A5089336356- Eurasian Exchange Networks
- Video Surveillance and Tracking Methods
- Turkish Urban and Social Issues
- Ottoman and Turkish Studies
- History and Cultural Heritage
- Families in Therapy and Culture
- Context-Aware Activity Recognition Systems
- Cultural Heritage Management and Preservation
- Linguistics and Cultural Studies
- Islamic Studies and History
- Non-Invasive Vital Sign Monitoring
- Advanced Neural Network Applications
- Historical Turkish Studies
- Gait Recognition and Analysis
- Autonomous Vehicle Technology and Safety
- Agricultural and Rural Development Research
- Anomaly Detection Techniques and Applications
- Urban Green Space and Health
- Byzantine Studies and History
- Ottoman Empire History and Society
- IoT and Edge/Fog Computing
- Advanced Glycation End Products research
- Cultural and Sociopolitical Studies
- Sleep and Work-Related Fatigue
- Advanced Image and Video Retrieval Techniques
Pamukkale University
2015-2024
Iowa State University
2017-2022
Syracuse University
2012-2016
Selçuk University
2005-2014
Laboratoire d'Informatique de Paris-Nord
2014
Activity detection and classification are very important for autonomous monitoring of humans applications, including assistive living, rehabilitation, surveillance. Wearable sensors have found wide-spread use in recent years due to their ever-decreasing cost, ease deployment use, ability provide continuous as opposed installed at fixed locations. Since many smart phones now equipped with a variety sensors, such accelerometer, gyroscope, camera, it has become more feasible develop activity...
The rapid advances of transportation infrastructure have led to a dramatic increase in the demand for smart systems capable monitoring traffic and street safety. Fundamental these applications are community-based evaluation platform benchmark object detection multi-object tracking. To this end, we organize AVSS2017 Challenge on Advanced Traffic Monitoring, conjunction with International Workshop Street Surveillance Safety Security (IWT4S), evaluate state-of-the-art tracking algorithms...
Robust detection of events and activities, such as falling, sitting, lying down, is a key to reliable elderly activity monitoring system. While fast precise falls critical in providing immediate medical attention, other activities like sitting down can provide valuable information for early diagnosis potential health problems. In this paper, we present fall classification system using wearable cameras. Since the camera worn by subject, not limited confined areas, extends wherever subject may...
Robust and reliable detection of falls is crucial especially for elderly activity monitoring systems. In this letter, we present a fall system using wearable devices, e.g., smartphones, tablets, equipped with cameras accelerometers. Since the portable device worn by subject, not limited to confined areas, extends wherever subject may travel, as opposed static sensors installed in certain rooms. Moreover, camera provides an abundance information, results presented here show that fusing...
Timely, precise, and reliable detection of fall events is very important for systems monitoring activities elderly people, especially the ones living independently. In this paper, we propose an autonomous system by taking a completely different view compared with existing vision-based activity applying reverse approach. our system, in contrast static sensors installed at fixed locations, camera worn subject, thus, not limited only to areas where are located extends wherever subject may...
Wearable sensors are being widely used to monitor daily human activities and vital signs. Accelerometer-based step counters commonly available, especially after integrated into smartphones smart watches. Moreover, accelerometer data is also measure length frequency for indoor positioning systems. Yet, accelerometer-based algorithms prone over-counting, since they count other routine movements, including movements of the phone, as steps. In addition, when users walk really slowly, or stop...
Fully autonomous navigation of unmanned vehicles, without relying on pre-installed tags or markers, still remains a challenge for GPS-denied areas and complex indoor environments. Doors are important as the entry/exit points. A novel approach is proposed to autonomously detect™ doorways by using Project Tango platform. We first detect candidate door openings from 3D point cloud, then use pre-trained detector corresponding RGB image regions verify if these indeed doors. employ Aggregate...
Determining camera motion is a challenging task in applications involving mobile smart cameras. With widespread use of cameras applications, analyzing motion-based information have become important. Optical flow has been popular technique determining motion. However, the traditional optical techniques can be computationally quite expensive and impractical for embedded with limited processing power, The aim this paper to provide an effective efficient determine direction. This based on...
