Collaborative acquisition of multi-view face images in real-time using a wireless camera network

Abstract

Abstract-In order to support real-time face recognition using a wireless camera network, we design a data acquisition service to quickly and reliably acquire face images of human subjects from multiple views and to simultaneously index each acquired image into its corresponding pose. In comparison with detection of frontal faces, the detection of non-frontal faces with unknown pose is a much more challenging problem that involves significant image processing. In this paper, we describe a collaborative approach in which multi-view camera geometry and inter-camera communication is utilized at run time to significantly reduce the required processing time. By doing so, we are able to achieve a high capture rate for both frontal and non-frontal faces and at the same time maintain a high detection accuracy. We implement our face acquisition system on a 1.6 GHz Intel Atom Processor based embedded camera network and show that we can reliably acquire frontal faces at 11 fps and non-frontal faces at 10 fps on images captured at a resolution of 640 by 480 pixels.

Multi-Camera Coordination and Control in Surveillance Systems

“…Object's correspondence across multiple views [Hu et al 2006;Orwell et al 1999;Fukuda et al 2000;Mittal and Davis 2001;Guler et al 2003;Wang et al 2011b;Nguyen et al 2003;Parupati et al 2011] No Coordination, only data fusion and feature matching across multiple cameras Camera selection and handoff [Wang et al 2011a] Control theory [Li and Bhanu 2009, 2012 Game theory [Daniyal and Cavallaro 2011;Daniyal et al 2010] Decision theory [Dieber et al 2012;Esterle et al 2014] Market-based approach [Cai and Aggarwal 1999;Dieber et al 2011] Ad-hoc optimization technique [Morioka et al 2008] Fuzzy based automaton…”

Heterogeneous feature fusion-based optimal face image acquisition in visual sensor network

“…Here, the face quality is estimated by the tracking information and nodes position. Parupati et al [6] proposed a multi-view face images acquisition method, where the visual sensor nodes are placed as a specific array to get different face views of target at the same time. Ding et al [7] developed a distributed PTZ camera network to execute pedestrian tracking, where face quality is a part of evaluation criterion of tracking performance.…”

Effectiveness of Multi-View Face Images and Anthropometric Data In Real-Time Networked Biometrics

“…• The Multi-view collaborative face detection system in [2] has been augmented with • Performance of the system has been analyzed in Closed set and Open-set scenarios.…”

“…The performance analyses of collaborative face acquisition has been discussed in detail in [2]. We use Microsoft Kincet [3] instead of Logitech Pro 9000 cameras that were used in [2]. The advantages of replacing the Logitech cameras with Microsoft Kinect [3] are:…”

“…To address these challenges and to make a successful transition to real-time human identification systems, this thesis makes the following contributions: (1) A score-based multimodal, multi-sample fusion technique is designed to combine face images acquired by a multi-camera network and the effectiveness of opportunistically acquired multi-view face images using a camera network in improving the identification performance is characterized; (2) The multi-view face acquisition system is complemented by a network of Microsoft Kinects for extracting human anthropometric features (specifically height, shoulder width and arm length). The score-fusion technique is augmented to utilize human anthropometric data and the effectiveness of this data is characterized.…”