figure></div><div><figure><img src="/files/hfrMrz0oQAuEyg0hKezh" alt=""><figcaption></figcaption></figure></div><div><figure><img src="/files/fX5JAsznvuf3djStoFX1" alt=""><figcaption></figcaption></figure></div><p></p></td></tr><tr><td><strong>Cloud Recognition vs Image Tracking</strong></td><td><h4>Different Feature Point Extraction Principles</h4><p><br>As the principles of feature point extraction differ, certain smooth or rounded shapes may receive a low star rating in cloud recognition, yet still perform adequately in image tracking.</p><div><figure><img src="/files/vvhmA5OURRM1fHQSCFcx" alt=""><figcaption></figcaption></figure></div><p></p><p>Actual Performance may still jitter. <br><img src="/files/9w45FGGfS2H2lUPVuPtd" alt=""><br><br><img src="/files/b4qmRq2AKMUBs7NelGaq" alt=""><br><br><strong>Higher Tolerance for Image Blur:</strong> <br><img src="/files/ifCsIwbQrbSt3o4GV8bP" alt=""><img src="/files/RLiq5p8T0yt8knl8GcvI" alt=""><br>Even with complex or slightly blurred images, tracking can remain relatively stable</p><p>(This does not encourage using blurred designs, only indicates that the system offers higher tolerance.)</p></td></tr><tr><td><strong>Avoid Gradient Designs</strong></td><td>Avoid using large gradient areas<br><img src="/files/kL4FAbreqdvc6uw4j3yR" alt=""></td></tr></tbody></table>

***

## Tips

### How to Improve Image Recognition

**Recommended Practice**

Before uploading an image for recognition, add a white border around it.

If the image will be printed, include a white border on the printed version as well.

<figure><img src="/files/vxRjNc6hj0jbqNZgx7cQ" alt=""><figcaption></figcaption></figure>

### Other Methods to Improve Image Tracking Stability

**Place AR objects tightly on the Image marker**

<figure><img src="/files/UE8fxUjjAN99kcyoPcW9" alt=""><figcaption></figcaption></figure>

**The AR scene placed on the Image marker should not be too tall.**

Example: Scanning a wall poster triggers an AR interaction.

<figure><img src="/files/ZPdlzcGMkmcn32NnXOxX" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/TIERBUhDWZQQWn8kNWcU" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/3QrZkrdsAycbhvHcMSeK" alt=""><figcaption></figcaption></figure>

* Users’ perception of model "shaking" is related to its height: the higher the AR object, the more noticeable the visual displacement at the top becomes.
* Design AR interactions thoughtfully to reduce the amplified shaking effect caused by overly tall layouts.

### **Include animation in the AR experience**

* Rich scene animations can visually dilute the discomfort caused by minor jitter.
* In some cases, even when tracking jitter is present, users may hardly notice it.

<div align="left"><figure><img src="/files/B2oMIAEJcq1HAgmoH6uC" alt="" width="152"><figcaption></figcaption></figure></div>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs-en.kivicube.com/ar-asset-creation-guide/image-marker/image-tracking-specifications.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.