MIDSCA: Towards a Smart Camera architecture of mobile internet devices

Wittke, Michael; Hoffmann, Martin; Hähner, Jörg; Schloer, C. Muller

doi:10.1109/icdsc.2008.4635713

Cited by 6 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, several papers have investigated the use of mobile phones in surveillance networks [1], [2]. Mobile devices are advantageous because they can be easily deployed on stationary or moving objects in the environment unuer observation.…”

Section: Introductionmentioning

confidence: 99%

Resource-aware architectures for particle filter based visual target tracking

Forte

Srivastava

2011

2011 International Green Computing Conference and Workshops

View full text Add to dashboard Cite

There are a �rowing number of visual tracking applications for mobile deVIces such as smart phones and smart cameras. However, existin � computer vision algorithms are demanding and mobile deVIces possess limited computational capabilities, energy, and bandwidth to support them. Conven tional approaches to distributed target tracking with a camera node and a receiver node are either sender based or receiver based. Both approaches are highly suited for certain scenarios, but have limIted applicability outside of their scope. In this gaper, we propose two new approaches for a particle filter ased tracking system. The first proposed approach reduces the energy and bandwidth typically required for the receiver based setup. The second proposed approach partitions tracking workload between sender and receiver and adapts to the frame to-frame demands of particle filtering. In doing so, this scheme promotes better balance of computin� capabilities, energy, and bandwidth among sender and receIVer. Results show that the proposed solutions require low additional overhead, can improve on tracking system lifetime, and may be more effective than conventional architectures for many tracking instances.

show abstract

Section: Introductionmentioning

confidence: 99%

Resource-aware architectures for particle filter based visual target tracking

Forte

Srivastava

2011

2011 International Green Computing Conference and Workshops

View full text Add to dashboard Cite

show abstract

“…For example, several groups have investigated the use of mobile phones in surveillance networks [Bolliger et al 2007;Wittke et al 2008]. Mobile devices are advantageous because they can easily be deployed on stationary or moving objects in the environment under observation.…”

Section: Introductionmentioning

confidence: 99%

Resource-aware architectures for adaptive particle filter based visual target tracking

Forte

Srivastava

2013

ACM Trans. Des. Autom. Electron. Syst.

View full text Add to dashboard Cite

There are a growing number of visual tracking applications now being envisioned for mobile devices. However, since computer vision algorithms such as particle filtering have large computational demands, they can result in high energy consumption and temperatures in mobile devices. Conventional approaches for distributed target tracking with a camera node and a receiver node are either sender-based (SB) or receiver-based (RB). The SB approach uses little energy and bandwidth, but requires a sender with large computational resources. The RB approach fits applications where computational resources are completely unavailable to the sender, but requires very large energy and bandwidth. In this article, we propose three architectures for distributed particle filtering that (i) reduce particle filtering workload and (ii) allow for dynamic migration of workload between nodes participating in tracking. We also discuss an adaptive particle filtering extension that adapts particle filter computational complexity and can be applied to both the conventional and proposed architectures for improved energy efficiency. Results show that the proposed solutions require low additional overhead, improve on tracking system lifetime, balance node temperatures, maintain track of the desired target, and are more effective than conventional approaches in many scenarios. ACM Reference Format:Forte, D. and Srivastava, A. 2013. Resource-aware architectures for adaptive particle filter based visual target tracking.

show abstract

“…It's also possible to build dedicated smart camera nodes around mobile chip sets with additional features like weather-proof and controllable orientation. Such platforms allow sophisticated image/video processings [1], [2], [3]. Face detection, for example, is one of the processings.…”

Section: Introductionmentioning

confidence: 99%

Target Domain Adaptation for Face Detection in a Smart Camera Network with Peer-to-Peer Communications

Chen¹,

Lü²,

Sun³

et al. 2015

2015 IEEE Global Communications Conference (GLOBECOM)

View full text Add to dashboard Cite

With the fast advance of mobile chips technologies, a node in a smart camera network can afford sophisticated processing via on-board multicore CPUs and GPUs, e.g., face detection. The performance of a general purpose face detector, however, may degrade seriously under specific situations with unexpected challenges such as facial coverage or bad illumination. This degradation is due to the difference of probability distributions between training data and testing data, known as source data domain and target data domain, respectively. To better adapt a smart camera network to a specific situation, some form of target domain adaptation is needed, which usually requires both the source domain data and as much as possible target domain data at each node, which may strain storage capacity and bandwidth. In this paper, we propose an adaptation method which fuses the source specific hypotheses (SSHs) and target specific hypotheses (TSHs) -requiring only a pre-trained face detector and a few target data to be shared by peer-to-peer communications, thus relieving the storage and bandwidth constraints. The method uses the "accuracy-regularization" objective as the adaptation model, to fuse SSHs and TSHs, and tries to minimize the misclassification error on target data. With an existing frontal face detector, we conduct experiments to verify our algorithm, covering cases of video surveillance, extreme pose challenge, and different illumination spectra. Significant performance gains are observed with only dozens of target data in all the experiments, demonstrating the effectiveness of the proposed adaptation model. Therefore, the proposed adaption can be applied to a smart camera network with peer-to-peer communications to improve the network's overall face detection performance.

show abstract

MIDSCA: Towards a Smart Camera architecture of mobile internet devices

Cited by 6 publications

References 17 publications

Resource-aware architectures for particle filter based visual target tracking

Resource-aware architectures for particle filter based visual target tracking

Resource-aware architectures for adaptive particle filter based visual target tracking

Target Domain Adaptation for Face Detection in a Smart Camera Network with Peer-to-Peer Communications

Contact Info

Product

Resources

About