Papers › Multi‑camera trajectory matching based on hierarchical clustering and constraints

Multi‑camera trajectory matching based on hierarchical clustering and constraints

19 Oct 2023Multimedia Tools and Applications 2023 10archive 2025-07-28

Gábor Szűcs, Regő Borsodi, Dávid Papp

The fast improvement of deep learning methods resulted in breakthroughs in image classification, object detection, and object tracking. Autonomous driving and traffic monitoring systems, especially the on-premise installed fixed position multi-camera configurations, benefit greatly from recent advances. In this paper, we propose a Multi-Camera Multi-Target (MCMT) vehicle tracking system using a constrained hierarchical clustering solution, which improves trajectory matching, and thus provides a more robust tracking of objects transitioning between cameras. YOLOv5, ByteTrack, and ResNet50-IBN ReID networks are used for vehicle detection and tracking. Static attributes such as vehicle type and vehicle color are determined from ReID features with SVM. The proposed ReID feature-based attribute categorization shows better performance, than its pure CNN counterpart. Single-camera trajectories (SCTs) are combined into multi-camera trajectories (MCTs) using hierarchical agglomerative clustering (HAC) with time and space constraints (our proposed algorithm is denoted by MCT#MAC). Similarities between SCTs are measured by comparing the mean ReID features cumulated on the trajectory. The system was evaluated on more datasets, and our experiments demonstrate that constraining HAC by manipulating the proximity matrix greatly improves the multi-camera IDF1 score.

Paper PDF Code

Code

regob/vehicle_mtmc pytorch 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.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Attribute Autonomous Driving Constrained Clustering Image Classification Object Detection Object Tracking Trajectory Clustering Unsupervised Vehicle Re-Identification Vehicle Re-Identification image-classification object-detection vehicle detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Vehicle Re-Identification	VeRi-Wild Large	ResNet50-IBN	mAP	58.62	#2 of 2	Archive leaderboard	report
Vehicle Re-Identification	VeRi-Wild Small	ResNet50-IBN	mAP	73.4	#3 of 3	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.

Methods

Batch Normalization SSD SVM

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