Simple online and realtime tracking with a deep association metric

Wojke, Nicolai; Bewley, Alex; Paulus, Dietrich

doi:10.1109/icip.2017.8296962

Cited by 3,376 publications

(2,023 citation statements)

References 23 publications

Supporting

Mentioning

2,015

Contrasting

Unclassified

Order By: Relevance

“…It reports the tracking results on the VIVA hand tracking dataset. To investigate the performance of our model in hand tracking, we apply PHDN to SORT tracker [20], deep SORT tracker [21], IOU tracker [22]. SORT we use three trackers to evaluate our model in the practical tracking task.…”

Section: Multiple Hand Tracking In Vehiclesmentioning

confidence: 99%

See 1 more Smart Citation

Towards interpretable and robust hand detection via pixel-wise prediction

Liú

Zhang

Luo

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions. In this paper, we propose a novel neural network model, which introduces interpretability into hand detection for the first time. The main improvements include: (1) Detect hands at pixel level to explain what pixels are the basis for its decision and improve transparency of the model. (2) The explainable Highlight Feature Fusion block highlights distinctive features among multiple layers and learns discriminative ones to gain robust performance. (3) We introduce a transparent representation, the rotation map, to learn rotation features instead of complex and non-transparent rotation and derotation layers. (4) Auxiliary supervision accelerates the training process, which saves more than 10 hours in our experiments. Experimental results on the VIVA and Oxford hand detection and tracking datasets show competitive accuracy of our method compared with state-of-the-art methods with higher speed. (Libo Zhang)1 Dan Liu and Tiejian Luo were contributed equally and should be considered as co-first authors. Models and code are available at https://isrc.iscas.ac.cn/gitlab/research/pr2020phdn.

show abstract

Section: Multiple Hand Tracking In Vehiclesmentioning

confidence: 99%

“…To evaluate our detector, we employ the SORT tracker [20], deep SORT tracker [21] and IOU tracker [22] to associate our detection results to extend a trajectory on the VIVA hand tracking dataset. The results are reported in…”

Section: Evaluations On Oxford Hand Detection Datasetmentioning

confidence: 99%

Towards interpretable and robust hand detection via pixel-wise prediction

Liú

Zhang

Luo

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Persons' appearance can be utilized as an important tracking cue. Although existing works exploit the entire body appearance [7,8], we suppose that only using the upper body appearance can alleviate occlusion problems in crowd scenes. Since 2D body poses are estimated in this work, the upper body image patches can be cropped accordingly.…”

Section: Matching Costmentioning

confidence: 99%

“…(5) and the cost matrix C by Eq. (8). In the first frame, all the observed locations are assigned to a tracking set.…”

Section: Matching Costmentioning

confidence: 99%

Using Panoramic Videos for Multi-Person Localization and Tracking In A 3D Panoramic Coordinate

Yang

Wu³

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This work proposes a new human-related video processing task named 3D panoramic multi-person localization and tracking. With a benchmark dataset and a simple yet effective solution, it establishes a new paradigm for multi-person tracking systems and related applications. Unlike existing methods that can only work on a 2D coordinate or a narrowangle-view 3D coordinate, our proposal can maximally explore the 3D trajectory information of tracking targets. This is approached by applying camera geometry to transform human locations from 2D panoramic image coordinates to a 3D panoramic camera coordinate, and then by applying a tracking algorithm that associates human appearance and 3D trajectory together. Our code and dataset will be available at https://github.com/fandulu/MPLT.

show abstract

“…For example, Fast-DT [2] relies on detector confidence to drop a track, by efficiently applying the object detector on individual tracker output. Unlike Fast-DT, SORT [14], [17] focuses mostly on data association and multi-target tracking. Recently methods such as the deep Siamese-FC network [1,8] have been proposed to exploit the expressive powers of deep learning in VOT.…”

Section: Introductionmentioning

confidence: 99%

On the Interaction Between Deep Detectors and Siamese Trackers in Video Surveillance

Kiran

Tiwari

Nguyen-Meidine

et al. 2019

2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

Visual object tracking is an important function in many real-time video surveillance applications, such as localization and spatio-temporal recognition of persons. In realworld applications, an object detector and tracker must interact on a periodic basis to discover new objects, and thereby to initiate tracks. Periodic interactions with the detector can also allow the tracker to validate and/or update its object template with new bounding boxes. However, bounding boxes provided by a state-of-the-art detector are noisy, due to changes in appearance, background and occlusion, which can cause the tracker to drift. Moreover, CNN-based detectors can provide a high level of accuracy at the expense of computational complexity, so interactions should be minimized for real-time applications. In this paper, a new approach is proposed to manage detectortracker interactions for trackers from the Siamese-FC family. By integrating a change detection mechanism into a deep Siamese-FC tracker, its template can be adapted in response to changes in a target's appearance that lead to drifts during tracking. An abrupt change detection triggers an update of tracker template using the bounding box produced by the detector, while in the case of a gradual change, the detector is used to update an evolving set of templates for robust matching. Experiments were performed using state-of-the-art Siamese-FC trackers and the YOLOv3 detector on a subset of videos from the OTB-100 dataset that mimic video surveillance scenarios. Results highlight the importance for reliable VOT of using accurate detectors. They also indicate that our adaptive Siamese trackers are robust to noisy object detections, and can significantly improve the performance of Siamese-FC tracking.

show abstract

Simple online and realtime tracking with a deep association metric

Cited by 3,376 publications

References 23 publications

Towards interpretable and robust hand detection via pixel-wise prediction

Towards interpretable and robust hand detection via pixel-wise prediction

Using Panoramic Videos for Multi-Person Localization and Tracking In A 3D Panoramic Coordinate

On the Interaction Between Deep Detectors and Siamese Trackers in Video Surveillance

Contact Info

Product

Resources

About