POI: Multiple Object Tracking with High Performance Detection and Appearance Feature

@inproceedings{Yu2016POIMO,
  title={POI: Multiple Object Tracking with High Performance Detection and Appearance Feature},
  author={Fengwei Yu and Wenbo Li and Quanquan Li and Yu Liu and Xiaohua Shi and Junjie Yan},
  booktitle={ECCV Workshops},
  year={2016}
}
Detection and learning based appearance feature play the central role in data association based multiple object tracking (MOT), but most recent MOT works usually ignore them and only focus on the hand-crafted feature and association algorithms. In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting. We make our detection and appearance feature publicly… Expand
MF-SORT: Simple Online and Realtime Tracking with Motion Features
TLDR
A novel Simple Online and Realtime Tracking with motion features (MF-SORT) that is able to take a trade-off between performance and efficiency by focusing on the motion features of the objects during data association is proposed. Expand
Multi-object Tracking by Joint Detection and Identification Learning
TLDR
Experimental results show that the proposed MOT method via joint learning on detection and identification by using existing MOT datasets without external training data achieves competitive performance compared with state-of-the-art methods in video-based object detection, cross-dataset person re-identification, and multi-object tracking. Expand
Attention-Enabled Object Detection to Improve One-Stage Tracker
State-of-the-art (SoTA) detection-based tracking methods mostly accomplish the detection and the identification feature learning tasks separately. Only a few efforts include the joint learning ofExpand
Online Multi-object Tracking with Multi-level Appearance Feature and Temporal Attention Mechanism
  • Ding Yongchao, Ye Chen
  • Computer Science
  • 2019 IEEE 5th International Conference on Computer and Communications (ICCC)
  • 2019
TLDR
A novel algorithm that integrates multi-level appearance feature and temporal attention mechanism is proposed for online multi-object tracking and can achieve good tracking performance compared to start-of-art tracking algorithms, especially in identity consistency. Expand
Real-Time Multiple Object Tracking with Discriminative Features
TLDR
This paper exploits the discriminative embedding features in the association stage to improve the tracking performance and shows that this method can achieve competitive tracking performance in real time compared to the state-of-the-art tracking methods. Expand
Convolutional Neural Network-based Simple Online Multiple Object Tracking
TLDR
The evaluation results confirmed that combine motion state with the appearance information extracted neural network is efficient for tracking multiple objects continually and stably. Expand
Online multi-person tracking assist by high-performance detection
TLDR
The low-rank-based foreground detection method is explored to refine the detections and show it can significantly lead a better tracking result in online multi-object tracking and solve the data association problem in online MOT. Expand
Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning
  • Nathanael L. Baisa
  • Computer Science
  • 2019 22th International Conference on Information Fusion (FUSION)
  • 2019
TLDR
A new online multi-object visual tracker based on a Gaussian mixture Probability Hypothesis Density (GM-PHD) filter in combination with a similarity Convolutional Neural Network (CNN) is proposed and significantly outperforms several state-of-the-art trackers in terms of tracking accuracy and precision. Expand
Improving Online Multiple Object tracking with Deep Metric Learning
TLDR
This paper trains a convolutional neural network to learn an embedding function in a Siamese configuration on a large person re-identification dataset offline and uses this learned appearance metric to robustly build estimates of pedestrian's trajectories in the MOT16 dataset. Expand
Multi-Person Tracking Based on Faster R-CNN and Deep Appearance Features
TLDR
This paper presents a novel algorithm for improved object detection followed by enhanced object tracking that has been increased by employing deep learning-based Faster region convolutional neural network (Faster R-CNN) algorithm. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 18 REFERENCES
Online Visual Tracking Using Temporally Coherent Part Cluster
TLDR
A robust online model is proposed, formulating the tracking task as a problem of identifying Temporally Coherent Part (TCP) clusters as a dense neighborhoods searching problem using a relational hyper graph in which the relationship among multiple temporal local parts is encoded as the affinity value of a hyper edge connecting them. Expand
Multiple Target Tracking Based on Undirected Hierarchical Relation Hypergraph
TLDR
A novel data association approach based on undirected hierarchical relation hypergraph is proposed, which formulates the tracking task as a hierarchical dense neighborhoods searching problem on the dynamically constructed Undirected affinity graph and makes the tracker robust to the spatially close targets with similar appearance. Expand
Online Deformable Object Tracking Based on Structure-Aware Hyper-Graph
TLDR
This paper constructs a structure-aware hyper-graph to capture higher order structural dependences of different parts of the tracking target in multiple consecutive frames, and solves the tracking problem by searching dense subgraphs on it. Expand
Person Re-identification in the Wild
TLDR
A new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, and it is shown that pedestrian detection aids re-ID through two simple yet effective improvements: a cascaded fine-tuning strategy that trains a detection model first and then the classification model, and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement. Expand
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
TLDR
An object detection system that relies on a multi-region deep convolutional neural network that also encodes semantic segmentation-aware features that aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. Expand
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
TLDR
A novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter is proposed and significantly outperforms state-of-the-art methods on this dataset. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
MOT16: A Benchmark for Multi-Object Tracking
TLDR
A new release of the MOTChallenge benchmark, which focuses on multiple people tracking, and offers a significant increase in the number of labeled boxes, but also provides multiple object classes beside pedestrians and the level of visibility for every single object of interest. Expand
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs
TLDR
This work proposes an approach to data association which incorporates both motion and appearance in a global manner and utilizes Generalized Minimum Clique Graphs to solve the optimization problem of the data association method. Expand
A mobile vision system for robust multi-person tracking
TLDR
A mobile vision system for multi-person tracking in busy environments that integrates continuous visual odometry computation with tracking-by-detection in order to track pedestrians in spite of frequent occlusions and egomotion of the camera rig is presented. Expand
...
1
2
...