Search

Background The myelin sheath produced by glial cells insulates the axons, and supports the function of the nervous system. Myelin sheath degeneration causes neurodegenerative disorders, such as multiple sclerosis (MS). There are no therapies for MS that promote remyelination. Drug discovery frequently involves screening thousands of compounds. However, this is not feasible for remyelination drugs, since myelin quantification is a manual labor-intensive endeavor. Therefore, the development of assistive software for expedited myelin detection is instrumental for MS drug discovery by enabling high-content image-based drug screens. New method In this study, we developed a machine learning based expedited myelin detection approach in fluorescence microscopy images. Multi-channel three-dimensional microscopy images of a mouse stem cell-based myelination assay were labeled by experts. A spectro-spatial feature extraction method was introduced to represent local dependencies of voxels both in spatial and spectral domains. Feature extraction yielded two data set of over forty-seven thousand annotated images in total. Results Myelin detection performances of 23 different supervised machine learning techniques including a customized-convolutional neural network (CNN), were assessed using various train/test split ratios of the data sets. The highest accuracy values of 98.84 ± 0.09 % and 98.46 ± 0.11 % were achieved by Boosted Trees and customized-CNN, respectively. Comparison with existing methods Our approach can detect myelin in a common experimental setup. Myelin extending in any orientation in 3 dimensions is segmented from 3 channel z-stack fluorescence images. Conclusions Our results suggest that the proposed expedited myelin detection approach is a feasible and robust method for remyelination drug screening.

Date of Conference: 30 November - 3 December 2020 Conference name: 12th International Conference on Computational Collective Intelligence, ICCCI 2020 Real-time flame detection is crucial in video-based surveillance systems. We propose a vision-based method to detect flames using Deep Convolutional Generative Adversarial Neural Networks (DCGANs). Many existing supervised learning approaches using convolutional neural networks do not take temporal information into account and require a substantial amount of labeled data. To have a robust representation of sequences with and without flame, we propose a two-stage training of a DCGAN exploiting spatio-temporal flame evolution. Our training framework includes the regular training of a DCGAN with real spatio-temporal images, namely, temporal slice images, and noise vectors, and training the discriminator separately using the temporal flame images without the generator. Experimental results show that the proposed method effectively detects flame in video with negligible false-positive rates in real-time. A. Enis Çetin’s research is partially funded by NSF with grant number 1739396 and NVIDIA Corporation. B. Uğur Töreyin’s research is partially funded by TÜBİTAK 114E426, İTÜ BAP MGA-2017-40964 and MOA-2019-42321.

Myelin sheath, wrapped around axons, allows rapid neural signal transmission, and degeneration of myelin causes various neurodegenerative diseases, such as, Multiple Sclerosis (MS). For candidate drug discovery, it is essential to quantify myelin. This requires tedious expert labor comprising myelin labelling on microscopic fluorescence images, usually acquired by confocal microscopes. In this study, semantic segmentation based automatic myelin segmentation on fluorescence microscopy images was introduced. Three-channel and three-dimensional fluorescence images of mouse stem cell derived neuron and oligodendrocyte co-cultures were labeled by an expert. The images were divided into patches for training and the labels corresponded to each patch were acquired. A data set of 11552 patches was used for training to identify myelin and non-myelin regions. In the data set, myelin detection performances of semantic segmentation technique were evaluated using 3 different learning algorithms. The highest accuracy value of 97.32 percent was achieved by using “RMSprop” learning algorithm with a group size of 8 and after 250 epochs. Results suggested that the proposed myelin segmentation method was suitable for detecting myelin. Thus, the outlined myelin segmentation method has the potential to be incorporated into remyelination drug screens.

