• Corpus ID: 235417008

Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion

@inproceedings{Song2020OnlineMT,
  title={Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion},
  author={Young-min Song and Young-Chul Yoon and Kwangjin Yoon and Moongu Jeon and Seong-Whan Lee and Witold Pedrycz},
  year={2020}
}
In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for… 
1 Citations

PolyTrack: Tracking with Bounding Polygons

TLDR
Results show that tracking polygons can be a good alternative to bounding box and mask tracking.

References

SHOWING 1-10 OF 56 REFERENCES

Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

TLDR
This paper proposes a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation and builds a more challenging MOTS dataset named APOLLO MOTS with higher instance density.

High-Speed Tracking with Kernelized Correlation Filters

TLDR
A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.

MOT16: A Benchmark for Multi-Object Tracking

TLDR
A new release of the MOTChallenge benchmark, which focuses on multiple people tracking, and offers a significant increase in the number of labeled boxes, but also provides multiple object classes beside pedestrians and the level of visibility for every single object of interest.

Track to Reconstruct and Reconstruct to Track

TLDR
This work exploits the 3D motion extracted from dynamic object reconstructions to track objects through long periods of complete occlusion and to recover missing detections, and outperforms all previous approaches for both bounding box and segmentation tracking.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation

TLDR
A self-supervised refining MOTS (i.e., ReMOTS) framework to improve the performance of Multiple Object Tracking and Segmentation by refinement utilizing adopted appearance features and thresholds that are automatically obtained from statistical information.

Deep Learning for Person Re-Identification: A Survey and Outlook

TLDR
A powerful AGW baseline is designed, achieving state-of-the-art or at least comparable performance on twelve datasets for four different Re-ID tasks, and a new evaluation metric (mINP) is introduced, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re- ID system for real applications.

Learning Multi-Object Tracking and Segmentation From Automatic Annotations

TLDR
The proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches, and leverages state-of-the-art instance segmentation results in combination with optical flow predictions.

A Predictor of Moving Objects for First-Person Vision

TLDR
This paper presents an accurate model to forecast the position of moving objects by disentangling global and object motion without the need of camera calibration or planarity assumptions and shows that it can forecast up to 60% more accurately than state-of-the-art predictors while being resilient to noisy observations.

Online Multi-Object Tracking With GMPHD Filter and Occlusion Group Management

TLDR
The proposed tracker efficiently handles occlusion situations and achieves competitive performance compared to the state-of-the-art methods, and shows the best multi-object tracking accuracy among the online and real-time executable methods.
...