# Position Tracking feature count

**URL:** <https://community.stereolabs.com/t/position-tracking-feature-count/10805>\
**Category:** ROS2\
**Tags:** ros, sdk, jetson\
**Created:** [February 14, 2026, 4:19pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805 "2026-02-14T16:19:02Z")\
**Posts on this page:** 20\
**Page:** 1

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 14, 2026, 4:19pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/1 "2026-02-14T16:19:02Z")

</div>

Hi,  
I was wondering if there’s a way to get the “number of features“ currently tracked by the feature tracker of the position tracker? That way, I can reset the position tracker when there are fewer features without accumulating error in the system

Thanks!

---

<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:** [February 16, 2026, 12:02pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/2 "2026-02-16T12:02:32Z")

</div>

There is a way to perform this operation:  
you can retrieve and count the positional tracking landmarks.

The `zed-sdk` GitHub repository provides a sample code that you can use for this purpose:

> <https://github.com/stereolabs/zed-sdk/blob/master/positional%20tracking/positional%20tracking/cpp/src/main.cpp#L249-L280>

You can also find a similar example code in the ZED ROS2 Wrapper:

> <https://github.com/stereolabs/zed-ros2-wrapper/blob/4540840984da2ddab93daf07fe37b23af55a69ca/zed_components/src/zed_camera/src/zed_camera_component_main.cpp#L6539-L6557>

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 17, 2026, 6:13pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/3 "2026-02-17T18:13:17Z")

</div>

Hi, thanks for the solution,  
I added a logger - \>

```auto
RCLCPP_INFO(get_logger(), "SLAM features: %zu total, %zu tracked",
            map_lm3d.size(), map_lm2d.size());

```

I was wondering what would be a good threshold for map\_lm3d.size() and map\_lm2d.size() to reset slam to avoid erroneous measurements

When the vehicle is very close to features, as seen in the image

 ![Screenshot from 2026-02-17 13-09-20](https://community.stereolabs.com/uploads/default/original/2X/6/6e669ae537ff0f2b5d9d5975f56c991e225436a7.jpeg)

The system accumulates angular error as seen in the next images  
The pink line is the approximate real alignment of the asile, and the red points are the tracked points of the slam, which have some error as seen in the image

 ![annotely_image (2)](https://community.stereolabs.com/uploads/default/original/2X/a/abc4091d680ed9b52ee9ba7c789f747fb2270af6.png)

 ![Screenshot from 2026-02-17 12-44-15](https://community.stereolabs.com/uploads/default/original/2X/2/2ab6d94144477179f7c5df5c3ec1da33603c67ad.png)

thanks!

---

<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:** [February 17, 2026, 6:31pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/4 "2026-02-17T18:31:46Z")

</div>

This is interesting information.  
Do you have an SVO recorded in the same conditions that we could use to improve the PT behaviors with similar conditions?

> [@hey\_you](#):
>
> I was wondering what would be a good threshold for map\_lm3d.size() and map\_lm2d.size() to reset slam to avoid erroneous measurements

Unfortunately, I do not have this information. You can only evaluate it with tests on the field.

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 17, 2026, 6:42pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/5 "2026-02-17T18:42:21Z")

</div>

Hi,  
I sent the SVO over the support email. Please do share your findings.

Thanks!

---

<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:** [February 17, 2026, 6:45pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/6 "2026-02-17T18:45:32Z")

</div>

Thank you. Really appreciated it.

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 17, 2026, 7:53pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/7 "2026-02-17T19:53:31Z")

</div>

I have some more findings. I was trying to visualize the landmarks in the image. I see that in some images, it just tracks ceiling points. What could be the reason for that

 ![Screenshot from 2026-02-17 14-49-25](https://community.stereolabs.com/uploads/default/original/2X/9/94217ad12ecfaa0c3940bfc49c4d0cd6ccbe8f10.jpeg)

Ideally, it should be like this imo

 ![Screenshot from 2026-02-17 14-49-33](https://community.stereolabs.com/uploads/default/original/2X/2/2edbdfde310a8f648b6dbe0e57285c835144aa88.jpeg)

 ![Screenshot from 2026-02-17 14-50-13](https://community.stereolabs.com/uploads/default/original/2X/2/28a13ac09099af86f275311dc49a0a3bbd2588cf.jpeg)

 ![Screenshot from 2026-02-17 14-50-29](https://community.stereolabs.com/uploads/default/original/2X/8/87858877c1ef7b57ca4c6613ac0851662f2c2d2d.jpeg)

 ![Screenshot from 2026-02-17 14-50-57](https://community.stereolabs.com/uploads/default/original/2X/d/d97b6ae1f832d1988ad8f25d8636ccc89271934f.jpeg)

---

<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:** [February 18, 2026, 9:25am UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/8 "2026-02-18T09:25:10Z")

</div>

It looks like the motion blur is one of the causes of the reduced number of features  
This condition is normally accentuated when the robot is rotating.

You could try to fix the exposure time to a low value to reduce the amount of blur effect.

Are you using a ZED 2i or a ZED X camera?

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 18, 2026, 2:30pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/9 "2026-02-18T14:30:51Z")

</div>

Hi, thanks for the response, currently I am using the Zed2i, I have ordered a ZedX as well to see if it helps (yet to get my hands on it), in the mean timeif you have any recommnedations of things I could try and how could I tune the exposure time please let me know!

Thanks!

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 18, 2026, 7:25pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/10 "2026-02-18T19:25:19Z")

</div>

since GEN\_3 uses IMU, I would think IMU should be abe to help when the visual features go low while its turning, is there something I can do to improve IMU calibration or weightage?

Thanks!

---

<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:** [February 19, 2026, 3:25pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/11 "2026-02-19T15:25:06Z")

</div>

> [@hey\_you](#):
>
> IMU, I would think IMU should be abe to help when the visual features go low while its turning,

This is true, but IMU data integration is prone to drift; this is why a full SLAM cannot be performed using only IMU sensors.

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 19, 2026, 3:41pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/12 "2026-02-19T15:41:47Z")

</div>

I agree, but since this thing lasts for a couple of frames, I’d think in a tightly coupled VIO system that should be ok, but I see your point. If I change the exposure settings, would that impact Slam’s performance?

---

<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:** [February 19, 2026, 4:56pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/13 "2026-02-19T16:56:59Z")

</div>

> [@hey\_you](#):
>
> If I change the exposure settings, would that impact Slam’s performance?

A lower exposure time causes less blur, this helps the feature detection step.

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 19, 2026, 5:08pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/14 "2026-02-19T17:08:22Z")

</div>

But it would also reduce the light entering the sensor, right? Just wondering about the impact of that

---

<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:** [February 19, 2026, 5:13pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/15 "2026-02-19T17:13:03Z")

</div>

> [@hey\_you](#):
>
> But it would also reduce the light entering the sensor, right?

Yes, you must find the right compromise. It depends on your environmental conditions.

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 20, 2026, 5:03pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/16 "2026-02-20T17:03:24Z")

</div>

Hi,  
any findings from the SVO? or is it caused just because of motion blur?

Thanks!

---

<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:** [February 20, 2026, 5:23pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/17 "2026-02-20T17:23:16Z")

</div>

> [@hey\_you](#):
>
> any findings from the SVO? or is it caused just because of motion blur?

Can you share your settings? Are you using the default values or have you changed something?

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 20, 2026, 5:31pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/18 "2026-02-20T17:31:17Z")

</div>

sure, I just have minor changes. I have attached the files

[common\_stereo\_5\_2.yaml](https://community.stereolabs.com/uploads/short-url/jiL4Bozpd9AyahyBkitaqCrPbuf.yaml) (22.0 KB)

[zed2i\_5\_2.yaml](https://community.stereolabs.com/uploads/short-url/mAoWis89auxPUypaCp36oseW5Pa.yaml) (706 Bytes)

Thanks!

---

<div class="post-metadata">

**Author:** ![hey\_you](https://community.stereolabs.com/letter_avatar_proxy/v4/letter/h/77aa72/32.png) [@hey\_you](https://community.stereolabs.com/u/hey_you)\
**Post date:** [February 21, 2026, 5:04pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/19 "2026-02-21T17:04:34Z")

</div>

Hi,  
I came across a great article on IMU preintegration (link below) and found it really insightful, especially how it can help during motion blur and brief featureless intervals. I’d really appreciate a deeper explanation of how ZED’s positional tracking uses IMU preintegration, and whether there are any potential improvements or enhancements worth exploring.  
[https://dongwonshin.vercel.app/blog/imu-preintegration-part1](https://dongwonshin.vercel.app/blog/imu-preintegration-part1?utm_source=chatgpt.com)  
Thanks in advance!

---

<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:** [February 23, 2026, 5:03pm UTC](https://community.stereolabs.com/t/position-tracking-feature-count/10805/20 "2026-02-23T17:03:42Z")

</div>

> [@hey\_you](#):
>
> I’d really appreciate a deeper explanation of how ZED’s positional tracking uses IMU preintegration, and whether there are any potential improvements or enhancements worth exploring.

Unfortunately, this is undisclosed information.

In any case, you are free to test any third-party algorithm for sensor data fusion.  
The positional tracking module of the ZED SDK is not mandatory. You can disable it and use your custom positional tracking processing.