Date of Conference: 12-17 May 2019 Conference Name: 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 Early detection of wildfire smoke in real-time is essentially important in forest surveillance and monitoring systems. We propose a vision-based method to detect smoke using Deep Convolutional Generative Adversarial Neural Networks (DC-GANs). Many existing supervised learning approaches using convolutional neural networks require substantial amount of labeled data. In order to have a robust representation of sequences with and without smoke, we propose a two-stage training of a DCGAN. Our training framework includes, the regular training of a DCGAN with real images and noise vectors, and training the discriminator separately using the smoke images without the generator. Before training the networks, the temporal evolution of smoke is also integrated with a motion-based transformation of images as a pre-processing step. Experimental results show that the proposed method effectively detects the smoke images with negligible false positive rates in real-time. The Institute of Electrical and Electronics Engineers Signal Processing Society

In this paper, we propose image analysis based methods for estimating fish tail beat frequency, which is an indicator of fish energy consumption at fish passage structures. For this purpose, average magnitude difference and autocorrelation function based periodicity detection techniques are utilized. Actual fish images are acquired using a visible range camera installed in a brush type fish pass in Ikizdere River, near Rize, Turkey, which is very rich in biodiversity. Results show that image analysis based periodicity detection methods can be used for fishway efficiency evaluation purposes. To the best of authors' knowledge, this is the first study that automatically estimates fish tail beat frequency using image analysis. The findings of this study are expected to have implications for fish monitoring and fishway design.

This study proposes a unique approach to classify CerbB2 tumor cell scores in breast cancer based on deep learning models. Another contribution of the study is the creation of a dataset from original breast cancer tissues. On the purpose of training, validating and testing with deep learning models cell fragments were generated from sample tissue images. CerbB2 tumor scores were generated for the cell fragments were classified with high performance by the aid of convolutional neural networks (CNN).

Cataloged from PDF version of article. This is a review article describing the recent developments in Video based Fire Detection (VFD). Video surveillance cameras and computer vision methods are widely used in many security applications. It is also possible to use security cameras and special purpose infrared surveillance cameras for fire detection. This requires intelligent video processing techniques for detection and analysis of uncontrolled fire behavior. VFD may help reduce the detection time compared to the currently available sensors in both indoors and outdoors because cameras can monitor “volumes” and do not have transport delay that the traditional “point” sensors suffer from. It is possible to cover an area of 100 km2 using a single pan-tiltzoom camera placed on a hilltop for wildfire detection. Another benefit of the VFD systems is that they can provide crucial information about the size and growth of the fire, direction of smoke propagation. © 2013 Elsevier Inc. All rights reserved

Hyperspectral data is composed of a set of correlated band images. In order to efficiently compress the hyperspectral imagery, this inherent correlation may be exploited by means of spectral decorrelators. In this paper, a fractional wavelet transform based method is introduced for spectral decorrelation of hyperspectral data. As opposed to regular wavelet transform which decomposes a given signal into two equal-length sub-signals, fractional wavelet transform is carried out by decomposing the signal corresponding to the spectral content into two sub-signals with different lengths. Sub-signal lengths are adapted to data to achieve a better spectral decorrelation. Performance results pertaining to AVIRIS datasets are presented in comparison with existing regular wavelet decomposition based compression methods.

The final step of the bearing production line constitutes the inspection of the bearing which is mostly performed by visual inspection. Three groups of bearings namely, properly assembled samples, conversely assembled rubber seal and samples where rubber seals were missing are classified using visible range images of these samples. According to the proposed method, extraction of seal regions from the bearing images using circular Hough transform is followed by a higher-order statistical analysis to finalize the classification. Experimental results show that this system may be employed as an assistive tool for bearing inspectors.

Sparse coding based compression of hyperspectral imagery yields better rate-distortion performance especially for low bit-rates when compared with other state-of-the-art methods in the literature. In this paper, an on-line dictionary learning based lossy compression method is proposed yielding even a better rate-distortion performance, thanks to the spectral decorrelation achieved by the Haar wavelet transform. The hyperspectral data is decorrelated in the spectral dimension using a single-level Haar transform which is followed by a dictionary learning step over the low-subband data. The higher subband is further compressed in a lossless manner using JPEG2000. Rate-distortion results are obtaind for AVIRIS hyperspectral data. Results indicate that the spectral decorrelation coupled with sparse dictionary learning of low-subband images yield superior performance over existing hyperspectral data compression schemes.

