# Clarity on target to predict for detection track

**URL:** <https://community.drivendata.org/t/clarity-on-target-to-predict-for-detection-track/10674>\
**Category:** NASA Pose Bowl\
**Created:** [April 28, 2024, 10:48am UTC](https://community.drivendata.org/t/clarity-on-target-to-predict-for-detection-track/10674 "2024-04-28T10:48:48Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![datasiast](https://avatars.discourse-cdn.com/v4/letter/d/74df32/32.png) [@datasiast](https://community.drivendata.org/u/datasiast)\
**Post date:** [April 28, 2024, 10:48am UTC](https://community.drivendata.org/t/clarity-on-target-to-predict-for-detection-track/10674/1 "2024-04-28T10:48:48Z")

</div>

For the detection track, the instruction includes -  
“Your task on this track of the challenge is to take a set of test images as inputs to your solution and produce bounding boxes identifying the spacecraft in each image”

For clarity, does identifying the spacecraft means predicting the exact spacecraft\_id (spacecraft type) in addition to the bounding boxes. Or, just predicting the bounding box around a spacecraft without attention to the type of spacecraft.

---

<div class="post-metadata">

**Author:** ![isms](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/isms/32/9_2.png) [@isms](https://community.drivendata.org/u/isms)\
**Post date:** [April 29, 2024, 12:29am UTC](https://community.drivendata.org/t/clarity-on-target-to-predict-for-detection-track/10674/2 "2024-04-29T00:29:13Z")

</div>

No spacecraft ID, just the bounding box. See the [labels format](https://www.drivendata.org/competitions/260/spacecraft-detection/page/833/#labels); your submission is the same columns.