HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
- Jonathon Luiten, Aljosa Osep, B. Leibe
- Computer ScienceInternational Journal of Computer Vision
- 16 September 2020
This work presents a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers.
MOTS: Multi-Object Tracking and Segmentation
- P. Voigtlaender, Michael Krause, B. Leibe
- Computer ScienceComputer Vision and Pattern Recognition
- 10 February 2019
This paper creates dense pixel-level annotations for two existing tracking datasets using a semi-automatic annotation procedure, and proposes a new baseline method which jointly addresses detection, tracking, and segmentation with a single convolutional network.
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
- A. Athar, S. Mahadevan, Aljosa Osep, L. Leal-Taixé, B. Leibe
- Computer ScienceEuropean Conference on Computer Vision
- 18 March 2020
A novel approach that segments and tracks instances across space and time in a single stage and is trained end-to-end to learn spatio-temporal embeddings as well as parameters required to cluster pixels belonging to a specific objectinstance over an entire video clip is proposed.
How to Train Your Deep Multi-Object Tracker
- Yihong Xu, Aljosa Osep, Yutong Ban, R. Horaud, L. Leal-Taixé, Xavier Alameda-Pineda
- Computer ScienceComputer Vision and Pattern Recognition
- 15 June 2019
A differentiable proxy of MOTA and MOTP is proposed, which is combined in a loss function suitable for end-to-end training of deep multi-object trackers and establishes a new state of the art on the MOTChallenge benchmark.
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
- Patrick Dendorfer, Aljosa Osep, L. Leal-Taixé
- Computer ScienceInternational Journal of Computer Vision
- 15 October 2020
This paper collects the first three releases of MOTChallenge and provides a categorization of state-of-the-art trackers and a broad error analysis, to help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light into potential future research directions.
Combined image- and world-space tracking in traffic scenes
- Aljosa Osep, Wolfgang Mehner, Markus Mathias, B. Leibe
- Computer ScienceIEEE International Conference on Robotics and…
- 1 May 2017
This work presents its tracking pipeline as a 3D extension of image-based tracking, which uses world-space 3D information at every stage of processing by combining a novel coupled 2D-3D Kalman filter with a conceptually clean and extendable hypothesize-and-select framework.
EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
- Aleksandr Kim, Aljosa Osep, L. Leal-Taixé
- Computer ScienceIEEE International Conference on Robotics and…
- 29 April 2021
This paper proposes EagerMOT, a simple tracking formulation that eagerly integrates all available object observations from both sensor modalities to obtain a well-informed interpretation of the scene dynamics and achieves state-of-the-art results across several MOT tasks on the KITTI and NuScenes datasets.
Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation
- Patrick Dendorfer, Aljosa Osep, L. Leal-Taixé
- Computer ScienceAsian Conference on Computer Vision
- 2 October 2020
Goal-GAN, an interpretable and end-to-end trainable model for human trajectory prediction, is presented, which establishes a new state-of-the-art on several benchmarks while being able to generate a realistic and diverse set of trajectories that conform to physical constraints.
STEP: Segmenting and Tracking Every Pixel
- Mark Weber, Jun Xie, Liang-Chieh Chen
- Computer ScienceNeurIPS Datasets and Benchmarks
- 23 February 2021
This work presents a new benchmark: Segmenting and Tracking Every Pixel (STEP), encompassing two datasets, KITTI-STEP, and MOTChallenge-STEP together with a new evaluation metric Segmentation and Tracking Quality (STQ), that fairly balances semantic and tracking aspects of this task and is suitable for evaluating sequences of arbitrary length.
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
- Matteo Fabbri, Guillem BrasĂł, R. Cucchiara
- Computer ScienceIEEE International Conference on Computer Vision
- 21 August 2021
MOTSynth, a large, highly diverse synthetic dataset for object detection and tracking using a rendering game engine, is generated and shows that MOTSynth can be used as a replacement for real data on tasks such as pedestrian detection, re-identification, segmentation, and tracking.
...
...