Filters








26,196 Hits in 5.9 sec

A Focal Plane Architecture for Motion Computation

Miguel Arias-Estrada, Marc Tremblay, Denis Poussart
1996 Real-time imaging  
A new Focal Plane Architecture for Motion Computation is presented. The design is based on the Smart Sensor paradigm: combining transduction and early processing at sensor level.  ...  The approach developed for VLSI implementation offers an excellent combination of small pixel area and a computationally efficient method for image motion measurement.  ...  Acknowledgments Research on computational sensors for motion is supported by Project MS-4 of the Institute of Robotics and Intelligent Systems of Canada.  ... 
doi:10.1006/rtim.1996.0036 fatcat:5xv7frizlra3hlkrpoxzx6qwy4

A Spatial-Temporal Multiresolution CMOS Image Sensor With Adaptive Frame Rates for Tracking the Moving Objects in Region-of-Interest and Suppressing Motion Blur

Jaehyuk Choi, Sang-Wook Han, Seong-Jin Kim, Sun-Il Chang, Euisik Yoon
2007 IEEE Journal of Solid-State Circuits  
This image sensor simultaneously generates two outputs: one for normal images ( 30 fps) of stationery background and the other for adaptable frame-rate images (over 960 fps) of moving objects.  ...  In this paper, we report a CMOS image sensor for spatial-temporal multiresolution images.  ...  In this paper, we report a multiresolution CMOS imager which can provide an adaptive spatial-temporal multiresolution for the specific ROI that is autonomously determined from motion detection.  ... 
doi:10.1109/jssc.2007.908716 fatcat:234aifupebdwheidl74lapf7c4

Special Issue on Video Analysis on Resource-Limited Systems

Rama Chellappa, Andrea Cavallaro, Ying Wu, Caifeng Shan, Yun Fu, Kari Pulli
2011 IEEE transactions on circuits and systems for video technology (Print)  
Acknowledgment We have many people to thank for their contributions to this special issue. We would like to thank all of the authors for submitting their papers to this special issue.  ...  Gharavi, for his constant support and guidance throughout the entire process that has led to the publication of this special issue.  ...  In the paper entitled "Adaptive Sampling for Feature Detection, Tracking and Recognition on Mobile Platforms" by Ebrahimi and Mayol-Cuevas, adaptive sampling is used to speed up local feature detection  ... 
doi:10.1109/tcsvt.2011.2165795 fatcat:x2ttfo4uybhzlpy4zjatwf763q

N-queens-based algorithm for moving object detection in distributed wireless sensor networks

Biljana Stojkoska, Danco Davcev, Trajkovik Vladimir
2008 ITI 2008 - 30th International Conference on Information Technology Interfaces  
Our algorithm is very suitable for intruder detection applications. Each node is responsible for processing the image captured by the video sensor, which consists of NxN blocks.  ...  If an intruder is detected in the monitoring region, the node will transmit the image for further processing. Otherwise, the node takes no action.  ...  We apply a similar idea as a technique for motion detection.  ... 
doi:10.1109/iti.2008.4588530 dblp:conf/iti/StojkoskaDV08 fatcat:hbfpnq6qznd7xd3gbe5k526hvu

N-Queens-based Algorithm for Moving Object Detection in Distributed Wireless Sensor Networks

Biljana L. Stojkoska, Danco P. Davcev, Vladimir Trajkovik
2008 Journal of Computing and Information Technology  
Our algorithm is very suitable for intruder detection applications. Each node is responsible for processing the image captured by the video sensor, which consists of NxN blocks.  ...  If an intruder is detected in the monitoring region, the node will transmit the image for further processing. Otherwise, the node takes no action.  ...  We apply a similar idea as a technique for motion detection.  ... 
doi:10.2498/cit.1001401 fatcat:dofbr4uqefaztoiivc5dzagvvm

Adaptive space-time structural coherence for selective imaging

David Gibson, Neill Campbell
2017 2017 Conference on Design and Architectures for Signal and Image Processing (DASIP)  
The close-tosensor design combined with state-of-the-art image sensors enables a wide field of view to be analysed for changes using on-sensor image sub-sampling.  ...  As whole images do not exist and compute resources are limited, motion estimation has to be applied to sub-sampled ROI in an efficient online manner.  ... 
doi:10.1109/dasip.2017.8122126 dblp:conf/dasip/GibsonC17 fatcat:zplbhlcqpnfnxhsdi5nf4sotui

Event triggered intelligent video recording system using MS-SSIM for smart home security

Haitham Abbas Khalaf, A.S. Tolba, M.Z. Rashid
2016 Ain Shams Engineering Journal  
Motion detection for initiation of the recording process is based on an enhanced Multi-Scale Structural Similarity detection technique.  ...  Sensors collaborate for identification of the area to be monitored and the events which are to be recorded.  ...  The interaction between defect size and image resolution is also an important factor. Therefore, using the MS-SSIM metric renders itself a good adaptive measure for motion detection.  ... 
doi:10.1016/j.asej.2016.10.001 fatcat:ei2b5qtwxfekpbgq54zomhvmye

Video enhancement on an adaptive image sensor

Maria E. Angelopoulou, Christos-Savvas Bouganis, Peter Y. K. Cheung
2008 2008 15th IEEE International Conference on Image Processing  
In particular, a super-resolution and a deconvolution-based approach, for motion deblurring on an adaptive image sensor, are proposed, compared and evaluated.  ...  The high density pixel sensors of the latest imaging systems provide images with high resolution, but require long exposure times, which limit their applicability due to the motion blur effect.  ...  Fig. 1 . 1 SR-based motion-deblurring on an adaptive image sensor. Fig. 2 . 2 (a) Deconvolution-based motion-deblurring on an adaptive image sensor.  ... 
doi:10.1109/icip.2008.4711846 dblp:conf/icip/AngelopoulouBC08 fatcat:y67gewtlcbhrxhlzhnv7bbup24

A Spatial-Temporal Multi-Resolution CMOS Image Sensor with Adaptive Frame Rates for Moving Objects in the Region-of-Interest

Jaehyuk Choi, Sang-Wook Han, Seong-Jin Kim, Sun-II Chang, Euisik Yoon
2007 Digest of technical papers / IEEE International Solid-State Circuits Conference  
The signal is sampled by one of the CDS/ADC blocks. The switches are in position N for normal image capture and R for the ROI. Figure 28.2.3 shows the operating procedures for motion detection.  ...  However, high frame-rate images of high spatial resolution require a large bandwidth and large power consumption, which is not feasible for bandwidth-limited applications such as wireless sensor networks  ...  However, high frame-rate images of high spatial resolution require a large bandwidth and large power consumption, which is not feasible for bandwidth-limited applications such as wireless sensor networks  ... 
doi:10.1109/isscc.2007.373514 dblp:conf/isscc/ChoiHKCY07 fatcat:rizklqoefnc6hkwvdhfydk5kea

A CMOS image sensor with on-chip motion detection and object localization

Bo Zhao, Xiangyu Zhang, Shoushun Chen
2011 2011 IEEE Custom Integrated Circuits Conference (CICC)  
This paper presents a 64x64 CMOS image sensor with on-chip moving objects detection and localization capability.  ...  The proposed image sensor has been implemented using UMC 0.18 f.Lm CMOS technology with a die area of l.Sx1.S mm2• The power consumption was measured to only 0.4 mW at 100 FPS.  ...  Motion Detection The image sensor consists of a 64 x64 pixel array, each pixel is equipped with an analog memory (capacitor), the whole Algorithm 1 Procedure for event clustering 1) Check the number of  ... 
doi:10.1109/cicc.2011.6055400 dblp:conf/cicc/ZhaoZC11 fatcat:27c7ylkmvjc3jgi53otgf5gpem

An adaptive framework for image and video sensing

Lior Zimet, Morteza Shahram, Peyman Milanfar, Nitin Sampat, Jeffrey M. DiCarlo, Ricardo J. Motta
2005 Digital Photography  
In this paper we outline a framework for an adaptive sensor where the spatial and temporal sampling rates are adapted to the scene.  ...  With bandwidth limitations inherent to any sensor, there is clearly a tradeoff between spatial and temporal sampling rates, which can be studied, and which present-day sensors do not exploit.  ...  A second sensor acquires the image in high spatial sampling rate and uses the motion information from the first sensor to deblur the image.  ... 
doi:10.1117/12.587417 dblp:conf/dphoto/ZimetSM05 fatcat:u3f44eigcbga3gztc4rblnj4za

TinyMotion

Jingtao Wang, John Canny
2006 CHI '06 extended abstracts on Human factors in computing systems - CHI EA '06  
This paper presents TinyMotion, a pure software approach that detects the movements of cell phones in real time by analyzing image sequences captured by the built-in camera.  ...  In contrast to earlier work, TinyMotion does not require additional sensors, special scenes or backgrounds and can run on today's main-stream camera phones without hardware modification.  ...  We also thank Qualcomm Corp. for their support in funding and equipment.  ... 
doi:10.1145/1125451.1125526 dblp:conf/chi/WangC06 fatcat:snwcqp36qzfwroaa4646ndmvku

Distributed mixed-signal architecture for programmable smart image sensors

Juliette Le Hir, Anthony Kolar, Filipe Vinci Dos Santos
2018 Analog Integrated Circuits and Signal Processing  
Keywords-Smart image sensor, vision system on a chip (VSoC), focal-plane array, algorithm-architecture matching, mixed analogdigital electronics.  ...  Smart vision systems on a chip are promising for embedded applications.  ...  In short, smart vision sensors currently perform one or several simple tasks such as: edge and/or motion detection [7] , edge detection, high dynamic range and tracking [16] , motion detection or low  ... 
doi:10.1007/s10470-018-1342-y fatcat:zdhhmpysengenkls75es5oy3zu

Distributed mixed-signal architecture for programmable smart image sensors

Juliette Le Hir, Anthony Kolar, Filipe Vinci Dos Santos
2017 2017 15th IEEE International New Circuits and Systems Conference (NEWCAS)  
Keywords-Smart image sensor, vision system on a chip (VSoC), focal-plane array, algorithm-architecture matching, mixed analogdigital electronics.  ...  Smart vision systems on a chip are promising for embedded applications.  ...  In short, smart vision sensors currently perform one or several simple tasks such as: edge and/or motion detection [7] , edge detection, high dynamic range and tracking [16] , motion detection or low  ... 
doi:10.1109/newcas.2017.8010178 dblp:conf/newcas/HirKS17 fatcat:thr3xpjyj5dwrnvx6vm25ok4q4

Enhancing Case-Based Retrieval Engine with Case Retrieval Nets for Humanoid Robot Motion Controller

Meteb M. Altaf, Bassant M. El Bagoury, Fahad Alraddady, Said Ghoniemy
2015 International Journal of Machine Learning and Computing  
of the case-memory.  ...  Moreover, Motion Controlling for Humanoid Robot is a very complex problem.  ...  The Case-Memory NAO humanoid robot has ten sensors, one distance sensor for measuring distance, eight force sensors, four in each foot and one accelerometer sensor for measuring acceleration.  ... 
doi:10.7763/ijmlc.2015.v5.513 fatcat:573apixcpfc3torzjnc5fckxcu
« Previous Showing results 1 — 15 out of 26,196 results