In this paper, a video based algorithm for fire and flame detection is developed. In addition to ordinary motion and color clues, flame flicker is distinguished from motion of flame colored moving objects using Markov models. Irregular nature of flame boundaries is detected by performing temporal wavelet analysis using Hidden Markov Models as well. Color variations in fire is detected by computing the spatial wavelet transform of moving fire-colored regions. Boundary of flames are represented in wavelet domain and irregular nature of the boundaries of fire regions is also used as an indication of the flame flicker. Decisions from sub-algorithms are linearly combined using an adaptive active fusion method. The main detection algorithm is composed of four sub-algorithms (i) detection of fire colored moving objects, (ii) temporal, and (iii) spatial wavelet analysis for flicker detection and (iv) contour analysis of fire colored region boundaries. Each algorithm yields a continuous decision value as a real number in the range [-1, 1] at every image frame of a video sequence. Decision values from sub-algorithms are fused using an adaptive algorithm in which weights are updated using the least mean square (LMS) method in the training (learning) stage.

A hyperspectral image compression method is proposed using an online dictionary learning approach. The online learning mechanism is aimed at utilizing least number of dictionary elements for each hyperspectral image under consideration. In order to meet this “sparsity constraint”, basis pursuit algorithm is used. Hyperspectral imagery from AVIRIS datasets are used for testing purposes. Effects of non-zero dictionary elements on the compression performance are analyzed. Results indicate that, the proposed online dictionary learning algorithm may be utilized for higher data rates, as it performs better in terms of PSNR values, as compared with the state-of-the-art predictive lossy compression schemes.

A lossy hyperspectral image compression method is proposed using online learning based sparse coding. The least number of coefficients are obtained to represent hyperspectral images by applying the sparse coding algorithm which is based on a dicriminative online dictionary learning method. Results indicate that a pre-analysis of the number of non-zero dictionary elements may help in improving the overall compression quality.

Cataloged from PDF version of article. In many surveillance systems the video is stored in wavelet compressed form.In this paper, an algorithm for moving object and region detection in video which is compressed using a wavelet transform (WT) is developed.The algorithm estimates the WT of the background scene from the WTs of the past image frames of the video.The WT of the current image is compared with the WT of the background and the moving objects are determined from the difference.The algorithm does not perform inverse WT to obtain the actual pixels of the current image nor the estimated background. This leads to a computationally efficient method and a system compared to the existing motion estimation methods. (C) 2005 Published by Elsevier B.V.

The goal of Ambient Assisted Living (AAL) research is to improve the quality of life of the elderly and handicapped people and help them maintain an independent lifestyle with the use of sensors, signal processing and telecommunications infrastructure. Unusual human activity detection such as fall detection has important applications. In this paper, a fall detection algorithm for a low cost AAL system using vibration and passive infrared (PIR) sensors is proposed. The single-tree complex wavelet transform (ST-CWT) is used for feature extraction from vibration sensor signal. The proposed feature extraction scheme is compared to discrete Fourier transform and mel-frequency cepstrum coefficients based feature extraction methods. Vibration signal features are classified into ''fall'' and ''ordinary activity'' classes using Euclidean distance, Mahalanobis distance, and support vector machine (SVM) classifiers, and they are compared to each other. The PIR sensor is used for the detection of a moving person in a region of interest. The proposed system works in real-time on a standard personal computer.

