Papers › Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking

Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking

27 Mar 2022CVPR 2023 1arXiv:2203.14360archive 2025-07-28

Jinkun Cao, Jiangmiao Pang, Xinshuo Weng, Rawal Khirodkar, Kris Kitani

Kalman filter (KF) based methods for multi-object tracking (MOT) make an assumption that objects move linearly. While this assumption is acceptable for very short periods of occlusion, linear estimates of motion for prolonged time can be highly inaccurate. Moreover, when there is no measurement available to update Kalman filter parameters, the standard convention is to trust the priori state estimations for posteriori update. This leads to the accumulation of errors during a period of occlusion. The error causes significant motion direction variance in practice. In this work, we show that a basic Kalman filter can still obtain state-of-the-art tracking performance if proper care is taken to fix the noise accumulated during occlusion. Instead of relying only on the linear state estimate (i.e., estimation-centric approach), we use object observations (i.e., the measurements by object detector) to compute a virtual trajectory over the occlusion period to fix the error accumulation of filter parameters during the occlusion period. This allows more time steps to correct errors accumulated during occlusion. We name our method Observation-Centric SORT (OC-SORT). It remains Simple, Online, and Real-Time but improves robustness during occlusion and non-linear motion. Given off-the-shelf detections as input, OC-SORT runs at 700+ FPS on a single CPU. It achieves state-of-the-art on multiple datasets, including MOT17, MOT20, KITTI, head tracking, and especially DanceTrack where the object motion is highly non-linear. The code and models are available at https://github.com/noahcao/OC_SORT.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 31 code samples harvested from 3 repositories linked to this paper: 27 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 11 honoured, 1 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 29 samples from 2 repositories, 25 ran (21 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

noahcao/OC_SORT officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
BingfengYan/DS_OCSORT mentioned on GitHubpytorchMITSyntology: 28 samples, 24 ran (4 instrument-failed) · 4 unverified report
dyhBUPT/StrongSORT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StrongSORT: Make DeepSORT Great Again (arXiv:2202.13514; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
mikel-brostrom/boxmot mentioned on GitHubpytorchAGPL-3.0Syntology: not harvested report
open-mmlab/mmtracking mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
kadirnar/ocsort-pip MITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

31 samples harvested: 27 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 11 honoured, 1 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
1ran; the contract check could not run
9ran
4unverified

Licence: 13 of the 31 samples are pointer only, meaning Syntology does not serve that copy's text. For 11 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

noahcao/OC_SORT official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
convert_x_to_bbox in 6 papers trackers/ocsort_tracker/ocsort.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded · 8d048ed3edc7034e · report fixture: signature x:ndarray/1/float, score:float/0/float · returned ndarray · level recorded 2026-09-22
get_image_list in 15 papers tools/demo_track.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 6874177200d9a346 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-22
BingfengYan/DS_OCSORT community (archive-listed) 28 samples, 24 ran (4 instrument-failed) · 4 unverified
add_expensive_edges motmetrics/lap.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 75c50b21f10622fe · report fixture: signature costs:ndarray/2/float · returned ndarray · level recorded 2026-09-24
convert_bbox_to_z in 7 papers trackers/ocsort_tracker/ocsort.py ran · our draft was wrong fingerprinted MIT (permissive) · 3137f9cd241030bc · report fixture: signature bbox:ndarray/1/float · returned ndarray · level recorded 2026-09-22
convert_bbox_to_z in 7 papers trackers/focsort_tracker/ocsort.py ran fingerprinted MIT (permissive) · 2d65f2912fca8087 · report fixture: signature bbox:ndarray/1/float · returned ndarray · level recorded 2026-09-24
convert_x_to_bbox in 6 papers trackers/focsort_tracker/ocsort.py ran MIT (permissive) · 5babcd4919eec944 · report fixture: signature x:ndarray/1/float, score:NoneType/0/? · returned ndarray · level recorded 2026-09-24
convert_x_to_bbox in 6 papers trackers/ocsort_tracker/ocsort.py ran fingerprinted MIT (permissive) · 90e53239ac6a25c6 · report fixture: signature x:ndarray/1/float, score:float/0/float · returned ndarray · level recorded 2026-09-24
diou_batch trackers/ocsort_tracker/association.py ran fingerprinted MIT (permissive) · 14d88680264a197c · report fixture: signature bboxes1:ndarray/2/float, bboxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
geometric_mean in 8 papers TrackEval/plotting.py ran · violated contract fingerprinted MIT (permissive) · 06d2be4ac9d0e95b · report fixture: signature x:ndarray/1/float, y:ndarray/1/float · returned ndarray · level recorded 2026-09-26
giou_batch trackers/ocsort_tracker/association.py ran fingerprinted MIT (permissive) · 43e795751f6be2d5 · report fixture: signature bboxes1:ndarray/2/float, bboxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
init_config in 12 papers TrackEval/utils.py ran MIT (permissive) · 0ce058e665602da2 · report fixture: signature config:dict/0/?, default_config:dict/0/?, name:str/0/str · returned dict · level recorded 2026-09-24
iou_batch trackers/ocsort_tracker/association.py ran fingerprinted MIT (permissive) · d5a0d4bd4cec1340 · report fixture: signature bboxes1:ndarray/2/float, bboxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-24
jaccard in 33 papers TrackEval/plotting.py ran · honoured contract fingerprinted MIT (permissive) · 00c662d6d9709fe4 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-26
k_previous_obs trackers/focsort_tracker/ocsort.py ran · honoured contract MIT (permissive) · c700a5eb9de050a3 · report fixture: signature observations:dict/0/?, cur_age:int/0/int, k:int/0/int · returned list · level recorded 2026-09-22
load_motchallenge in 5 papers motmetrics/io.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · df7c890d21316ed3 · report fixture: signature fname:str/0/str · returned DataFrame · level recorded 2026-09-24
load_multiple_tracker_summaries in 7 papers TrackEval/plotting.py ran · our draft was wrong MIT (permissive) · e9f7b2829ca9731b · report fixture: signature tracker_folder:str/0/str, tracker_list:list/1/str, cls:str/0/str · returned dict · level recorded 2026-09-26
lsa_solve_scipy motmetrics/lap.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 73aafda163f7eb35 · report fixture: signature costs:ndarray/2/float · returned tuple · level recorded 2026-09-24
norm2squared_matrix in 5 papers motmetrics/distances.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 8aac7a69af7327b2 · report fixture: signature objs:ndarray/2/float, hyps:ndarray/2/float, max_d2:float/0/float · returned ndarray · level recorded 2026-09-24
num_frames motmetrics/metrics.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · c226fad167ab7651 · report fixture: signature df:DataFrameWrapper/0/? · returned int · level recorded 2026-09-24
obj_frequencies motmetrics/metrics.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · fd57be74b7693046 · report fixture: signature df:MockDataFrame/0/? · returned Series · level recorded 2026-09-24
pred_frequencies motmetrics/metrics.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · b443457d657ce785 · report fixture: signature df:MockDF/0/? · returned Series · level recorded 2026-09-24
predict in 126 papers trackers/ocsort_tracker/kalmanfilter.py ran MIT (permissive) · 1ada6d867045a7b1 · report fixture: signature x:ndarray/1/float, P:ndarray/2/float, F:ndarray/2/float, Q:ndarray/2/float, u:ndarray/1/float, B:ndarray/2/float, alpha:float/0/float · returned tuple · level recorded 2026-09-24
quiet_divide motmetrics/math_util.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 8c8460f479f8b77e · report fixture: signature a:ndarray/2/float, b:ndarray/2/float · returned ndarray · level recorded 2026-09-24
rect_min_max motmetrics/distances.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · d8bed56ba7a09f52 · report fixture: signature r:Tensor/2/float · returned tuple · level recorded 2026-09-24
time in 9 papers TrackEval/_timing.py ran · our draft was wrong MIT (permissive) · df1bd31f4da1bed6 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-26
update_config in 54 papers TrackEval/utils.py ran · our draft was wrong MIT (permissive) · 5ef3f617efb9ddc4 · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-24
linear_sum_assignment motmetrics/lap.py unverified MIT (permissive) here; the stored copy is pointer only · afa1b0e940655c4c · report
load_detrac_mat motmetrics/io.py unverified MIT (permissive) · 5b5527b1491dfa1e · report
load_vatictxt motmetrics/io.py unverified MIT (permissive) here; the stored copy is pointer only · 56d557c272771a4b · report
validate_metrics_list in 5 papers TrackEval/utils.py unverified MIT (permissive) · 9792bf1150d36891 · report
kadirnar/ocsort-pip community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
predict in 126 papers ocsort/kalmanfilter.py ran MIT (permissive) · 11a2969e11993458 · report fixture: signature x:ndarray/1/float, P:ndarray/2/float, F:ndarray/2/float, Q:ndarray/2/float, u:ndarray/1/float, B:ndarray/2/float, alpha:float/0/float · returned tuple · level recorded 2026-09-24

Tasks

Multi-Object TrackingMultiple Object TrackingObjectObject DetectionObject Trackingobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack OC-SORT AssA 38.0 #29 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack OC-SORT HOTA 55.1 #29 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack OC-SORT IDF1 54.2 #29 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack OC-SORT MOTA 89.4 #29 of 37 Archive leaderboard report
Multi-Object Tracking MOT17 OC-SORT HOTA 63.2 #14 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 OC-SORT IDF1 77.5 #14 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 OC-SORT MOTA 78.0 #14 of 48 Archive leaderboard report
Multi-Object Tracking MOT20 OC-SORT HOTA 62.4 #12 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 OC-SORT IDF1 76.4 #12 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 OC-SORT MOTA 75.9 #12 of 27 Archive leaderboard report
Multi-Object Tracking SportsMOT OC-SORT AssA 61.5 #12 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT OC-SORT DetA 88.5 #12 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT OC-SORT HOTA 73.7 #12 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT OC-SORT IDF1 74.0 #12 of 22 Archive leaderboard report
Multi-Object Tracking SportsMOT OC-SORT MOTA 96.5 #12 of 22 Archive leaderboard report
Multiple Object Tracking CroHD OC-SORT HOTA 44.1 #2 of 5 Archive leaderboard report
Multiple Object Tracking CroHD OC-SORT IDF1 62.9 #2 of 5 Archive leaderboard report
Multiple Object Tracking CroHD OC-SORT MOTA 67.9 #2 of 5 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) OC-SORT HOTA 76.5 #12 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) OC-SORT IDSW 250 #12 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) OC-SORT MOTA 90.3 #12 of 34 Archive leaderboard report
Multiple Object Tracking SportsMOT OC-SORT AssA 61.5 #10 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT OC-SORT DetA 88.5 #10 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT OC-SORT HOTA 73.7 #10 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT OC-SORT IDF1 74.0 #10 of 19 Archive leaderboard report
Multiple Object Tracking SportsMOT OC-SORT MOTA 96.5 #10 of 19 Archive leaderboard report
Object Tracking QuadTrack OC-SORT HOTA 20.83 #3 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections