# Is it possible to split the imaging module and the depth computing module?

**URL:** <https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109>\
**Category:** C++\
**Tags:** zed-gstreamer, zed-sdk, jetson, depth, windows\
**Created:** [March 28, 2026, 9:26am UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109 "2026-03-28T09:26:20Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![JanFrog](https://community.stereolabs.com/user_avatar/community.stereolabs.com/janfrog/32/6013_2.png) [@JanFrog](https://community.stereolabs.com/u/JanFrog)\
**Post date:** [March 28, 2026, 9:26am UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109/1 "2026-03-28T09:26:20Z")

</div>

I’m working on a project on extracting depth of a specific item in the scene which is extremely sensitive to realtime performance.

I’m wondering can it be more efficient on depth-computing if I could manage the images pushed into depth-computing module by keeping specific Mat ROI and delete the rest part according to YOLO’s result so that I can improve the operation efficiency.

Furthermore, is it possible to achieve that on Gstreamer ?

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [March 30, 2026, 1:23pm UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109/2 "2026-03-30T13:23:31Z")

</div>

Hi @JanFrog  
You can use the Region of Interest feature to extract depth information only from specific zones of the image:

> **[Camera Class Reference | API Reference | Stereolabs](https://www.stereolabs.com/docs/api/classsl_1_1Camera.html#afefd8c2cf4f07e7eee47dfe098920eaa)**
>
> This class serves as the primary interface between the camera and the various features provided by the SDK. More...

---

<div class="post-metadata">

**Author:** ![lin-yuxiang](https://community.stereolabs.com/user_avatar/community.stereolabs.com/lin-yuxiang/32/6036_2.png) [@lin-yuxiang](https://community.stereolabs.com/u/lin-yuxiang)\
**Post date:** [March 31, 2026, 8:31am UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109/3 "2026-03-31T08:31:21Z")

</div>

Hi @Myzhar , when the ROI is set, should the depth map be calculated within this area? Or just crop the ROI from the whole resolution depth map to output

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [March 31, 2026, 10:18am UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109/4 "2026-03-31T10:18:16Z")

</div>

Hi @lin-yuxiang  
Welcome to the [StereoLabs](https://www.stereolabs.com/) community.

> [@lin-yuxiang](#):
>
> when the ROI is set, should the depth map be calculated within this area? Or just crop the ROI from the whole resolution depth map to output

The depth is calculated only in the specific area.

---

<div class="post-metadata">

**Author:** ![JanFrog](https://community.stereolabs.com/user_avatar/community.stereolabs.com/janfrog/32/6013_2.png) [@JanFrog](https://community.stereolabs.com/u/JanFrog)\
**Post date:** [March 31, 2026, 10:46am UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109/5 "2026-03-31T10:46:01Z")

</div>

Thank you for reviewing on this post.

I have another question, can the last _ **grab** _ be stored in memory so that I can preprocess the next frame of the image before YOLO infers the ROI ?

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [March 31, 2026, 10:47am UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109/6 "2026-03-31T10:47:43Z")

</div>

> [@JanFrog](#):
>
> can the last _ **grab** _ be stored in memory so that I can preprocess the next frame of the image before YOLO infers the ROI ?

No, this is not possible. You are always one frame late.

---

<div class="post-metadata">

**Author:** ![Myzhar](https://community.stereolabs.com/user_avatar/community.stereolabs.com/myzhar/32/11_2.png) [@Myzhar](https://community.stereolabs.com/u/Myzhar)\
**Post date:** [March 31, 2026, 11:37am UTC](https://community.stereolabs.com/t/is-it-possible-to-split-the-imaging-module-and-the-depth-computing-module/11109/7 "2026-03-31T11:37:12Z")

</div>

> [@Myzhar](#):
>
> The depth is calculated only in the specific area.

@lin-yuxiang I checked with the SDK Team to confirm this, and I was wrong.  
The ROI is extracted from the full depth map.  
It’s not possible to calculate the depth map on a subsection of the images.