Date of Conference: 5-8 Sept. 2011 Spectrum sensing is one of the most essential characteristics of cognitive radios (CRs). Robustness and adaptation to varying wireless propagation scenarios without compromising the sensing accuracy are desirable features of any spectrum sensing method to be deployed in CR systems. In this study, an online adaptive cooperation technique for spectrum sensing is proposed in order to maintain the level of reliability and performance. Cooperation is achieved by sensors which employ energy detection. These sensors send their output to a center where data fusion operation is carried out in an online and adaptive manner. Adaptation is realized by the use of orthogonal projections onto convex sets (POCS). In conjunction with the proposed method, an end-to-end methodology for a flexible experimental setup is also proposed in this study. This setup is arranged to emulate the proposed adaptive cooperation scheme for spectrum sensing and validate its practical use in cognitive radio systems. Comparative performance results for both inphase and quadrature branches are presented. © 2011 IEEE.

A Pyro-electric Infrared (FIR) sensor based flame detection system is proposed using a Markovian decision algorithm. A differential PIR sensor is only sensitive to sudden temperature variations within its viewing range and it produces a time-varying signal. The wavelet transform of the FIR sensor signal is used for feature extraction from sensor signal and wavelet parameters are fed to a set of Markov models corresponding to the flame flicker process of an uncontrolled fire, ordinary activity of human beings and other objects. The final decision is reached based on the model yielding the highest probability among others. Comparative results show that the system can be used for fire detection in large rooms. (c) 2012 Elsevier Ltd. All rights reserved.

Date of Conference: 8-11 May 2011 Conference name: 18th International Conference on Telecommunications, 2011 Cooperative spectrum sensing methods in the literature assume a static communication scenario with fixed channel and propagation environment characteristics. In order to maintain the level of sensing reliability and performance under changing channel and environment conditions, in this study, an online adaptive cooperation scheme is proposed. Energy detection data from each cooperating sensor are fused together by an adaptive weighted linear combination at the fusion center. Weight update operation is performed online through the use of orthogonal projections onto convex sets (POCS). Also, in this paper, an end-to-end methodology for a flexible experimental setup is proposed. This setup is specifically deployed to emulate the proposed adaptive cooperation scheme for spectrum sensing and validate its practical use in cognitive radio systems. © 2011 IEEE.

Spectrum sensing is one of the most important features of Cognitive Radio (CR) systems. Matched-filter based spectrum sensing techniques provide optimum sensing performance given that a number of characteristics of the transmitted signal are known by the sensors. Assuming that the received signal pertains to one communication standard from a given set of wireless technologies, conventional spectrum sensors employ separate filters corresponding to each standard which gives rise to increased power consumption and ciruit size. A novel reconfigurable matched-filter based spectrum sensor to be deployed in CR systems is proposed in order to overcome the disadvantages of conventional design methods. This approach proposes a spectrum of design qualities which trade-off area for reconfiguration overhead. We will show that our approach is capable of designing reconfigurable filter for standards with widely varying filter characteristics.

Date of Conference: 20-22 April 2011 Conference Name: 19th Signal Processing and Communications Applications Conference, SIU 2011 In this paper, an online Adaptive Decision Fusion (ADF) framework is proposed for the central spectrum awareness engine of a spectrum sensor network in Cognitive Radio (CR) systems. Online learning approaches are powerful tools for problems where drifts in concepts take place. Cooperative spectrum sensing in cognitive radio networks is such a problem where channel characteristics and utilization patterns change frequently. The importance of this problem stems from the requirement that secondary users must adjust their frequency utilization strategies in such a way that the communication performance of the primary users would not be degraded by any means. In the proposed framework, sensing values from several sensor nodes are fused together by weighted linear combination at the central spectrum awareness engine. The weights are updated on-line according to an active fusion method based on performing orthogonal projections onto convex sets describing power reading values from each sensor. The proposed adaptive fusion strategy for cooperative spectrum sensing can operate independent from the channel type between the primary user and secondary users. Results of simulations and experiments for the proposed method conducted in laboratory are also presented. © 2011 IEEE.

