Objective Evaluation of Pedestrian and Vehicle Tracking on the CLEAR Surveillance Dataset

Taj, Murtaza; Maggio, Emilio; Cavallaro, Andrea

doi:10.1007/978-3-540-68585-2_13

Cited by 5 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The graph correspondence for vehicle tracking and classification is used in [58], [86], and [142]. In [131], vehicle and pedestrian tracking is evaluated on the CLEAR data set [25] and uses greedy graph correspondence tracking based on [123]. Dynamic programming approaches can be used to find an optimal path through nodes of several frames.…”

Section: Trackingmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Computer Vision Techniques for the Analysis of Urban Traffic

Buch

Velastín

Orwell

2011

IEEE Trans. Intell. Transport. Syst.

543

231

View full text Add to dashboard Cite

Automatic video analysis from urban surveillance cameras is a fast-emerging field based on computer vision techniques. We present here a comprehensive review of the state-of-the-art computer vision for traffic video with a critical analysis and an outlook to future research directions. This field is of increasing relevance for intelligent transport systems (ITSs). The decreasing hardware cost and, therefore, the increasing deployment of cameras have opened a wide application field for video analytics. Several monitoring objectives such as congestion, traffic rule violation, and vehicle interaction can be targeted using cameras that were typically originally installed for human operators. Systems for the detection and classification of vehicles on highways have successfully been using classical visual surveillance techniques such as background estimation and motion tracking for some time. The urban domain is more challenging with respect to traffic density, lower camera angles that lead to a high degree of occlusion, and the variety of road users. Methods from object categorization and 3-D modeling have inspired more advanced techniques to tackle these challenges. There is no commonly used data set or benchmark challenge, which makes the direct comparison of the proposed algorithms difficult. In addition, evaluation under challenging weather conditions (e.g., rain, fog, and darkness) would be desirable but is rarely performed. Future work should be directed toward robust combined detectors and classifiers for all road users, with a focus on realistic conditions during evaluation.

show abstract

Section: Trackingmentioning

confidence: 99%

“…There is only event-based ground truth, which is of limited use for the evaluation of low-level algorithms. Tracking ground truth is available for parts of videos through [25], with a vehicle and pedestrian tracker evaluated in [131]. The data set has also been used in [20]- [22].…”

Section: B Data Setsmentioning

confidence: 99%

A Review of Computer Vision Techniques for the Analysis of Urban Traffic

Buch

Velastín

Orwell

2011

IEEE Trans. Intell. Transport. Syst.

543

231

View full text Add to dashboard Cite

show abstract

“…Furthermore, a suitable metric has also been proposed for evaluating the performance of pedestrian tracking algorithms. The OSPA metric is appropiate for comparing estimates of possibly different cardinalities, so it is better suited for evaluating performance of visual tracking algorithms than previously proposed benchmark suites [106].…”

Section: Summary and Contributionsmentioning

confidence: 99%

State Estimation and Smoothing for the Probability Hypothesis Density Filter

Hernandez¹

View full text Add to dashboard Cite

<p>Tracking multiple objects is a challenging problem for an automated system, with applications in many domains. Typically the system must be able to represent the posterior distribution of the state of the targets, using a recursive algorithm that takes information from noisy measurements. However, in many important cases the number of targets is also unknown, and has also to be estimated from data. The Probability Hypothesis Density (PHD) filter is an effective approach for this problem. The method uses a first-order moment approximation to develop a recursive algorithm for the optimal Bayesian filter. The PHD recursion can implemented in closed form in some restricted cases, and more generally using Sequential Monte Carlo (SMC) methods. The assumptions made in the PHD filter are appealing for computational reasons in real-time tracking implementations. These are only justifiable when the signal to noise ratio (SNR) of a single target is high enough that remediates the loss of information from the approximation. Although the original derivation of the PHD filter is based on functional expansions of belief-mass functions, it can also be developed by exploiting elementary constructions of Poisson processes. This thesis presents novel strategies for improving the Sequential Monte Carlo implementation of PHD filter using the point process approach. Firstly, we propose a post-processing state estimation step for the PHD filter, using Markov Chain Monte Carlo methods for mixture models. Secondly, we develop recursive Bayesian smoothing algorithms using the approximations of the filter backwards in time. The purpose of both strategies is to overcome the problems arising from the PHD filter assumptions. As a motivating example, we analyze the performance of the methods for the difficult problem of person tracking in crowded environments</p>

show abstract

Recognizing Interactions in Video

Taj

Cavallaro

2010

Studies in Computational Intelligence

View full text Add to dashboard Cite

Objective Evaluation of Pedestrian and Vehicle Tracking on the CLEAR Surveillance Dataset

Cited by 5 publications

References 15 publications

A Review of Computer Vision Techniques for the Analysis of Urban Traffic

A Review of Computer Vision Techniques for the Analysis of Urban Traffic

State Estimation and Smoothing for the Probability Hypothesis Density Filter

Recognizing Interactions in Video

Contact Info

Product

Resources

About