Courses
Some courses I have created and gave:
- 2020-present (Faculty of ECE, Technion): Overview of Electrical and Computer Engineering. This course describes for first-year students in our faculty the various fields included in Electrical and Computer Engineering, and presents main aspects of an engineer’s skills in the high-tech industry. I co-created this course with Prof. Avinoam Kolodny and have been co-teaching it with him since.
- 2011-present (Faculty of ECE, Technion): Introduction Project in Electrical and Computer Engineering. This course provides a gentle introduction to the Electrical and Computer Engineering profession for first-year students in our faculty. I am part of the team who created this course, have been involved in teaching it since, and have been the teacher in charge of this course for several semesters.
- 2005-present: Image & video compression course (various places). A course that I have co-created and give in various places together with Nimrod Peleg. The course deals with the principles of image & video compression as well as industry standards such as JPEG, MPEG-1/2/4, H.261/3/4, H.265/HEVC. Also covers other image and video processing topics such as image and video quality assessment.
- 2002-present (Faculty of ECE, Technion): Object Oriented Programming and Design. This course was created by Gabi Zodik and I, and has been given by both of us since 2002. Since 2017, I am the lecturer of this course. The course covers major themes of OOP, software design, and design patterns. The Java programming language is used.
- 2005-present (various places): Various courses on C, C++, Java, and software engineering.
- 2001 (Mediatech college): MCSD (Microsoft Certified Solution Developer) course. Covering C, C++ and the Microsoft .NET platform. As far as I know, I was the first in the northern Israel to teach the .NET architecture. 430 hours.
- 1997 (MALAM): PC technician course. 100 hours.
Experiments, Presentations, …
I have co-created and supervised several experiments for undergraduate students. I have also written a number of presentations and documents on lesser known aspects of MATLAB, and I’m the faculty’s “knowledge center” on the subject.
Projects
In SIPL, I have supervised the following undergraduate student projects (* means co-supervision):
| Project Name | Area | Collaborator | Sem. |
|---|---|---|---|
| Open world classification of ship radars | Communications, DL | RAFAEL | 2020B |
| Blood pressure estimation with a smartwatch | Physiological, DL | CardiacSense | 2020B |
| Suspicious moles detection using binary masks | Image, DL | Marpe Technologies | 2020B |
| Augmented reality app for physics classrooms | Image, DL | 2020B | |
| Depth-based semantic segmentation for four-legged robot | Image, DL | RAFAEL | 2020B |
| Classification of parent-child synchronization during interaction | Video, DL | Faculty of Education in Science and Technology | 2020B |
| Configuring an Intelligent Reflecting Surface for wireless communications* | Communications, DL | IEEE Signal Processing Cup 2021 | 2020A |
| No-reference singing quality assessment | Speech, Music | 2020A | |
| Estimating speaker characteristics based on his speech | Speech, DL | 2020A | |
| Speech to singing conversion using deep learning* | Speech, Music, DL | Lyrica | 2020A |
| Voice DeepFake | Speech, DL | 2020A | |
| Open set classification of ship radars | Communications, DL | RAFAEL | 2019B |
| Blood pressure estimation with a smartwatch | Physiological, DL | 2019B | |
| Speech dereverberation using deep learning* | Speech, DL | 2019B | |
| Melanoma detection | Image, DL | Marpe Technologies | 2019B |
| Unsupervised anomly detection in autonomous systems | Manifold Learning, DL | IEEE Signal Processing Cup 2020 | 2019A |
| Estimating blood pressure using PPG signals | Physiological, DL | 2019A | |
| Speech emotion recognition | Speech, DL | 2019A | |
| Speech2Singing | Speech, Music | Lyrica | 2019A |
| Pneumonia detection from chest X-Rays with robustness to deformations | Image, DL | Zebra Medical Vision | 2019A |
| Thermal to visible facial image translation | Image, DL | 2019A | |
| Health maps from PPG | Physiological | GT-CARDIO | 2018B |
| Detection of pool entry using an acoustic sensor | Audio | Sosense | 2018B |
| Suspicious moles detection | Image | Marpe Technologies | 2018B |
| Material recognition using images from thermal mobile camera | Image | 2018B | |
| Blood pressure estimation using PPG signals | Physiological, DL | Faculty of Medicine Rambam Medical Center | 2018A |
| Speech2Singing | Speech, Music | Elad Keidan | 2018A |
| Alarm sound detection | Audio, DL | 2018A | |
| Material recognition using thermal images | Image, DL | 2018A | |
| Object localization in thermal images | Image, DL | 2018A | |
| Classroom mechanics augmented reality application | Video, DL | 2018A | |
| Pneumonia detection from chest x-rays | Image, DL | 2017B | |
| Deep learning for classroom mechanics augmented reality | Video, DL | 2017B | |
| Blood pressure estimation from smartphone video | Video, Physiological | 2017A | |
| Real-time pedestrian traffic light recognition using deep learning | Video, DL | 2017A | |
| Classroom mechanics augmented reality with your smartphone | Video | 2017A | |
| Fast video coding using deep learning | Video | Harmonic | 2016B |
| Influence of motion on video quality perception | Video | Harmonic | 2016B |
| Detection of alarm sounds using deep learning | Audio | 2016A | |
| Rodent bones identification using deep learning | Image | Hebrew Univ. | 2016A |
| Rural road detection for a self-driving car | Image | RAFAEL | 2016A |
| Pedestrian traffic light recognition on video using deep learning | Video | 2016A | |
| Android App for objects removal from crowded image background* | Video | 2016A | |
| 3D data processing and registration with multiple RealSesnse cameras | 3D | 2016A | |
| Registration of RealSense 3D scans and CAD models | 3D | 2015C | |
| Detection of alarm sounds in noisy environments | Audio | 2015B | |
| Red/green pedestrian traffic light recognition | Image | 2015B | |
| Rodent bones classification | Image | Hebrew Univ. | 2015B |
| Blood pressure estimation using a smartphone camera | Video, PPG | 2015B | |
| Super-resolution for infrared surveillance video | Video | IDF | 2015B |
| Musical plagiarism detection | Audio | 2015A | |
| Robust underwater image compression* | Image | RAFAEL | 2015A |
| Sidescan sonar image compression* | Image | RAFAEL | 2015A |
| Image compression using block removal and synthesis | Image | 2015A | |
| Objects removal from crowded image background* | