Object Tracking

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 )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1251–1275 of 1966 papers

Title	Date	Tasks	Status	Hype
Rotation Equivariant Siamese Networks for Tracking	Dec 24, 2020	2D Pose EstimationBenchmarking	CodeCode Available	1
Coarse-to-Fine Object Tracking Using Deep Features and Correlation Filters	Dec 23, 2020	image-classificationImage Classification	CodeCode Available	0
Limitation of Acyclic Oriented Graphs Matching as Cell Tracking Accuracy Measure when Evaluating Mitosis	Dec 22, 2020	Cell TrackingMulti-Object Tracking	—Unverified	0
Accurate Object Association and Pose Updating for Semantic SLAM	Dec 21, 2020	Multiple Object TrackingObject	—Unverified	0
Computer Vision based Animal Collision Avoidance Framework for Autonomous Vehicles	Dec 20, 2020	Autonomous VehiclesCollision Avoidance	—Unverified	0
Recent Advances of Generic Object Detection with Deep Learning: A Review	Dec 19, 2020	Action RecognitionData Augmentation	—Unverified	0
Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations	Dec 18, 2020	3D Object Detection3D Object Tracking	CodeCode Available	2
End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box	Dec 17, 2020	Autonomous DrivingDeep Learning	—Unverified	0
Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences	Dec 15, 2020	3D Multi-Object TrackingMulti-Object Tracking	—Unverified	0
FlowMOT: 3D Multi-Object Tracking by Scene Flow Association	Dec 14, 2020	3D Multi-Object Trackingmotion prediction	—Unverified	0
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation	Dec 12, 2020	Object TrackingSemi-Supervised Video Object Segmentation	CodeCode Available	1
AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking	Dec 10, 2020	3D Multi-Object TrackingMulti-Object Tracking	—Unverified	0
Contrastive Transformation for Self-supervised Correspondence Learning	Dec 9, 2020	Object TrackingSelf-Supervised Learning	CodeCode Available	1
Multi-modal Visual Tracking: Review and Experimental Comparison	Dec 8, 2020	Object TrackingRgb-T Tracking	CodeCode Available	1
Learning Tactile Models for Factor Graph-based Estimation	Dec 7, 2020	ObjectObject Tracking	—Unverified	0
Isometric Multi-Shape Matching	Dec 4, 2020	3D ReconstructionObject Tracking	—Unverified	0
Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking	Dec 3, 2020	Multiple Object TrackingObject Tracking	—Unverified	0
DeFMO: Deblurring and Shape Recovery of Fast Moving Objects	Dec 1, 2020	DeblurringObject Tracking	CodeCode Available	1
Generalised Bayesian Filtering via Sequential Monte Carlo	Dec 1, 2020	Bayesian InferenceObject Tracking	—Unverified	0
A Hypergradient Approach to Robust Regression without Correspondence	Nov 30, 2020	Multi-Object TrackingObject Tracking	—Unverified	0
A CRF-based Framework for Tracklet Inactivation in Online Multi-Object Tracking	Nov 30, 2020	Multi-Object TrackingObject Tracking	—Unverified	0
SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking	Nov 27, 2020	ClusteringObject	CodeCode Available	0
A Deep Learning Bidirectional Temporal Tracking Algorithm for Automated Blood Cell Counting from Non-invasive Capillaroscopy Videos	Nov 26, 2020	Cell TrackingMultiple Object Tracking	CodeCode Available	0
Relation3DMOT: Exploiting Deep Affinity for 3D Multi-Object Tracking from View Aggregation	Nov 25, 2020	3D Multi-Object TrackingAutonomous Navigation	—Unverified	0
An Occlusion‐aware Edge‐Based Method for Monocular 3D Object Tracking using Edge Confidence.	Nov 24, 2020	3D Object TrackingMulti-Object Tracking	CodeCode Available	0

Show:10 25 50

← PrevPage 51 of 79Next →

All datasets COESOT FE108 QuadTrack SeaDronesSee BIRDSAI - ICVGIP 2020 KITTI MMPTRACK Perception Test VisEvent

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	HR-CEUTrack-Large	Success Rate	65	—	Unverified
2	HR-CEUTrack-Base	Success Rate	63.2	—	Unverified
3	CEUTrack-Large	Success Rate	62.8	—	Unverified
4	CEUTrack-Base	Success Rate	62	—	Unverified
5	SiamR-CNN	Success Rate	60.9	—	Unverified
6	TransT	Success Rate	60.5	—	Unverified
7	SuperDiMP	Success Rate	60.2	—	Unverified
8	TrDiMP	Success Rate	60.1	—	Unverified
9	KeepTrack	Success Rate	59.6	—	Unverified
10	AiATrack	Success Rate	59	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HR-MonTrack-Base	Success Rate	68.5	—	Unverified
2	HR-MonTrack-Tiny	Success Rate	66.3	—	Unverified
3	Multi-modal	Success Rate	63.4	—	Unverified
4	PrDiMP	Success Rate	59	—	Unverified
5	DiMP	Success Rate	57.1	—	Unverified
6	MonTrack	Success Rate	54.9	—	Unverified
7	ATOM	Success Rate	46.5	—	Unverified
8	KYS	Success Rate	26.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	OmniTrack	HOTA	23.45	—	Unverified
2	DeepSORT	HOTA	21.16	—	Unverified
3	OC-SORT	HOTA	20.83	—	Unverified
4	ByteTrack	HOTA	20.66	—	Unverified
5	TrackFormer	HOTA	19.62	—	Unverified
6	HybridSORT	HOTA	16.64	—	Unverified
7	DiffMOT	HOTA	16.4	—	Unverified
8	Bot-SORT	HOTA	15.77	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DiMP50	Success Rate	67.33	—	Unverified
2	PrDiMP50	Success Rate	67	—	Unverified
3	PrDiMP18	Success Rate	65.9	—	Unverified
4	DiMP18	Success Rate	64.6	—	Unverified
5	Atom	Success Rate	63.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	final	Humans	0.14	—	Unverified
2	night_fury	Humans	0.05	—	Unverified
3	Yolo based method	Humans	0.02	—	Unverified
4	final	Humans	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	M2-Track	mean precision	83.4	—	Unverified
2	BAT	mean precision	75.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UMMT	3DMOTA	95	—	Unverified
2	MMPTRACK	3DMOTA	94.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Siam-FC	Average IOU	0.66	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RT-MDNet	Precision Plot	0.63	—	Unverified