Rached Tourki

Bio: Rached Tourki is an academic researcher from University of Monastir. The author has contributed to research in topics: Network on a chip & Cryptography. The author has an hindex of 11, co-authored 71 publications receiving 495 citations.

Definition and Performance Evaluation of a Robust SVM Based Fall Detection Solution

Abstract: We propose an automatic approach to detect falls in home environment. A Support Vector Machine based classifier is fed by a set of selected features extracted from human body silhouette tracking. The classifier is followed by filtering operations taking into account the temporal nature of a video. The features are based on height and width of human body bounding box, the user's trajectory with her/his orientation, Projection Histograms and moments of order 0, 1 and 2. We study several combinations of usual transformations of the features (Fourier Transform, Wavelet transform, first and second derivatives), and we show experimentally that it is possible to achieve high performance using a single camera.We evaluated the robustness of our method using a realistic dataset. Experiments show that the best tradeoff between classification performance and time processing result is obtained combining the original data with their first derivative. The global error rate is lower than 1%, and the recall, specificity and precision are high (respectively 0.98, 0.996 and 0.942). The resulting system can therefore be used in a real environment. Hence, we also evaluated the robustness of our system regarding location changes. We proposed a realistic and pragmatic protocol which enables performance to be improved by updating the training in the current location, with normal activities records.

Hardware Co-simulation For Video Processing Using Xilinx System Generator

Abstract: The use of rapid prototyping tools such as MATLAB- Simulink and Xilinx System Generator becomes increasingly important because of time-to-market constraints. This paper presents a methodology for implementing real-time DSP applications on a reconfigurable logic platform using Xilinx System Generator (XSG) for Matlab. The methodology aims to improve the design verfication efficiency for such complex system. It presents an architecture for Color Space Conversion (CSC) RGBTOYCbCr for video processing using Xilinx System Generator. The design was implemented targeting a Spartan3 device (3S200PQ208) then a Virtex II Pro (xc2vp7-6ff672). Obtained results are discussed and compared with an other architecture. The conversion method has been verified successfully with no visually perceptual errors in the transformed images.

Implementation of CPA analysis against AES design on FPGA

Abstract: Physical implementations of cryptographic algorithms may let relatively side channel information. By analyzing this information leakage, the confidential data, like the cryptographic keys, can be revealed. The correlation power analysis(CPA) is a well-known attack of the cryptographic device. This paper conduces a successful CPA of the Advanced Encryption Standard AES implemented on the Xilinx FPGA with the Side-channel Attack Standard Evaluation Board (SASEBO). The experimental results show that the choice of the power model and the number of power traces can further improve the performance of CPA attack in extracting the correct key.

Human detection based on integral Histograms of Oriented Gradients and SVM

Abstract: This paper presents a method for human detection in video sequence. The Histogram of Oriented Gradients (HOG) descriptors show experimentally significantly out-performs existing feature sets for human detection. Because of HOG computation influence on performance, we finally choose a more better HOG descriptor to extract human feature from visible spectrum images based on OpenCv and MS VC++. We realized an image descriptor based on Integral Histograms of Oriented Gradients (HOG), associated with a Support Vector Machine (SVM) classifier and evaluate its efficiency.

A Reconfigurable Implementation of the New Secure Hash Algorithm

Abstract: The main applications of the hash functions are met in the fields of communication's integrity and signature authentication. Many hash algorithms have been investigated and developed in the last years. This work is related to hash functions FPGA implementation. Field programmable gate arrays (FPGAs) being reconfigurable, flexible and physically secure are a natural choice for implementation of hash functions in a broad range of applications with different area-performance requirements. We propose a configurable secure hash algorithm (SHA) processor for extended signature authentication. This paper investigates different optimizations algorithms of recent techniques that have been proposed in the literature. In our implementation based on Xilinx Virtex FPGAs, the throughput of SHA processor is equal to 1296 Mbit/s. Speed/area results from these processors are analyzed and shown to compare favorably with other FPGA-based implementations. A fastest data throughput is achieved by our optimized algorithm

Deep Learning for Fall Detection: Three-Dimensional CNN Combined With LSTM on Video Kinematic Data

Abstract: Fall detection is an important public healthcare problem. Timely detection could enable instant delivery of medical service to the injured. A popular nonintrusive solution for fall detection is based on videos obtained through ambient camera, and the corresponding methods usually require a large dataset to train a classifier and are inclined to be influenced by the image quality. However, it is hard to collect fall data and instead simulated falls are recorded to construct the training dataset, which is restricted to limited quantity. To address these problems, a three-dimensional convolutional neural network (3-D CNN) based method for fall detection is developed, which only uses video kinematic data to train an automatic feature extractor and could circumvent the requirement for large fall dataset of deep learning solution. 2-D CNN could only encode spatial information, and the employed 3-D convolution could extract motion feature from temporal sequence, which is important for fall detection. To further locate the region of interest in each frame, a long short-term memory (LSTM) based spatial visual attention scheme is incorporated. Sports dataset Sports-1 M with no fall examples is employed to train the 3-D CNN, which is then combined with LSTM to train a classifier with fall dataset. Experiments have verified the proposed scheme on fall detection benchmark with high accuracy as 100%. Superior performance has also been obtained on other activity databases.

UP-Fall Detection Dataset: A Multimodal Approach.

Abstract: Falls, especially in elderly persons, are an important health problem worldwide. Reliable fall detection systems can mitigate negative consequences of falls. Among the important challenges and issues reported in literature is the difficulty of fair comparison between fall detection systems and machine learning techniques for detection. In this paper, we present UP-Fall Detection Dataset. The dataset comprises raw and feature sets retrieved from 17 healthy young individuals without any impairment that performed 11 activities and falls, with three attempts each. The dataset also summarizes more than 850 GB of information from wearable sensors, ambient sensors and vision devices. Two experimental use cases were shown. The aim of our dataset is to help human activity recognition and machine learning research communities to fairly compare their fall detection solutions. It also provides many experimental possibilities for the signal recognition, vision, and machine learning community.

Vision-Based Fall Detection with Convolutional Neural Networks

Abstract: One of the biggest challenges in modern societies is the improvement of healthy aging and the support to older persons in their daily activities. In particular, given its social and economic impact, the automatic detection of falls has attracted considerable attention in the computer vision and pattern recognition communities. Although the approaches based on wearable sensors have provided high detection rates, some of the potential users are reluctant to wear them and thus their use is not yet normalized. As a consequence, alternative approaches such as vision-based methods have emerged. We firmly believe that the irruption of the Smart Environments and the Internet of Things paradigms, together with the increasing number of cameras in our daily environment, forms an optimal context for vision-based systems. Consequently, here we propose a vision-based solution using Convolutional Neural Networks to decide if a sequence of frames contains a person falling. To model the video motion and make the system scenario independent, we use optical flow images as input to the networks followed by a novel three-step training phase. Furthermore, our method is evaluated in three public datasets achieving the state-of-the-art results in all three of them.

A survey on vision-based fall detection

Abstract: Falls are a major cause of fatal injury for the elderly population. To improve the quality of living for seniors, a wide range of monitoring systems with fall detection functionality have been proposed over recent years. This article is a survey of systems and algorithms which aim at automatically detecting cases where a human falls and may have been injured. Existing fall detection methods can be categorized as using sensors, or being exclusively vision-based. This literature review focuses on vision-based methods.