Date of Conference: 14-19 March 2010 In this paper, we propose a novel method for detecting and monitoring Volatile Organic Compounds (VOC) gas leaks by using a Pyro-electric (or Passive) Infrared (PIR) sensor whose spectral range intersects with the absorption bands of VOC gases. A continuous time analog signal is obtained from the PIR sensor. This signal is discretized and analyzed in real time. Feature parameters are extracted in wavelet domain and classified using a Markov Model (MM) based classifier. Experimental results are presented. ©2010 IEEE.

Cataloged from PDF version of article. There has been an increasing interest in the study of video based fire detection algorithms as video based surveillance systems become widely available for indoor and outdoor monitoring applications. A novel method explicitly developed for video based detection of wildfires at night (in the dark) is presented in this paper. The method comprises four sub-algorithms: (i) slow moving video object detection, (ii) bright region detection, (iii) detection of objects exhibiting periodic motion, and (iv) a sub-algorithm interpreting the motion of moving regions in video. Each of these sub-algorithms characterizes an aspect of fire captured at night by a visible range PTZ camera. Individual decisions of the sub-algorithms are combined together using a least-mean-square (LMS) based decision fusion approach, and fire/nofire decision is reached by an active learning method. (C) 2009 Elsevier Ltd. All rights reserved

Date of Conference: 9-11 April 2009 Conference Name: IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009 There has been increasing interest in the study of video based fire detection as video based surveillance systems become widely available for indoor and outdoor monitoring applications. Video based fire detection methods in computer vision literature do not take into account whether the fire takes place in the day time or at night. A novel method explicitly developed for video based detection of fire at night (in the dark) is presented in this paper. The method comprises three sub-algorithms each of which characterizes certain part of fire at night. Individual decisions of the sub-algorithms are combined together using a least-mean-square based decision fusion approach.

Date of Conference: 13-17 April, 2009 Conference name: SPIE Defense, Security, and Sensing - Acquisition, Tracking, Pointing, and Laser Systems Technologies XXIII Shadows constitute a problem in many moving object detection and tracking algorithms in video. Usually, moving shadow regions lead to larger regions for detected objects. Shadow pixels have almost the same chromaticity as the original background pixels but they only have lower brightness values. Shadow regions usually retain the underlying texture, surface pattern, and color value. Therefore, a shadow pixel can be represented as a.x where x is the actual background color vector in 3-D RGB color space and a is a positive real number less than 1. In this paper, a shadow detection method based on two-dimensional (2-D) cepstrum is proposed. © 2009 SPIE.

Date of Conference: 19-24 April 2009 Conference name: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing A computer vision based algorithm for wildfire detection is developed. The main detection algorithm is composed of four sub-algorithms detecting (i) slow moving objects, (ii) gray regions, (iii) rising regions, and (iv) shadows. Each algorithm yields its own decision as a real number in the range [-1,1] at every image frame of a video sequence. Decisions from subalgorithms are fused using an adaptive algorithm. In contrast to standard Weighted Majority Algorithm (WMA), weights are updated using the Least Mean Square (LMS) method in the training (learning) stage. The error function is defined as the difference between the overall decision of the main algorithm and the decision of an oracle, who is the security guard of the forest look-out tower. ©2009 IEEE.

Chapter 6 It is now possible to install cameras monitoring sensitive areas but it may not be possible to assign a security guard to each camera or a set of cameras. In addition, security guards may get tired and watch the monitor in a blank manner without noticing important events taking place in front of their eyes. Current CCTV surveillance systems are mostly based on video and recently intelligent video analysis systems capable of detecting humans and cars were developed for surveillance applications. Such systems mostly use Hidden Markov Models (HMM) or Support Vector Machines (SVM) to reach decisions. They detect important events but they also produce false alarms. It is possible to take advantage of other low cost sensors including audio to reduce the number of false alarms. Most video recording systems have the capability of recording audio as well. Analysis of audio for intelligent information extraction is a relatively new area. Automatic detection of broken glass sounds, car crash sounds, screams, increasing sound level at the background are indicators of important events. By combining the information coming from the audio channel with the information from the video channels, reliable surveillance systems can be built. In this chapter, current state of the art is reviewed and an intelligent surveillance system analyzing both audio and video channels is described.

