Robustly and efficiently tracking pedestrians in the infrared spectrum is a crucial requirement for a number of applications. At the same time, it is also particularly critical due to both the peculiarities of infrared images and pedestrian targets. In fact, low resolutions and high signal-to-noise ratios combined with extremely variable target signatures, chaotic trajectories, and frequent occlusions have forced researchers to develop ever more complex strategies characterized by a neat trade-off between tracking accuracy and computational complexity. Thus, most of the existing techniques might not be capable of ensuring real-time performances with a suitable degree of robustness, especially on limited-resource hardware used, e.g., in automotive or security scenarios. We present a technique that extends an extremely efficient tracking method originally tailored to targets that exhibit a clear and stable hot spot to allow it to deal with pedestrian targets by reusing its core components and integrating an occlusion detection and recovery mechanism. Experimental results obtained on public datasets confirmed that the devised method is able to obtain a robustness that is superior to that of other common approaches by maintaining the high tracking speed of the reference method.
Intensity variation function and template matching-based pedestrian tracking in infrared imagery with occlusion detection and recovery / Lamberti, Fabrizio; Santomo, R.; Sanna, Andrea; Montuschi, Paolo. - In: OPTICAL ENGINEERING. - ISSN 0091-3286. - STAMPA. - 54:3:(2015), pp. 1-19. [10.1117/1.OE.54.3.033106]
Intensity variation function and template matching-based pedestrian tracking in infrared imagery with occlusion detection and recovery
LAMBERTI, FABRIZIO;SANNA, Andrea;MONTUSCHI, PAOLO
2015
Abstract
Robustly and efficiently tracking pedestrians in the infrared spectrum is a crucial requirement for a number of applications. At the same time, it is also particularly critical due to both the peculiarities of infrared images and pedestrian targets. In fact, low resolutions and high signal-to-noise ratios combined with extremely variable target signatures, chaotic trajectories, and frequent occlusions have forced researchers to develop ever more complex strategies characterized by a neat trade-off between tracking accuracy and computational complexity. Thus, most of the existing techniques might not be capable of ensuring real-time performances with a suitable degree of robustness, especially on limited-resource hardware used, e.g., in automotive or security scenarios. We present a technique that extends an extremely efficient tracking method originally tailored to targets that exhibit a clear and stable hot spot to allow it to deal with pedestrian targets by reusing its core components and integrating an occlusion detection and recovery mechanism. Experimental results obtained on public datasets confirmed that the devised method is able to obtain a robustness that is superior to that of other common approaches by maintaining the high tracking speed of the reference method.File | Dimensione | Formato | |
---|---|---|---|
oe.pdf
non disponibili
Descrizione: post-print
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
2.82 MB
Formato
Adobe PDF
|
2.82 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2592724
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo