CAT-Free: Multi-View Pedestrian Localization without Calibration, Annotations, or Target-Scene Training via Adaptive Geometric Filtering

Taigo Sakai; Hiroki Kouno; Naoki Kato; Kazuhiro Hotta

cs.CVSep 28, 2026

CAT-Free: Multi-View Pedestrian Localization without Calibration, Annotations, or Target-Scene Training via Adaptive Geometric Filtering

Authors: Taigo Sakai, Hiroki Kouno, Naoki Kato, Kazuhiro Hotta

Organizations: Meijo University Department of Science Technology · Chubu Electric Power Co., Inc.

Abstract

Multi-camera pedestrian localization is useful for wide-area monitoring in public and commercial spaces. However, deploying these systems often requires considerable setup for each new environment. Existing methods typically require camera calibration, position annotations, or target-scene training. CAT-Free removes all three requirements. It uses synchronized RGB video as its only scene-specific input. Camera configuration is estimated directly from the video. Pedestrian locations are then estimated by combining observations from multiple cameras. Automatic camera estimation is not always accurate. This can produce unreliable pedestrian locations. CAT-Free therefore introduces two adaptive geometric filters. They remove unreliable position estimates. Their thresholds are estimated from each input sequence. CAT-Free achieves 82.5, 84.5, and 65.7 MODA on WildTrack, MultiviewX, and GMVD. It uses no supplied calibration, position annotations, or target-scene training. Published methods using such scene-specific information report 88.2--95.0 MODA on WildTrack and 83.9--96.5 on MultiviewX under their respective protocols. CAT-Free also transfers without retuning. It reaches 74.9 MODA on four additional sequences and 78.6 on an unseen 8-camera installation. Finally, localization uncertainty predicts MODA with $r=-0.98$ . This provides a label-free estimate of localization reliability.

Figures & tables

Figure 1 : RGB video in, tracked ground positions out, with no supplied calibration, no position annotations from the target scene, and no target-scene training. (b) shows the recovered ground, cameras, and every trajectory in the WildTrack test sequence. (c) relates published WildTrack MODA to each method’s requirements. Table 9 in the supplement lists the protocol differences.

Figure 2 : CAT-Free pipeline. ❶ Pretrained models with fixed weights extract information from each camera view: VGGT estimates the camera configuration and ground surface, YOLO11x with pose provides pedestrian detections and 3D rays with reliability $w_{i}$ , and OSNet provides appearance features. ❷ Detections of the same pedestrian are matched across cameras, and their rays are combined to estimate candidate 3D pedestrian positions. ❸ The proposed filters remove positions that are imprecise ( $\sigma>\tau_{\sigma}$ ) or inconsistent with the ground ( $g>\tau_{g}$ ), followed by non-maximum suppression (NMS). ❹ The remaining positions are linked over time to form pedestrian trajectories on the ground. Both thresholds are estimated from the input sequence, without supplied calibration, position annotations, or target-scene training. The lower row shows the four stages on WildTrack frame 1900. No ground truth is used.

	Localization				Tracking
Dataset	MODA	MODP	Precision	Recall	MOTA	MOTP $\downarrow$	IDF1	HOTA
WildTrack	82.46	70.94	92.52	89.71	81.41	0.156	71.36	64.72
MultiviewX	84.54	77.04	96.74	87.48	79.05	0.138	64.96	59.65
GMVD (s5/c1/seq1)	65.69	62.12	96.56	68.11	64.00	0.212	55.23	46.44
WildTrack, 360 unused frames	58.27	65.49	88.96	66.52	59.46	0.215	52.31	46.52
GMVD c1, seqs. 2–5, mean	74.90	61.22	94.69	79.37	74.36	0.216	58.03	50.19

Table 1 : Main results. The upper block contains the three development sequences. The lower block reports post-development transfer. The bold column is the primary localization metric. MODA and MODP use a 0.5 m matching threshold; MOTA, MOTP, and IDF1 use 1 m. HOTA is computed with TrackEval.

