Deborah Estrin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Deborah Estrin has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Rahimi
Center for Embedded Networked Sensing, University of California, Los Angeles
3 shared publications - Hyungjin Kim
Dept. of Electr. Eng., Univ. of California, Los Angeles, CA
2 shared publications - John D. Villasenor
Univ Calif Los Angeles, Dept Elect Engn, Los Angeles, CA 90095 USA
2 shared publications - Mark Hansen
Center of Embedded Networked Sensors, Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA
2 shared publications - Nithya Ramanathan
Center for Embedded Networked Sensing, Department of Computer Sciences, University of California, Los Angeles, USA
2 shared publications - Teresa Ko
Center of Embedded Networked Sensors, Department of Computer Science, University of California at Los Angeles, Los Angeles, CA , USA
2 shared publications
Latest Publications
- Open Access
- 18 May 2011
- Published by Springer Nature in European Journal of Clinical Nutrition
- Vol. 65 (10) , 1156-1162
Feasibility testing of an automated image-capture method to aid dietary recall
Background/Objectives: The accuracy of dietary recalls might be enhanced by providing participants with photo images of foods they consumed during the test period. Subjects/Methods: We examined the feasibility of a system (Image-Diet Day) that is a user-initiated camera-equipped mobile phone that is programmed to automatically capture and transmit images to a secure website in conjunction with computer-assisted, multipass, 24-h dietary recalls in 14 participants during 2007. Participants used the device during eating periods on each of the three independent days. Image processing filters successfully eliminated underexposed, overexposed and blurry images. The captured images were accessed by the participants using the ImageViewer software while completing the 24-h dietary recall on the following day. Results: None of the participants reported difficulty using the ImageViewer. Images were deemed ‘helpful’ or ‘sort of helpful’ by 93% of participants. A majority (79%) of users reported having no technical problems, but 71% rated the burden of wearing the device as somewhat to very difficult, owing to issues such as limited battery life, self-consciousness about wearing the device in public and concerns about the field of view of the camera. Conclusion: Overall, these findings suggest that automated imaging is a promising technology to facilitate dietary recall. The challenge of managing the thousands of images generated can be met. Smaller devices with a broader field of view may aid in overcoming self-consciousness of the user with using or wearing the device.
- 18 May 2011
- Published by Springer Nature in European Journal of Clinical Nutrition
- Vol. 65 (10) , 1156-1162
Open AccessFeasibility testing of an automated image-capture method to aid dietary recall
Background/Objectives: The accuracy of dietary recalls might be enhanced by providing participants with photo images of foods they consumed during the test period. Subjects/Methods: We examined the feasibility of a system (Image-Diet Day) that is a user-initiated camera-equipped mobile phone that is programmed to automatically capture and transmit images to a secure website in conjunction with computer-assisted, multipass, 24-h dietary recalls in 14 participants during 2007. Participants used the device during eating periods on each of the three independent days. Image processing filters successfully eliminated underexposed, overexposed and blurry images. The captured images were accessed by the participants using the ImageViewer software while completing the 24-h dietary recall on the following day. Results: None of the participants reported difficulty using the ImageViewer. Images were deemed ‘helpful’ or ‘sort of helpful’ by 93% of participants. A majority (79%) of users reported having no technical problems, but 71% rated the burden of wearing the device as somewhat to very difficult, owing to issues such as limited battery life, self-consciousness about wearing the device in public and concerns about the field of view of the camera. Conclusion: Overall, these findings suggest that automated imaging is a promising technology to facilitate dietary recall. The challenge of managing the thousands of images generated can be met. Smaller devices with a broader field of view may aid in overcoming self-consciousness of the user with using or wearing the device.
- 5 November 2010
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 330 (6005) , 759-760
Open mHealth Architecture: An Engine for Health Care Innovation
Chronic diseases like diabetes, asthma, and obesity account for 46% of global disease burden (1). The traditional model of episodic care in clinic and hospital-based settings is suboptimal for improving chronic disease outcomes (2). Mobile communication devices, in conjunction with Internet and social media, present opportunities to enhance disease prevention and management by extending health interventions beyond the reach of traditional care—an approach referred to as mHealth (3). However, mHealth is emerging as a patchwork of incompatible applications (“apps”) serving narrow, albeit valuable, needs, and thus could benefit from more coordinated development (4). A public-private partnership to define and instantiate an “open” mHealth architecture (described below), in the context of economic incentives and enabling policies, could support medical discovery and evidence-based practice about managing and preventing chronic disease.
- 5 November 2010
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 330 (6005) , 759-760
Open mHealth Architecture: An Engine for Health Care Innovation
Chronic diseases like diabetes, asthma, and obesity account for 46% of global disease burden (1). The traditional model of episodic care in clinic and hospital-based settings is suboptimal for improving chronic disease outcomes (2). Mobile communication devices, in conjunction with Internet and social media, present opportunities to enhance disease prevention and management by extending health interventions beyond the reach of traditional care—an approach referred to as mHealth (3). However, mHealth is emerging as a patchwork of incompatible applications (“apps”) serving narrow, albeit valuable, needs, and thus could benefit from more coordinated development (4). A public-private partnership to define and instantiate an “open” mHealth architecture (described below), in the context of economic incentives and enabling policies, could support medical discovery and evidence-based practice about managing and preventing chronic disease.
- 16 September 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 98 (11) , 1934-1946
Embedded Imagers: Detecting, Localizing, and Recognizing Objects and Events in Natural Habitats
Imaging sensors, or “imagers,” embedded in the natural environment enable remote collection of large quantities of data, thus easing the design and deployment of sensing systems in a variety of application domains. Yet, the data collected from such imagers are difficult to interpret due to a variety of “nuisance factors” in the data formation process, such as illumination, vantage point, partial occlusions, etc. These are especially severe in natural environments, where the objects of interest (e.g., plants, animals) have evolved to blend with their habitat, exhibit complex variability in shape and appearance, and perform rapid motions against dynamic backgrounds with rapid illumination changes. We describe three applications that exemplify these problems and the solutions we developed. First, we show how temporal oversampling can simplify the analysis of a slow process such as the avian nesting cycle. Then, we show how to overcome temporal undersampling in order to detect birds at a feeder station. Finally, we show how to exploit temporal consistency to reliably detect pollinators as they visit flowers in the field.
- 16 September 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 98 (11) , 1934-1946
Embedded Imagers: Detecting, Localizing, and Recognizing Objects and Events in Natural Habitats
Imaging sensors, or “imagers,” embedded in the natural environment enable remote collection of large quantities of data, thus easing the design and deployment of sensing systems in a variety of application domains. Yet, the data collected from such imagers are difficult to interpret due to a variety of “nuisance factors” in the data formation process, such as illumination, vantage point, partial occlusions, etc. These are especially severe in natural environments, where the objects of interest (e.g., plants, animals) have evolved to blend with their habitat, exhibit complex variability in shape and appearance, and perform rapid motions against dynamic backgrounds with rapid illumination changes. We describe three applications that exemplify these problems and the solutions we developed. First, we show how temporal oversampling can simplify the analysis of a slow process such as the avian nesting cycle. Then, we show how to overcome temporal undersampling in order to detect birds at a feeder station. Finally, we show how to exploit temporal consistency to reliably detect pollinators as they visit flowers in the field.
- 23 September 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 2 (4) , 526-537
Energy-Aware High Resolution Image Acquisition via Heterogeneous Image Sensors
We present an energy-efficient high resolution image acquisition approach based on a two-tiered system comprising low-cost, low-power, non-actuated, extremely resource-constrained stereo image sensor platforms and more capable but more power-consumptive high resolution imaging platforms with actuation capability. The resource constrained platforms are used to compute 3D object location and subsequently to compute appropriate pan/tilt/zoom settings for the high resolution imaging platforms. The high resolution imaging platforms with actuation capability acquire high resolution images which can be utilized for various recognition purposes. We present a design methodology and system architecture, and evaluate latency and energy tradeoffs in the system. Experimental results show that use of the two-tiered network significantly reduces energy consumption of high resolution image acquisition versus a single-tiered network with minimum loss in detection capability.
- 23 September 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 2 (4) , 526-537
Energy-Aware High Resolution Image Acquisition via Heterogeneous Image Sensors
We present an energy-efficient high resolution image acquisition approach based on a two-tiered system comprising low-cost, low-power, non-actuated, extremely resource-constrained stereo image sensor platforms and more capable but more power-consumptive high resolution imaging platforms with actuation capability. The resource constrained platforms are used to compute 3D object location and subsequently to compute appropriate pan/tilt/zoom settings for the high resolution imaging platforms. The high resolution imaging platforms with actuation capability acquire high resolution images which can be utilized for various recognition purposes. We present a design methodology and system architecture, and evaluate latency and energy tradeoffs in the system. Experimental results show that use of the two-tiered network significantly reduces energy consumption of high resolution image acquisition versus a single-tiered network with minimum loss in detection capability.
- 1 May 2008
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 123 (5_Suppleme) , 3102
Experience with VoxNet: a rapidly-deployable acoustic monitoring system for bio-acoustic studies
Terrestrial bioacoustic census is a difficult problem because of propagation characteristics, obstructions, the diversity of bioacoustic sources, and the impact of noise. To address this problem we have developed VoxNet, a complete hardware and software platform for distributed acoustic monitoring applications. Each VoxNet node is a portable, self‐contained processor with a small four‐channel acoustic array. Using a distributed set of VoxNet nodes, a forested habitat can be monitored and the behavior of animals can be recorded and analyzed acoustically. In this work we present our experiences applying VoxNet to bioacoustic census. This work is based on data collected using the system during a deployment in Chiapas, Mexico at the Chajul Biological Field Station. The Chajul station is located in a region of dense rain forest and is home to Mexico's most diverse ecosystem. Using VoxNet in this harsh environment, we obtained census estimates based on observation of bird calls.
- 1 May 2008
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 123 (5_Suppleme) , 3102
Experience with VoxNet: a rapidly-deployable acoustic monitoring system for bio-acoustic studies
Terrestrial bioacoustic census is a difficult problem because of propagation characteristics, obstructions, the diversity of bioacoustic sources, and the impact of noise. To address this problem we have developed VoxNet, a complete hardware and software platform for distributed acoustic monitoring applications. Each VoxNet node is a portable, self‐contained processor with a small four‐channel acoustic array. Using a distributed set of VoxNet nodes, a forested habitat can be monitored and the behavior of animals can be recorded and analyzed acoustically. In this work we present our experiences applying VoxNet to bioacoustic census. This work is based on data collected using the system during a deployment in Chiapas, Mexico at the Chajul Biological Field Station. The Chajul station is located in a region of dense rain forest and is home to Mexico's most diverse ecosystem. Using VoxNet in this harsh environment, we obtained census estimates based on observation of bird calls.
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 313-320
Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks
Advances in DSP technology create important avenues of research for embedded vision. One such avenue is the investigation of tradeoffs amongst system parameters which affect the energy, accuracy, and latency of the overall system. This paper reports work on benchmarking the performance and cost of scale invariant feature transform (SIFT) for visual classification on a Blackfin DSP processor. Through measurements and modeling of the camera sensor node, we investigate system performance (classification accuracy, latency, energy consumption) in light of image resolution, arithmetic precision, location of processing (local vs. server-side), and processor speed. A case study on counting eggs during avian nesting season is used to experimentally determine the tradeoffs of different design parameters and discuss implications to other application domains.
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 313-320
Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks
Advances in DSP technology create important avenues of research for embedded vision. One such avenue is the investigation of tradeoffs amongst system parameters which affect the energy, accuracy, and latency of the overall system. This paper reports work on benchmarking the performance and cost of scale invariant feature transform (SIFT) for visual classification on a Blackfin DSP processor. Through measurements and modeling of the camera sensor node, we investigate system performance (classification accuracy, latency, energy consumption) in light of image resolution, arithmetic precision, location of processing (local vs. server-side), and processor speed. A case study on counting eggs during avian nesting season is used to experimentally determine the tradeoffs of different design parameters and discuss implications to other application domains.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 216-225
Energy-Optimized Image Communication on Resource-Constrained Sensor Platforms
Energy-efficient image communication is one of the most important goals for a large class of current and future sensor network applications. This paper presents a quantitative comparison between the energy costs associated with 1) direct transmission of uncompressed images and 2) sensor platform-based JPEG compression followed by transmission of the compressed image data. JPEG compression computations are mapped onto various resource-constrained sensor platforms using a design environment that allows computation using the minimum integer and fractional bit-widths needed in view of other approximations inherent in the compression process and choice of image quality parameters. Detailed experimental results examining the tradeoffs in processor resources, processing/transmission time, bandwidth utilization, image quality, and overall energy consumption are presented.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 216-225
Energy-Optimized Image Communication on Resource-Constrained Sensor Platforms
Energy-efficient image communication is one of the most important goals for a large class of current and future sensor network applications. This paper presents a quantitative comparison between the energy costs associated with 1) direct transmission of uncompressed images and 2) sensor platform-based JPEG compression followed by transmission of the compressed image data. JPEG compression computations are mapped onto various resource-constrained sensor platforms using a design environment that allows computation using the minimum integer and fractional bit-widths needed in view of other approximations inherent in the compression process and choice of image quality parameters. Detailed experimental results examining the tradeoffs in processor resources, processing/transmission time, bandwidth utilization, image quality, and overall energy consumption are presented.