Particle PHD Filtering for Multi-Target Visual Tracking

Maggio, Emilio; Piccardo, E.; Regazzoni, Carlo S.; Cavallaro, Andrea

doi:10.1109/icassp.2007.366104

Cited by 62 publications

(50 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the first video "motinas-multi-face-fast" [17], three males move quickly and occlude each other frequently. We take the second video of four objects with DV.…”

Section: Resultsmentioning

confidence: 99%

Structured Learning for Multiple Object Tracking

Wang¹,

Han²,

Pavlović³

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

Many adaptive tracking-by-detection methods have been proposed to track object with slowly changing appearance. However, most of those methods are designed for single object tracking. This paper proposes a method for adaptively tracking multiple objects based on a modified structured Support Vector Machine (SVM). The method utilizes the inter-object constraints and the layout information, which are frequently present in multiple object tracking. Moreover, our approach detects the existences of objects by adding binary constraints in the structured SVM formulation, and therefore can handle frequent occlusions in multiple object tracking. In contrast, the original structured SVM assumes continual existence of the tracked object, making it susceptible to drift. Experimental results show the proposed method works better than existing adaptive trackingby-detection method, as well as non-adaptive association-based multiple object tracking approach.

show abstract

“…In the first video "motinas-multi-face-fast" [17], three males move quickly and occlude each other frequently. We take the second video of four objects with DV.…”

Section: Resultsmentioning

confidence: 99%

Structured Learning for Multiple Object Tracking

Wang¹,

Han²,

Pavlović³

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…Данный подход представлен ал-горитмами на основе фильтра Калмана [10] и фильтров частиц (Particle Filters) [11,12].…”

Section: Introductionunclassified

Application of binary descriptors to multiple face tracking in video surveillance systems

Леонидович¹

2016

Naučno-teh. vestn. inf. tehnol. meh. opt.

View full text Add to dashboard Cite

Mechanics and Optics, 2016, vol. 16, no. 4, pp. 670-677. doi: 10.17586/2226-1494 Abstract Subject of Research. The paper deals with the problem of multiple face tracking in a video stream. The primary application of the implemented tracking system is the automatic video surveillance. The particular operating conditions of surveillance cameras are taken into account in order to increase the efficiency of the system in comparison to existing general-purpose

show abstract

“…For this reason, we filter the detections using a Probability Hypothesis Density filter (PHD filter) ( [14]), which helps eliminating temporally inconsistent false positives and smoothing the results of the detections (Figure 1). Once the objects are extracted, we associate objects across consecutive frames in order to establish the track X r t for object r up to time t. The trajectory X r t is estimated with a graph matching algorithm ( [21]).…”

Section: Object Extraction and Trackingmentioning

confidence: 99%

Object and Scene-Centric Activity Detection Using State Occupancy Duration Modeling

Taj

Cavallaro

2008

2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance

Self Cite

View full text Add to dashboard Cite

We propose a video event analysis framework based on object segmentation and tracking, combined with a Hidden Semi-Markov Model (HSMM) that uses state occupancy duration modeling. The observations generated by a multiobject detector and tracker are used as emitting symbols and the corresponding probabilities are computed using multivariate Gaussians. Next, we recognize events by estimating the most likely object state sequence using a HSMM decoding strategy, based on the Viterbi algorithm. Moreover, the duration distribution enforces the state transition after certain time and hence better models the events constrained on time intervals. We demonstrate and evaluate the proposed framework on a dataset of approximately 20K frames, and show that the duration modeling improves the event detection results by 7% to 11%, compared to state-ofthe-art HMMs.

show abstract

Particle PHD Filtering for Multi-Target Visual Tracking

Cited by 62 publications

References 9 publications

Structured Learning for Multiple Object Tracking

Structured Learning for Multiple Object Tracking

Application of binary descriptors to multiple face tracking in video surveillance systems

Object and Scene-Centric Activity Detection Using State Occupancy Duration Modeling

Contact Info

Product

Resources

About