Method	Supplied calibration	Target annotations	Target training	WildTrack MODA	MultiviewX MODA
UMPD [ 11 ]	Yes	No	Yes	76.6	67.5
DCHM [ 13 ]	Yes	No	Yes	84.2	78.4
CAT-Free (ours)	No	No	No	82.5	84.5
MVDet [ 7 ]	Yes	Yes	Yes	88.2	83.9
MVDeTr [ 8 ]	Yes	Yes	Yes	91.5	93.7
EarlyBird [ 16 ]	Yes	Yes	Yes	91.2	94.2

Table 2 : Published MODA on WildTrack and MultiviewX together with the per-installation resources used by each reported result. “Supplied calibration” indicates that dataset camera calibration is given to the method, “Target annotations” indicates that annotations from the target environment are used for learning, and “Target training” indicates that model fitting or fine-tuning is performed on images from that environment. Published accuracy values follow the respective papers and may use different training and evaluation protocols; the table is therefore intended to contextualize accuracy against deployment requirements rather than provide a strict controlled ranking.

Variant	WT	MVX	GMVD	Mean	$\Delta$ Mean
Q (camera support)	80.99	82.06	59.93	74.33	–
Ground only	81.51	81.73	59.71	74.32	-0.01
Uncertainty, add	76.89	82.93	64.58	74.80	+0.47
Uncertainty, replace	78.47	83.07	64.68	75.41	+1.08
Ground $\rightarrow$ uncertainty, replace	80.46	83.94	63.14	75.85	+1.52
Ground $\rightarrow$ uncertainty, add	79.83	84.40	63.80	76.01	+1.68

Table 3 : Adaptive-filter ablation on the development sequences (MODA).

\Delta

Mean is relative to Q. The best ordering applies localization uncertainty before ground-plane consistency.

Variant	WT	MVX	GMVD
(A) single-camera ground projection	32.88	15.66	42.84
(B) best two-ray estimate	79.10	75.23	60.59
CAT-Free	82.46	84.54	65.69
(C) CAT-Free with ground-truth calibration	79.94	81.26	65.17

Table 4 : Controlled localization baselines on the development sequences (MODA). WT denotes WildTrack and MVX denotes MultiviewX. All rows use the same pedestrian detections, estimated ground, and trajectory stage.

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Stage	Fixed setting	Estimated per sequence
Detection	confidence $\geq 0.30$	–
Rays	$\sigma_{\theta}=0.0206$ rad	pose/non-pose ratio $(s_{\text{pose}}/s_{\text{other}})^{2}$ ; median box height $\tilde{h}$
Association	residual $\leq 2\sigma_{\theta}$ ; appearance threshold 0.6; uniqueness ratio 0.3	–
Triangulation	Huber $\delta=0.01E$ ; outlier $>3\delta$	–
Scoring	–	signal weights and threshold (Otsu); reconstruction confidence gain
Selection	residual $\leq 2\sigma_{\theta}$ ; support radius $\sigma_{\theta}$ ; NMS $r=0.018E$ ;	$\tau_{\sigma}$ , $\tau_{g}$ (log-Otsu)

Appendix

Table 5 : Downstream settings after detection and camera estimation. Fixed values are shared across datasets.

E

is the reconstructed scene extent, and

\sigma_{\theta}

is the angular noise standard deviation.

Figure 3 : Ray reliability $w_{i}$ on WildTrack frame 1900. Each box is a detection and each dot is the bottom-center point that defines its back-projection ray. Colour is $w_{i}$ from Eq. ( 3 ): distant people project to short boxes, so their foot point carries a larger angular error and receives a smaller weight. Triangulation and view support use these weights; no ground truth is involved.

Figure 4 : The two geometric filters. (a) Localization uncertainty

\sigma

increases with viewing distance and poor intersection angles. Ellipses show the positional covariance

\mathbf{\Lambda}^{-1}

of Eq. ( 6 ). (b) The point-to-plane distance

g

exposes an incorrect correspondence that ground-constrained triangulation would hide.

				Recovered rig (RGB only)			GT calibration (diagnostic)
Frames	GT	People/frame	Cameras/person	MODA	Recall	Precision	MODA	Recall	Precision
0–199	989	24.7	3.68	33.37	46.01	78.45	40.34	49.14	84.82
200–399	703	17.6	3.74	48.22	64.72	79.68	52.49	65.29	83.61
400–599	898	22.4	3.75	50.33	62.69	83.53	54.68	63.47	87.83
600–799	931	23.3	4.16	62.84	67.56	93.46	63.05	67.78	93.48
800–999	1,264	31.6	4.35	60.05	66.06	91.66	63.05	66.06	95.65

Appendix

Table 6 : Evaluation on 360 WildTrack frames not used during development, grouped into 200-frame intervals. Camera parameters and dense reconstruction come from frames 1800–1995. Thresholds are estimated again on the 360 evaluation frames. The right block replaces the estimated camera parameters with ground-truth calibration as a diagnostic.

Seq.	GT	MODA	MODP	Prec.	Rec.	MOTA	MOTP $\downarrow$	IDF1	HOTA	Out	MODA out-FP
2	2,802	74.09	66.81	96.97	76.48	73.98	0.184	66.80	57.41	265	64.63
3	2,803	79.02	58.25	94.86	83.55	79.27	0.221	61.04	50.22	216	71.32
4	4,160	71.32	62.32	93.01	77.12	71.01	0.230	51.52	46.26	80	69.40
5	2,692	75.15	57.49	93.92	80.35	73.18	0.227	52.77	46.86	80	72.18
Mean	–	$74.90\!\pm\!3.19$	$61.22\!\pm\!4.29$	$94.69\!\pm\!1.70$	$79.37\!\pm\!3.26$	$74.36\!\pm\!3.51$	$0.216\!\pm\!0.021$	$58.03\!\pm\!7.21$	$50.19\!\pm\!5.20$	–	$69.38\!\pm\!3.37$

Appendix

Table 7 : Post-development evaluation on four additional GMVD scene-5/configuration-1 sequences. The method and sequence-1 camera parameters are fixed. MODA out-FP counts predictions outside the evaluation grid as false positives.

Seq.	GT	MODA	MODP	Prec.	Rec.	MOTA	MOTP $\downarrow$	IDF1	HOTA	Out	MODA out-FP
1	4,086	70.31	69.70	95.16	74.08	69.43	0.172	65.61	56.74	191	65.64
2	2,802	73.55	65.03	96.40	76.41	73.09	0.194	72.71	61.03	487	56.17
3	2,803	86.41	69.43	95.91	90.26	84.34	0.167	71.24	61.55	366	73.35
4	4,161	80.25	67.90	94.94	84.76	77.63	0.185	61.96	56.28	159	76.42
5	2,692	82.24	66.58	93.28	88.63	79.05	0.182	58.82	55.13	238	73.40
Mean	–	$78.55\!\pm\!6.54$	$67.73\!\pm\!1.96$	$95.14\!\pm\!1.19$	$82.83\!\pm\!7.25$	$76.71\!\pm\!5.71$	$0.180\!\pm\!0.011$	$66.07\!\pm\!5.92$	$58.15\!\pm\!2.95$	–	$69.00\!\pm\!8.25$

Appendix

Table 8 : Post-development evaluation on an unseen 8-camera installation, GMVD scene 5, configuration 2. Camera parameters are estimated from RGB with the fixed 25-iteration procedure. Iteration 20 is selected by triangulation residual. MODA out-FP counts predictions outside the evaluation grid as false positives.

Figure 5 : Qualitative results on the middle evaluation frame of each development dataset. Top: camera 1 and person detections. Bottom: bird’s-eye view after evaluation-only similarity alignment. Predictions and people are matched at the 0.5 m MODA threshold.

Method	Given calibration	Target labels	Target training	Eval. GT align	WildTrack	MultiviewX
MVDet [ 7 ]	✓	✓	✓	–	88.2	83.9
MVDeTr [ 8 ]	✓	✓	✓	–	91.5	93.7
EarlyBird [ 16 ]	✓	✓	✓	–	91.2	94.2
TrackTacular [ 17 ]	✓	✓	✓	–	93.2	96.5
CaMuViD [ 4 ]	–	✓	✓	–	95.0	96.5
UMPD [ 11 ]	✓	–	✓	–	76.6	67.5

Appendix

Table 9 : Resource and protocol context using reported MODA. This is not a controlled ranking because each method follows its authors’ protocol. CAT-Free uses development-set method selection, full-sequence processing, and evaluation-time similarity alignment.

Figure 6 : Localization uncertainty $\sigma$ and point-to-plane distance $g$ after angular consistency filtering, normalized by the NMS radius. Log-Otsu estimates $\tau_{\sigma}$ from all hypotheses and $\tau_{g}$ from hypotheses with $\sigma\leq\tau_{\sigma}$ . The shaded region is accepted. Ground truth is used only to color points.

Cameras	Co-visibility	MODA	Recall	Precision
2	1.80	$-8.51$	5.9	29.0
3	2.76	47.58	49.4	96.5
4	2.95	56.20	62.5	90.8
5	3.68	66.81	75.0	90.2
6	4.66	81.41	87.9	93.1
7	5.28	82.46	89.7	92.5

Appendix

Table 10 : Camera-removal experiment on the WildTrack development frames. Frames, detections, camera parameters, ground plane, and fixed constants do not change. The first

k

of seven cameras provide the rays. Co-visibility is the mean number of those cameras that observe each annotated person.

Setting	Median $\sigma$ (cm)	MODA
2 cameras, development frames	76.4	$-8.51$
3 cameras, development frames	31.9	47.58
4 cameras, development frames	31.2	56.20
5 cameras, development frames	20.3	66.81
6 cameras, development frames	18.2	81.41
7 cameras, development frames	15.2	82.46

Appendix

Table 11 : One curve, two ways of varying difficulty. Median

\sigma

from Eq. ( 6 ) at the annotated positions, against measured MODA, pooling the camera-removal sweep with two time windows evaluated at the full seven cameras. Over these eight settings

\log\sigma

predicts MODA with Pearson

r=-0.98

(Spearman

-0.93

p<0.001

Dataset	Cameras	All-camera MODA	LOO mean	LOO min	LOO SD	Held-out center error
WildTrack	7	82.46	81.87	79.62	1.13	0.30 m
MultiviewX	6	84.54	84.56	84.27	0.16	0.19 m
GMVD (s5/c1/seq1)	6	65.69	64.64	62.48	1.14	0.40 m

Appendix

Table 12 : Leave-one-camera-out evaluation alignment. The similarity transform is refitted after withholding one camera center, and all predictions are rescored. The last column measures the distance between the withheld camera’s estimated and annotated centers after alignment.

	Change	WildTrack	MultiviewX	GMVD	Mean
I	earlier baseline (pose-confirmed detections only, unweighted rays)	78.68	78.92	56.36	71.32
K	all detections $\geq 0.30$ + ray reliability $w_{i}$	80.57	81.39	59.64	73.87
Q	remove exclusive assignment after support recount	80.99	82.06	59.93	74.33
BF	weighted view support $\rightarrow$ uncertainty filter	78.47	83.07	64.68	75.41
BK	+ ground-plane filter after the uncertainty filter	81.62	84.34	64.51	76.82
BS	+ inlier refit of the triangulated position	82.25	84.54	64.63	77.14

Appendix

Table 13 : Development-set MODA after cumulative changes. Method I is the initial controlled baseline. Variants were selected on these sequences.

Figure 7 : (a) Development MODA after each adopted change. (b) Outcome of every annotated person under the final pipeline. Outcomes are a true positive, a prediction 0.5–1 m away, removal by tracking, rejection by selection, or no triangulated hypothesis. FP is the number of false positives.

Variant	WildTrack	MultiviewX	GMVD	Mean
no trajectory stage (per-frame positions)	79.94	81.12	62.01	74.36
BS (all rules)	82.25	84.54	64.63	77.14
$-$ short static-track removal (BT)	82.46	84.54	65.69	77.56
$-$ gap interpolation	82.25	84.54	64.63	77.14
$-$ track extension	80.46	78.92	59.03	72.80
$-$ appearance in linking and extension	81.72	84.20	64.46	76.79

Appendix

Table 14 : Trajectory ablation on the peaks of BS (MODA). Each row removes one rule from BS.

Threshold rule	WildTrack	MultiviewX	GMVD	Mean
fixed quantile p50	81.83	55.69	41.56	59.69
fixed quantile p60	79.52	74.50	57.19	70.40
fixed quantile p70	76.26	84.27	67.38	75.97
log-Otsu (ours)	82.46	84.54	65.69	77.56

Appendix

Table 15 : Per-sequence versus fixed thresholds (MODA). Both filter thresholds are replaced by the same fixed quantile on every dataset. The best fixed quantile differs by dataset, while log-Otsu is within 0.6 points of the best fixed choice on WildTrack and MultiviewX.

Variant	seq1	seq2	seq3	seq4	seq5	Mean
weighted view support	64.83	67.31	80.73	74.86	77.04	72.95
uncertainty filter only	67.79	64.85	83.59	77.12	73.37	73.34
ground-plane filter first	67.16	69.38	81.63	78.23	79.83	75.25
uncertainty then ground-plane filter (ours)	70.31	73.55	86.41	80.25	82.24	78.55

Appendix

Table 16 : Filter ablation on the unseen 8-camera installation (GMVD configuration 2, MODA). The variants match Table 3 . The order selected on the development sequences performs best on every sequence.

Separation	Filter	$\phi<10^{\circ}$	$10$ – $30^{\circ}$	$30$ – $45^{\circ}$	$45$ – $60^{\circ}$	$60$ – $75^{\circ}$	$75$ – $90^{\circ}$
0.5 m	uncertainty	93.4	93.3	93.1	93.4	93.2	93.3
0.5 m	both	64.2	65.1	68.1	72.0	75.0	77.4
1.0 m	uncertainty	93.5	93.5	93.6	93.9	93.8	93.8
1.0 m	both	40.1	42.4	49.1	57.8	66.1	72.0
2.0 m	uncertainty	92.3	92.6	93.3	94.2	94.7	94.9
2.0 m	both	8.1	11.3	19.9	32.9	47.8	58.3

Appendix

Table 17 : Fraction of incorrect two-camera pairs that survive each filter, grouped by the angle

\phi

between the directions joining the two people and the two cameras. Lower is better.

	WildTrack	MultiviewX	GMVD
all triangulated hypotheses	92.2	93.4	74.6
+ angular consistency filter	91.5	93.4	74.3
+ uncertainty filter	89.0	90.3	67.4
+ ground-plane filter	87.2	89.1	65.1
BT: unmatched GT–prediction pairs within 0.5–1 m	12	11	46
BT: MODA if all were fixed	84.98 (+2.52)	86.01 (+1.47)	67.94 (+2.25)

Appendix

Table 18 : GT coverage (fraction of annotated people within 0.5 m of some output) after each stage of BK, and the MODA upper bound from fixing near misses of BT.

Explore similar work

GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Tracking
Sep 15, 2026Taigo Sakai, Kazuhiro Hotta, Hiroki Kouno +1Multi-Object Tracking Bird'S-Eye View
Meijo university · Chubu Electric Power Co., Inc. · Department of Science Technology 1-1 Higashishin-cho, Higashi-ku, 1-501, Shiogamaguchi, Nagoya 461-8680, Japan Tempaku, Nagoya 468-8501, Japan
Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives
Jun 3, 2026Ayumi Umemura, Toshinori Kuwahara, Marc Pollefeys +1Indoor Localization Floor Plan Generation
ETH Zurich · Tohoku University
Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment
Jul 22, 2026Ponleur Veng, Dominique Vaufreydaz, Phutphalla KongMulti-Object Tracking Extrinsic Calibration
CADT, M-PSI · Cambodia Academy of Digital Technology · Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 38000 Grenoble, France +2

Sep 15, 2026, cs.CVJ/K move · Enter open · S save

GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Tracking

Taigo Sakai, Kazuhiro Hotta, Hiroki Kouno, Naoki Kato

Meijo university · Chubu Electric Power Co., Inc. · Department of Science Technology 1-1 Higashishin-cho, Higashi-ku, 1-501, Shiogamaguchi, Nagoya 461-8680, Japan Tempaku, Nagoya 468-8501, Japan

Multi-Object Tracking Bird'S-Eye View Roadside Cameras

Open paper AskPDF arXiv

Reducing the number of cameras reduces the deployment cost but removes views that correct BEV responses stretched away from true pedestrian positions by projection and short score drops that can split tracks} in Bird's-Eye View (BEV) tracking. We introduce GRACE, a camera-efficient multi-view tracker with three components. Volumetric-Guided Fusion combines homography-based BEV features with features lifted through 3D space. Ray Conditioning exposes each camera's viewing direction to the fusion network. Its tracking component, BEV Track Recovery (BTR), uses low-confidence detections only to continue existing tracks. The same detections cannot start new tracks. With two WildTrack cameras, GRACE improves MOTA from 83.54 for TrackTacular, our baseline, to 91.07.

Abstract

Explore similar work

GRACE: Geometry- and Ray-Aware Camera-Efficient Multi-View Pedestrian Tracking

Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives

Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment