INTRODUCTIONSurveillance is one of the promising applications to which smart Distributed smart cameras have received increased focus in the camera motes forming a vision-enabled network can add research community over the past several months. The notion of increasing levels of intelligence. We see a high degree of in-node cameras combined with embedded computation power and processing in combination with distributed reasoning algorithms interconnected through radio links opens up a new realm of as the key enablers for such intelligent surveillance systems. To intelligent vision-enabled applications. Real-time image put these systems into practice still requires a considerable processing and distributed reasoning made possible by smart amount of research ranging from mote architectures, pixelcameras can not only enhance existing applications but also processing algorithms, up to distributed reasoning engines. This motivate new applications. Potential application areas range from paper introduces MeshEye, an energy-efficient smart camera home monitoring, elderly care, and smart environments to mote architecture that has been designed with intelligent security and surveillance in public or corporate buildings. Critical surveillance as the target application in mind. Special attention is issues influencing the success of smart camera deployments for given to MeshEye's unique vision system: a low-resolution stereo such applications include reliable and robust operation with as vision system continuously determines position, range, and size of little maintenance as possible. moving objects entering its field of view. This information triggers a color camera module to acquire a high-resolution image ncmpaisonito alar sensors, shsm r e pess sub-array cotinn th obet whic ca.eefiinl humidity, velocity, and acceleration sensors, vision sensors pub-arocessedainysubseq stae I t offer redced complextly generate much higher bandwidth data due to the two-dimensional processed in subsequent stages. It offers reduced complexity, naueothipxlary.Tesermutofawda response~~~~~~~tie.n oe osmto vrcnetoa nature of their pixel array. The sheer amount of raw data soons. Bic vnd aorith or obec detecntional generated precludes it from human analysis in many applications. aquition. Ban trcion ar desribed and illustratedtonrHence distributed intelligent algorithms supported by in-node world data. The paper alsoprsents a. basicpo er odelt image processing are required to successfully operate scalable networks of wireless smart cameras. We see the combination of estimates lifetime of our smart camera mote in battery-powered local processing and distributed reasoning as the key challenge in operation for intelligent surveillance event processing. making intelligent vision-enabled applications a reality. As outlined in [1]-[3], local processing calls for adequate low-level
Recognizing activities in a home environment is challenging due to the variety of activities that can be performed at home and the complexity of the environment. Multiple cameras are usually needed to cover the whole observation area. This adds camera fusion as another challenge to activity recognition. We propose a hierarchical approach that recognizes both coarse-level and fine-level activities, in which different image features and learning methods are used for different activities based on their characteristics. The paper focuses on discussing the second-level of activity recognition with spatio-temporal features. Specifically, three fusion approaches for multiview activity recognition with spatiotemporal features are presented, including two decision fusion methods and one feature fusion method. They are comparatively analyzed in terms of their tradeoffs on assumptions on system setup, model transferability and recognition rate. Experiments show that challenging activities with subtle motions such as eating, cutting, scrambling, typing, reading etc. can be recognized with our approaches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.