Project Archive

  • Year - 2017
  • US

    Tissue Doppler Imaging (TDI) plays a major role in evaluating the left ventricular function [1]. This modality is characterized by an intrinsic noise, which leads to the classical thickness of the graphs displayed in commercial ultrasonic equipment. The agreement between TDI and Mitral Annulus Plane Excursion (MAPE) has been shown to be sub-optimal [2]. We hypothesize that this discordance is due to the noise in TDI. By taking the neighborhood space expectancy of the Tissue Doppler through time as the velocity of the Mitral Annulus Plane we obtain a periodic measurement which agrees better with the MAPE as measured manually. To validate our results we integrated the obtained velocity over time and obtained the cumulative displacement of the Mitral Annulus Plane. The Euclidean error between this displacement and manually marked MAPE was found to behave as a Gaussian distribution with mean 0 and standard deviation of 0.8 under QQ-plots and Kolmogorov-Smirnov test with significance levels of 5%.

  • Year - 2016
  • 7-1-300x226

    The majority of car accidents which involve pedestrians occur due to Moving violations cause by the driver, therefor our main goal in this project was to detect

    pedestrians near pedestrian crossings in low visibility conditions in order to alert drivers.

  • fi1

    ThermTrack is an Android application that enables to track objects with a low-cost thermal camera of type Thermapp according to temperature range and basic image features.
    Image processing features like blob detection and object area, circularity, convexity etc. were taken from OpenCV libraries.
    The original goal was tracking pedestrians, pedestrian tracking can be utilized by the operator by choosing suitable parameters of the available features.
    The development was done using Android studio, OpenCV libraries were used for the image processing part, Thermapp SDK was used for interfacing with the camera.

  • fi

    The project's goal was making feasibility check for improving the time-consuming algorithm of tomography with a new method of opto-acoustic.

  • fi-6-300x203

    Turbulence creates refractive perturbations to light passing through a scene which causes random distortions when imaging background objects.
    A simple example we are experience on daily basis is refraction through glass of water or distortions above a road on a hot day

  • fi

    In the project, we will build an exhibition for the illusion of a three dimension in an interactive way.

  • fi-1-300x169

    Millions of pedestrians spend time every day waiting for the green light to cross a crosswalk.
    In a typical traffic light, the period is fixed
    Adjusting the traffic-light period dynamically can decrease waiting time.

  • Year - 2015
  • 2015w11-FI-300x168

    An interface was developed for interfacing a Kinect cameras to a PC through Ethernet connection. This should solve the bottleneck of the USB connection which allows connecting max 2 Kinect cameras version 1 or one Kinect cameras version 2.

  • 2015w01FI-277x200

    There are many types of solutions that can help to avoid forgetting kids in hot car but we chose to develop an alarm system based on image processing tools like face detection algorithm and image filtering.

  • aestetics

    Aesthetics, in the world of art and photography, refers to the principles of the nature and appreciation of beauty. Judging beauty and other aesthetic qualities of photographs is a highly subjective task

  • 1

    Combined with image processing, computerized graphics and Machine Learning, CPK system will alert and avoid sinking young children in private pools

  • fi-300x139

    In recent years drones became more accessible and we would like to explore the magnificent world of drones and autonomous systems.
    We would like to use the drone in order to accomplish basic mission, and create an infrastructure for next to come

  • fi-1-300x257

    In our days we relay more and more on image processing, but what if we want to process multiple video streams from different angles in the room or on the street and create a joint 4D video analysis.

  • fi-2

    Stereo vision & structured light are well-studied methods in the field of computer vision. Several products, such as Kinect, RealSense3D & DUO3D, use those technologies in order to reconstruct a 3D scene indoors

  • fi-1

    The aim of this project is change detection between medical images (CT scans and MRI) for later medical research and treatment, using the iterative Ricci flow algorithm

  • fi-2-300x248

    Nowadays, depth cameras (e.g. Kinect), are capable to map the entire room. It is doing so, by generating point clouds (x,y,z) of the object, in front of them. But it still maps only one angle of the object in front. In order to receive 3D mapping of the object, it is necessary to picture from every angle. After all the data is received, all the angles should be transferred to one coordinate system – this process is called registration

  • 11-300x237

    Many models of statistical signals are related to the "Markov Model". By this model there is a dependency between a value of specific sample of a signal.

  • texture-300x172

    Interpolation is one of the fundamental tasks in image processing. While many interpolation techniques have been proposed for that task, most of them comprise an averaging effect and therefore not optimized for texture image

1 2 3 11