ELECTRICITY: An Efficient Multi-camera Vehicle Tracking System for Intelligent City

Qian, Yijun; Yu, Lean; Liu, Wenhe; Hauptmann, Alexander G.

doi:10.1109/cvprw50498.2020.00302

Cited by 58 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to some prior methods [49,8] that require certain overlapping ratios between the cameras, DyGLIP can gracefully handle both overlapping and nonoverlapping scenarios. Similar to prior MC-MOT methods [16,26], the task of tracking in each camera is assumed to be performed by an off-the-shelf single-camera MOT tracker. We choose DeepSORT [41]…”

Section: Problem Formulationmentioning

confidence: 99%

“…Non-overlapping FOVs dataset on Car/Vehicles Tracking Table 10 shows the results on the AI City challenge validation set. We use the same ReID features as in ELECTRICITY [26]. Indeed, DyGLIP obtains much better results, higher on MOTA and ID F1 in S02 (37.2 % and 11.1%, respectively), in S05 (10.5 % and 3.5%, respectively), thanks to the dynamic graph formulation and the attention module.…”

Section: Comparison With State-of-the-arts Mc-motmentioning

confidence: 99%

See 1 more Smart Citation

DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking

Quach

Nguyen

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Multi-Camera Multiple Object Tracking (MC-MOT) is a significant computer vision problem due to its emerging applicability in several real-world applications. Despite a large number of existing works, solving the data association problem in any MC-MOT pipeline is arguably one of the most challenging tasks. Developing a robust MC-MOT system, however, is still highly challenging due to many practical issues such as inconsistent lighting conditions, varying object movement patterns, or the trajectory occlusions of the objects between the cameras. To address these problems, this work, therefore, proposes a new Dynamic GraphModel with Link Prediction (DyGLIP) approach 1 to solve the data association task. Compared to existing methods, our new model offers several advantages, including better feature representations and the ability to recover from lost tracks during camera transitions. Moreover, our model works gracefully regardless of the overlapping ratios between the cameras. Experimental results show that we outperform existing MC-MOT algorithms by a large margin on several practical datasets. Notably, our model works favorably on online settings but can be extended to an incremental approach for large-scale datasets.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Section: Comparison With State-of-the-arts Mc-motmentioning

confidence: 99%

DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking

Quach

Nguyen

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…This association is typically stated as a bipartite graph matching problem and solved applying minimum-cost flow techniques, e.g., resolving an association matrix using the Hungarian algorithm [9]- [11]. Re-Identification appearance cues [12] that may be combined with 3D spatial location [13], [14] are widely used to build the association matrix. However, due to their computational cost, the use of minimumcost flow-based solvers in practical implementations is limited to datasets not containing large number of data [15].…”

Section: Introductionmentioning

confidence: 99%

Graph Neural Networks for Cross-Camera Data Association

Luna¹,

SanMiguel²,

Martínez³

et al. 2022

Preprint

View full text Add to dashboard Cite

Cross-camera image data association is essential for many multi-camera computer vision tasks, such as multi-camera pedestrian detection, multi-camera multi-target tracking, 3D pose estimation, etc. This association task is typically stated as a bipartite graph matching problem and often solved by applying minimum-cost flow techniques, which may be computationally inefficient with large data. Furthermore, cameras are usually treated by pairs, obtaining local solutions, rather than finding a global solution at once. Other key issue is that of the affinity measurement: the widespread usage of non-learnable pre-defined distances, such as the Euclidean and Cosine ones. This paper proposes an efficient approach for cross-cameras data-association focused on a global solution, instead of processing cameras by pairs. To avoid the usage of fixed distances, we leverage the connectivity of Graph Neural Networks, previously unused in this scope, using a Message Passing Network to jointly learn features and similarity. We validate the proposal for pedestrian multiview association, showing results over the EPFL multi-camera pedestrian dataset. Our approach considerably outperforms the literature data association techniques, without requiring to be trained in the same scenario in which it is tested. Our code is available at http://www-vpu.eps.uam.es/publications/gnn cca.

show abstract

“…Multiple object tracking (MOT) is a well-known computer vision task that aims to track multiple objects across a video, and has been widely used in autonomous driving [1], motion recognition [2], and city-scale traffic management [3]. With the advancement of convolutional neural networks (CNNs) and their feature extraction ability, the performance of MOT methods has greatly improved.…”

Section: Introductionmentioning

confidence: 99%

Weakly-Supervised Multiple Object Tracking Via A Masked Center Point Warping Loss

Soon-Ock

Shim

Park

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Multiple object tracking (MOT), a popular subject in computer vision with broad application areas, aims to detect and track multiple objects across an input video. However, recent learning-based MOT methods require strong supervision on both the bounding box and the ID of each object for every frame used during training, which induces a heightened cost for obtaining labeled data. In this paper, we propose a weakly-supervised MOT framework that enables the accurate tracking of multiple objects while being trained without object ID ground truth labels. Our model is trained only with the bounding box information with a novel masked warping loss that drives the network to indirectly learn how to track objects through a video. Specifically, valid object center points in the current frame are warped with the predicted offset vector and enforced to be equal to the valid object center points in the previous frame. With this approach, we obtain an MOT accuracy on par with those of the state-of-the-art fully supervised MOT models, which use both the bounding boxes and object ID as ground truth labels, on the MOT17 dataset.

show abstract

ELECTRICITY: An Efficient Multi-camera Vehicle Tracking System for Intelligent City

Cited by 58 publications

References 19 publications

DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking

DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking

Graph Neural Networks for Cross-Camera Data Association

Weakly-Supervised Multiple Object Tracking Via A Masked Center Point Warping Loss

Contact Info

Product

Resources

About