We propose a Quantization Guided Training (QGT) method to guide DNN training towards optimized low-bit-precision targets and reach extreme compression levels below 8-bit precision. Unlike standard quantization-aware (QAT) approaches, QGT uses customized regularization encourage weight values distribution that maximizes accuracy while reducing quantization errors. One of the main benefits this approach is ability identify bottlenecks. validate using state-of-the-art model architectures on...
Automated monitoring of activities elderly is very important in the field healthcare. While fast and precise detection falls critical providing immediate medical attention, other like walking, sitting lying down can provide valuable information for early diagnosis potential health problems. Recently, wearable smart cameras have emerged as a new area research, since they several advantages. First, activity not restricted to confined environments, where static sensors are installed. Second,...
In this paper, we present a novel model to detect lane regions and extract departure events (changes incursions) from challenging, lower-resolution videos recorded with mobile cameras. Our algorithm used Mask-RCNN based detection as pre-processor. Recently, deep learning-based models provide state-of-the-art technology for object combined segmentation. Among the several learning architectures, convolutional neural networks (CNNs) outperformed other machine models, especially region proposal...
Robust detection of events and activities, such as falling, sitting lying down, is a key to reliable elderly activity monitoring system. While fast precise falls critical in providing immediate medical attention, other activities like down can provide valuable information for early diagnosis potential health problems. In this paper, we present fall classification system using wearable cameras. Since the camera worn by subject, extends wherever subject may go. Furthermore, since captured...
ÖZ Bu araştırmanın amacı; Türkiye sanayisinin ana merkezi niteliğindeki İstanbul Metropoliten Alanı doğu çeperinde yer alan Tuzla yerleşmesinin mekânsal ve işlevsel gelişim-değişim sürecinde organize sanayi yatırımlarının etkilerinin araştırılmasıdır
In this paper, we present an autonomous method to track and count footsteps by using the camera data from mobile phones or tablets. Many step counters, relying on accelerometer data, are widely available. However, accelerometer-based algorithms prone overcounting. our proposed method, feature points detected first. Then, in order increase robustness accuracy especially case of highly-textured ground floor surfaces, Kalman filter based tracking is performed. The compared with existing...
Ozet Bu araþtýrmanýn amacý, Turkiye'nin metropolitenleþme surecindeki tarihsel kentlerinden Konya kentsel koruma alanýnda kulturel mirasa konu olan deðerlerin surdurulebilir korunmasý ve geliþtirilmesinde acýkyeþil alan kullanýmlarýný etkin kýlacak bir planlama modelinin mekânsal iþlevsel ilkelerinin tanýmlanmasýdýr. tanýmlamalar, alanýna iliþkin 1/1.000 olcekli amaclý imar planý raporu ile tespit calýþmalarýndan elde edilen acýk-yeþil kullanýmlarýna niceliksel niteliksel verilere...
Objective: The aim of this study was to examine the ageand gender-related differences in peroxide production, manganese superoxide dismutase (MnSOD) activity and expression liver mitochondria Wistar rats at 12 24 months age. Methods: chemiluminometric method for fluorometric malondialdehyde (MDA) levels, cumene hydroperoxide assay glutathione peroxidase (GPx), nitroblue tetrazolium MnSOD activity, Western-blotting were used. Results: Mitochondrial peroxides are increased significantly both...
Multi-class object detection is critical for intelligent traffic monitoring applications in smart cities as well connected autonomous vehicles. Although, numerous research works evaluate the performance of image processing algorithms on-vehicle cameras, body evaluating stationary cameras located near intersections limited. In this research, we use region-based deformable fully convolutional networks to detect 14 different classes within images from surveillance cameras. The include vehicles,...
Abstract Milkweed ( Asclepias spp.) are host plants of monarch butterflies Danaus plexippus ). It is important to detect milkweed plant locations assess the status and trends habitat in support conservation programs. In this paper, we describe autonomous detection using cameras mounted vehicles. For detection, used both aggregated channel features ACF ) for running detectors on embedded computing platforms with central processing unit faster region‐based convolutional neural network (Faster...
Traditional settlements which have to be conserved and sustained due their cultural, social, economic, archaeological aesthetic values contribute much perceptibility of cities by transferring the emotion, thought, social life background time when established. Since different cultures coincide, leading a variety this is reflected in space, Turkey has rich, cultural natural heritage together. Mustafapaşa (Sinasos) an authentic settlement with its spatial characteristics shaped rich culture...