mmtracking Roadmap of MMTracking

We keep this issue open to collect feature requests from users and hear your voice.

You can either:

Suggest a new feature by leaving a comment.
Vote for a feature request with 👍 or be against with 👎. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
Tell us that you would like to help implement one of the features in the list or review the PRs. (This is the greatest things to hear about!)

Recently we do not have enough bandwidth/developers to support new methods. If you are interested in joining us as an intern or a full-time researcher/engineer, feel free to let us know. You can directly drop an email to [email protected], [email protected], or [email protected].

Besides the developments from OpenMMLab, we also welcome all contributions from the community. You can make a PR of your work to this repository following CONTRIBUTING.md.

Jan 05 '21 06:01 OceanPang

Thank you for the amazing work! Do you have any plan on releasing more baselines on Single Object Tracking (Siam-like, ATOM, DiMP, OCEAN, KYS, LWL) as well as more dataset (OTB, VOT, TrackingNet, UAV123, NFS)?

Jan 23 '21 11:01 SilvioGiancola

Hello! I think CenterTrack would be a great incorporation to the multiple object tracking.

Jan 23 '21 15:01 agirbau

Hi @SilvioGiancola @agirbau, thanks for your interest!

We are discussing a development plan in which we tend to support 2-3 new methods for each task and support the other popular datasets.

For the methods, the Siam-Like and some recent SOTA methods (not decided which one yet) are the first priority for SOT @SilvioGiancola. As @agirbau suggested, We do have a plan to support CenterTrack but need to wait for the CenterNet in mmdetection.

For the datasets, we will support the datasets @SilvioGiancola mentioned, and also support some other large scale MOT benchmarks.

However, considering the limited bandwidth, we cannot clearly state the release schedule of these updates. If you are also interested in supporting these features, we will really appreciate your pull requests. : )

Jan 24 '21 07:01 OceanPang

Just wanted to add, it would also be cool, If a multi object tracking and segmentation baseline could be added like (TrackRCNN) https://github.com/VisualComputingInstitute/TrackR-CNN for example. As many benchmarks and workshops are introducing datasets and problems specifically in this domain such as MOTS CHALLENGE, KITTI MOTS, BDD100K MOTS etc.

And again, really appreciate this amazing work, for putting everything in such a modular perspective with efficiency.

Mar 25 '21 06:03 imr555

Thanks for your hard work on maintaining this wonderful repo. It would be nice to include recently released large-vocabulary tracking data TAO as well.

Apr 07 '21 15:04 shwoo93

When will release the CenterTrack in your plan?

Jul 06 '21 06:07 RaymondByc

What about HOTA metrics?

Sep 09 '21 09:09 dzambrano

Hi, I'd like to suggest StrongSORT MOT algorithm #541

May 04 '22 15:05 austinmw

I am considering to make support to some features in the short future. Let me know if some are already in process or your vote for their priority.

~~Support of DanceTrack[0] dataset.~~( #543)
~~Support of OC-SORT[6] for multi-object tracking.~~ (#545 )
~~multi-class multi-object tracking, which is already supported in Youtube-VIS but still absent on MOT task.~~ (#548)
transformer-based detector, e.g. DETR[1], and tracker, e.g. TransTrack[2], Trackformer[3].
more MOT datasets, such as KITTI[4].
make BYTE[5] and OC-SORT optional flags in other KalmanFilter-based tracking methods.

[0] "DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion" [1] "End-to-end object detection with transformers" [2] "Transtrack: Multiple object tracking with transformer" [3] "Trackformer: Multi-object tracking with transformers" [4] "Vision meets robotics: The kitti dataset" [5] "ByteTrack: Multi-Object Tracking by Associating Every Detection Box" [6] "Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking"

May 06 '22 03:05 noahcao

Pose track is also a good to-do as a new task, baseline methods include PoseFlow[1]. The corresponding datasets are PoseTrack[2] and HiEve[3].

[1] "Pose Flow: Efficient online pose tracking" [2] "Posetrack: A benchmark for human pose estimation and tracking" [3] "Human in events: A large-scale benchmark for human-centric video analysis in complex events"

An existing codebase Alphapose may be a good reference for the practice, which focuses on pose estimation while leaving tracking modules not actively maintained.

May 06 '22 22:05 noahcao

VID feature request like mmdetection toolmmdetection/tools/analysis_tools(eg. visualize dataset's ground truth, output confusion matrix).

May 11 '22 02:05 Cavaradossi

Agree with @Cavaradossi more analysis tools like mmdetection would be great help. Currently experiencing problems in creating one of my own for plotting the confusion matrix.

Jul 17 '22 14:07 godwinrayanc

Hello! We are the authors of this paper. We implemented our method fully based on MMTracking 0.x and experimented some more datasets like UVO v0.5 and OVIS. I see previous reply mentioned transformer-base detection/tracking which is what we have. Would be interested in creating a PR if you think it is a good idea to include our model. Thanks!

Dec 03 '22 21:12 zitongzhan

Hello! We are the authors of this paper. We implemented our method fully based on MMTracking 0.x and experimented some more datasets like UVO v0.5 and OVIS. I see previous reply mentioned transformer-base detection/tracking which is what we have. Would be interested in creating a PR if you think it is a good idea to include our model. Thanks!

Hi~, We are glad you're willing to create a pr to implement your model in MMTracking.