Accurate annotation is fundamental to quantify the performance of multi-sensor and multi-modal object detectors and trackers. However, invasive or expensive instrumentation is needed to automatically generate these annotations. To mitigate this problem, we present a multi-modal approach that leverages annotations from reference streams (e.g. individual camera views) and measurements from unannotated additional streams (e.g. audio) to infer 3D trajectories through an optimization. The core of our approach is a multi-modal extension of Bundle Adjustment with a cross-modal correspondence detection that selectively uses measurements in the optimization. We apply the proposed approach to fully annotate a new multi-modal and multi-view dataset for multi-speaker 3D tracking.
Accurate Target Annotation in 3D from Multimodal Streams
Oswald Lanz
;Alessio Brutti;Alessio Xompero;Xinyuan Qian;Maurizio Omologo;
2019-01-01
Abstract
Accurate annotation is fundamental to quantify the performance of multi-sensor and multi-modal object detectors and trackers. However, invasive or expensive instrumentation is needed to automatically generate these annotations. To mitigate this problem, we present a multi-modal approach that leverages annotations from reference streams (e.g. individual camera views) and measurements from unannotated additional streams (e.g. audio) to infer 3D trajectories through an optimization. The core of our approach is a multi-modal extension of Bundle Adjustment with a cross-modal correspondence detection that selectively uses measurements in the optimization. We apply the proposed approach to fully annotate a new multi-modal and multi-view dataset for multi-speaker 3D tracking.File | Dimensione | Formato | |
---|---|---|---|
20190218055852_820837_4957.pdf
solo utenti autorizzati
Descrizione: CRC
Tipologia:
Documento in Pre-print
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
1.72 MB
Formato
Adobe PDF
|
1.72 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.