Wyniki wyszukiwania - BazTech

1

Dual-Path Image Reconstruction: Bridging Vision Transformer and Perceptual Compressive Sensing Networks

Bairi Zakaria, Bey Kadda Beghdad, Ben-Ahmed Olfa, Amamra Abdenour, Bradai Abbas

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

347--354

EN

Over the past few years, notable advancements have been made through the adoption of self-attention mechanisms and perceptual optimization, which have proven to be successful techniques in enhancing the overall quality of image reconstruction. Self-attention mechanisms in Vision Transformers have been widely used in neural networks to capture long-range dependencies in image data, while perceptual optimization has been shown to enhance the perceptual quality of reconstructed images. In this paper, we present a novel approach to image reconstruction by bridging the capabilities of Vision Transformer and Perceptual Compressive Sensing Networks. Specifically, we use a self-attention mechanism to capture the global context of the image and guide the sampling process, while optimizing the perceptual quality of the sampled image using a pre-trained perceptual loss function. Our experiments demonstrate that our proposed approach outperforms existing state-of-the-art methods in terms of reconstruction quality and achieves visually pleasing results. Overall, our work contributes to the development of efficient and effective techniques for image sampling and reconstruction, which have potential applications in a wide range of domains, including medical imaging and video processing.

2

Crime scene reconstruction with RGB-D sensors

Amamra Abdenour, Amara Yacine, Boumaza Khalid, Benayad Aissa

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

391-–396

EN

Photographic surveying, a fundamental procedure in crime investigation, is typically performed using 2D cameras. Although useful, such cameras remain limited due to the lack of depth information. In this work, we propose a 3D reconstruction solution that leverages the advantages of cheap RGB-D sensors to create a 3D model of the crime scene and to provide the investigator with an interactive crime scenario simulation environment. A structure from motion approach is proposed in order to align the captured point clouds on each other using 3D key points. An iterative refinement and a global optimization algorithm are later adapted for the optimization of the registered 3D model, which is then triangulated before the underlying surface is reconstructed. The resulting model is used for interactive crime investigation and object dynamics simulation. The obtained results show the effectiveness of our solution with a visually appealing rendering, an accurate simulation and a quantitative error of less than 18cm for the $4m \times 4 m$ indoor scene. An accompanying video is provided in order to illustrate the processing pipeline (https://youtu.be/IYnJSNV7QkI).

3

A social bonds integration approach for crowd panic simulation

Bouderbal Imene, Amamra Abdenour

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

303–-308

EN

Crowd panic has incurred massive injuries and deaths throughout history; thus understanding it is particularly important in order to save human lives. Recently, numerous simulation methods have been contributed in order to provide insight into the design of evacuation planning strategies. In this paper, we integrate a social structure to the crowd mobility model for the purpose of investigating the influence of social bonds on collective behavior during panic. A macroscopic crowd panic model based on social science theories was integrated as an internal module to the microscopic mobility model. The resulting framework is tunable and permits the implementation of several panic scenarios. It is also designed to run in different situations for a better comprehension of panic-related phenomena. The results demonstrate the smoothness of our crowd flow model and the realism of evacuation during panic.

4

A GIS data realistic road generation approach for traffic simulation

Amara Yacine, Amamra Abdenour, Daheur Yasmine, Saichi Lamia

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

385–-390

EN

Road networks exist in the form of polylines with attributes within the GIS databases. Such a representation renders the geographic data impracticable for 3D road traffic simulation. In this work, we propose a method to transform raw GIS data into a realistic, operational model for real-time road traffic simulation. For instance, the proposed raw to simulation-ready data transformation is achieved through several curvature estimation, interpolation/approximation, and clustering schemes. The obtained results show the performance of our approach and prove its adequacy to real traffic simulation scenario as can be seen in this video (https://youtu.be/t8eyphcFYHc.)

5

A Deep learning and multimodal ambient sensing framework for human activity recognition

Yachir Ali, Amamra Abdenour, Djamaa Badis, Zerrouki Ali, khierEddine Amour Ahmed

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

101--105

EN

Human Activity Recognition (HAR) is an important area of research in ambient intelligence for various contexts such as ambient-assisted living. The existing HAR approaches are mostly based either on vision, mobile or wearable sensors. In this paper, we propose a hybrid approach for HAR by combining three types of sensing technologies, namely: smartphone accelerometer, RGB cameras and ambient sensors. Acceleration and video streams are analyzed using multiclass Support Vector Machine (SVM) and Convolutional Neural Networks, respectively. Such an analysis is improved with the ambient sensing data to assign semantics to human activities using description logic rules. For integration, we design and implement a Framework to address human activity recognition pipeline from the data collection phase until activity recognition and visualization. The various use cases and performance evaluations of the proposed approach show clearly its utility and efficiency in several everyday scenarios.