Date of Conference: 09 - 11 July, 2007 Conference name: CIVR '07 Proceedings of the 6th ACM international conference on Image and video retrieval Visual surveillance and activity analysis is an active research field of computer vision. As a result, there are several different algorithms produced for this purpose. To obtain more robust systems it is desirable to integrate the different algorithms. To help achieve this goal, we propose a flexible, distributed software collaboration framework and present a prototype system for automatic event analysis. Copyright 2007 ACM.

Date of Conference: 11-13 June 2007 Conference Name: 15th Signal Processing and Communications Applications, IEEE 2007 A method for detection of dynamic textures in video is proposed. It is observed that the motion vectors of most of the dynamic textures (e.g. sea waves, swaying tree leaves and branches in the wind, etc.) exhibit random motion. On the other hand, regular motion of ordinary video objects has well-defined directions. In this paper, motion vectors of moving objects are estimated and tracked based on a minimum distance based metric. The direction of the motion vectors are then quantized to define two threestate Markov models corresponding to dynamic textures and ordinary moving objects with consistent directions. Hidden Markov Models (HMMs) are used to classify the moving objects in the final step of the algorithm.

Conference name: 2006 IEEE International Symposium on Circuits and Systems Date of Conference: 21-24 May 2006 A method for detection of tree branches and leaves in video is proposed. It is observed that the motion vectors of tree branches and leaves exhibit random motion. On the other hand regular motion of green colored objects has well-defined directions. In this paper, the wavelet transform of motion vectors are computed and objects are classified according to the wavelet coefficients of motion vectors. Color information is also used to reduce the search space in a given image frame of the video. Motion trajectories of moving objects are modeled as Markovian processes and Hidden Markov Models (HMMs) are used to classify the green colored objects in the final step of the algorithm. © 2006 IEEE.

In this paper we present an instance based machine learning algorithm and system for real-time object classification and human action recognition which can help to build intelligent surveillance systems. The proposed method makes use of object silhouettes to classify objects and actions of humans present in a scene monitored by a stationary camera. An adaptive background subtract-tion model is used for object segmentation. Template matching based supervised learning method is adopted to classify objects into classes like human, human group and vehicle; and human actions into predefined classes like walking, boxing and kicking by making use of object silhouettes.

In this paper, an algorithm for moving region detection in compressed video is developed. It is assumed that the video can be compressed either using the Discrete Cosine Transform (DCT) or the Wavelet Transform (WT). The method estimates the WT of the background scene from the WTs of the past image frames of the video. The WT of the current image is compared with the WT of the background and the moving objects are determined from the difference. The algorithm does not perform inverse WT to obtain the actual pixels of the current image nor the estimated background. In the case of DCT compressed video, the DC values of 8 by 8 image blocks of Y, U and V channels are used for estimating the background scene. This leads to a computationally efficient method and a system compared to the existing motion detection methods.

Date of Conference: 11-13 June 2007 Conference Name: 15th Signal Processing and Communications Applications, IEEE 2007 Falls are one of the most important problems for frail and elderly people living independently. Early detection of falls is vital to provide a safe and active lifestyle for elderly. In this paper, signals produced by sound and passive infrared (PIR) sensors are simultaneously analyzed to detect suddenly falling elderly people. A typical room in a supportive home can be equipped with sound and PIR sensors. Hidden Markov models are trained for regular and unusual activities of an elderly person and a pet for each sensor signal. Decisions of HMMs can be fused together to reach a final decision.