Assessment and optimization of methods for tracking people in riot control scenarios

Hübner, Yvonne; Metzler, Jürgen; Dürr, Bernhard; Jäger, Uwe; Willersinn, Dieter

doi:10.1117/12.799827

Cited by 5 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Covariance descriptors were originally introduced for detection and classification tasks in [3]. They were then successfully applied to tracking [7] and have been shown to be well suited for person tracking in aerial images [8,9]. They also yield high accuracy when used for appearance-based person re-identification [10,11].…”

Section: Related Workmentioning

confidence: 99%

Person re-identification across aerial and ground-based cameras by deep feature fusion

Schumann

Metzler

2017

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Person re-identification is the task of correctly matching visual appearances of the same person in image or video data while distinguishing appearances of different persons. The traditional setup for re-identification is a network of fixed cameras. However, in recent years mobile aerial cameras mounted on unmanned aerial vehicles (UAV) have become increasingly useful for security and surveillance tasks. Aerial data has many characteristics different from typical camera network data. Thus, re-identification approaches designed for a camera network scenario can be expected to suffer a drop in accuracy when applied to aerial data.In this work, we investigate the suitability of features, which were shown to give robust results for reidentification in camera networks, for the task of re-identifying persons between a camera network and a mobile aerial camera. Specifically, we apply hand-crafted region covariance features and features extracted by convolutional neural networks which were learned on separate data. We evaluate their suitability for this new and as yet unexplored scenario. We investigate common fusion methods to combine the hand-crafted and learned features and propose our own deep fusion approach which is already applied during training of the deep network.We evaluate features and fusion methods on our own dataset. The dataset consists of fourteen people moving through a scene recorded by four fixed ground-based cameras and one mobile camera mounted on a small UAV. We discuss strengths and weaknesses of the features in the new scenario and show that our fusion approach successfully leverages the strengths of each feature and outperforms all single features significantly.

show abstract

Section: Related Workmentioning

confidence: 99%

Person re-identification across aerial and ground-based cameras by deep feature fusion

Schumann

Metzler

2017

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…where is the unnormalized graph Laplacian as defined by Equation (15). Now let the intrinsic dimensionality of the training data set (the intrinsic dimensionality of the manifold need to be known or need to be estimated).…”

Section: Training Stagementioning

confidence: 99%

“…The authors obtained excellent results in several tracking tasks by using covariance descriptors [14], and in [13] it was shown that these descriptors are also efficient for object detections tasks. In [15] we evaluated the performance of the Covariance-Tracker for tracking people in crowds and compared the results to other tracking methods. This evaluation confirmed the suitability of using covariance descriptors.…”

Section: Introductionmentioning

confidence: 99%

Human detection in MOUT scenarios using covariance descriptors and supervised manifold learning

Metzler

Willersinn

2010

Visual Information Processing XIX

Self Cite

View full text Add to dashboard Cite

Military Operations in Urban Terrain (MOUT) require the capability to perceive and to analyse the situation around a patrol in order to recognize potential threats. As in MOUT scenarios threats usually arise from humans one important task is the robust detection of humans. Detection of humans in MOUT by image processing systems can be very challenging, e.g., due to complex outdoor scenes where humans have a weak contrast against the background or are partially occluded. Porikli et al. introduced covariance descriptors and showed their usefulness for human detection in complex scenes. However, these descriptors do not lie on a vector space and so well-known machine learning techniques need to be adapted to train covariance descriptor classifiers. We present a novel approach based on manifold learning that simplifies the classification of covariance descriptors. In this paper, we apply this approach for detecting humans. We describe our human detection method and evaluate the detector on benchmark data sets generated from real-world image sequences captured during MOUT exercises

show abstract

“…The authors obtained excellent results in several tracking tasks by using covariance descriptors [8], and in [5] it was shown that these descriptors are also suitable for object detections tasks. In [2] we evaluated the performance of the Covariance-Tracker for tracking people in crowds and compared the results to other tracking methods. This evaluation confirmed the advantage of covariance descriptors.…”

Section: • Efficient Fusion Of Multiple Featuresmentioning

confidence: 99%

Robust tracking of people in crowds with covariance descriptors

Metzler¹,

Willersinn²

2009

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

In order to control riots in crowds, it is helpful to get the ringleader under control. A great support to achieve this task is the capability to automatically track individual persons in a video sequence taken from a crowd. In this paper we address the robustness of such a tracking function. We start from the results of a previous evaluation of tracking methods, where a so-called Covariance-Tracker was found to be most appropriate. This tracker uses covariance matrices as object descriptors, as proposed by Porikli et al. The set of all covariance matrices describes a Riemannian manifold that is used to compare and update the covariance descriptors during tracking. We propose Covariance-Tracker adaptations to improve its performance. Furthermore, we summarize the performance evaluation results of the original method and compare these with the results of the adapted one. The result is a robust method for tracking people in crowds which can improve situational awareness

show abstract

Assessment and optimization of methods for tracking people in riot control scenarios

Cited by 5 publications

References 8 publications

Person re-identification across aerial and ground-based cameras by deep feature fusion

Person re-identification across aerial and ground-based cameras by deep feature fusion

Human detection in MOUT scenarios using covariance descriptors and supervised manifold learning

Robust tracking of people in crowds with covariance descriptors

Contact Info

Product

Resources

About