17 datasets found

The Global Data Association for Multi-Object Tracking using Network Flows dataset is used to evaluate the performance of multi-object tracking algorithms.

The proposed Tracking-by-Animation (TBA) framework achieves unsupervised end-to-end learning of MOT tasks.

Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based...

The Cars dataset is a multi-object multi-camera network application.

The dataset used for the MOT20 challenge, which consists of 8 different sequences depicting very crowded challenging scenes.

MOT16 is a benchmark for multi-object tracking, consisting of 16 video sequences with 1000 frames each.

The MOTS20 dataset is used for multi-object tracking and segmentation.

The MOT16, MOT17, and MOT20 datasets are used for evaluating the proposed One More Check (OMC) tracker.

The CLEAR MOT metrics are used to evaluate the performance of multi-object tracking algorithms.

Object permanence is the concept that objects in a physical world continue to exist despite the observers inability to sense them. This can result in temporally unstable...

A synthetic dataset for multi-object tracking, providing ground truth annotations for invisible objects.

The dataset used for tracking multiple people across multiple cameras is a large-scale multi-camera tracking dataset, DukeMTMC.

The KITTI Object Detection Benchmark consists of 7,481 training images and 7,518 testing images, with 3D LiDAR point clouds and camera images.

The 2DMOT15 and 2DMOT16 datasets are used to evaluate the performance of the proposed online MOT algorithm.

MOT-Challenge datasets are a benchmark for multi-object tracking.

Virtual worlds as proxy for multi-object tracking analysis

Many Multi-Object Tracking (MOT) approaches exploit motion information to associate all the detected objects across frames. However, many methods that rely on filtering-based...