Object Tracking
584 papers with code • 7 benchmarks • 61 datasets
Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.
( Image credit: Towards-Realtime-MOT )
Benchmarks
These leaderboards are used to track progress in Object Tracking
Libraries
Use these libraries to find Object Tracking models and implementationsDatasets
Subtasks
Latest papers
BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking
To utilize low-detection score bounding boxes in one-stage association, we propose to boost the confidence scores of two groups of detections: the detections we assume to correspond to the existing tracked object, and the detections we assume to correspond to a previously undetected object.
PillarTrack: Redesigning Pillar-based Transformer Network for Single Object Tracking on Point Clouds
LiDAR-based 3D single object tracking (3D SOT) is a critical issue in robotics and autonomous driving.
SFSORT: Scene Features-based Simple Online Real-Time Tracker
This paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets.
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest.
DepthMOT: Depth Cues Lead to a Strong Multi-Object Tracker
Inspired by this, even though the bounding boxes of objects are close on the camera plane, we can differentiate them in the depth dimension, thereby establishing a 3D perception of the objects.
Self-Supervised Multi-Object Tracking with Path Consistency
In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision.
Ego-Motion Aware Target Prediction Module for Robust Multi-Object Tracking
Conventional prediction methods in DBT utilize Kalman Filter(KF) to extrapolate the target location in the upcoming frames by supposing a constant velocity motion model.
Representation Alignment Contrastive Regularization for Multi-Object Tracking
Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage.
OmniVid: A Generative Framework for Universal Video Understanding
The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically detect objects or actions in a video and analyze their temporal evolution.
Multiple Object Tracking as ID Prediction
In Multiple Object Tracking (MOT), tracking-by-detection methods have stood the test for a long time, which split the process into two parts according to the definition: object detection and association.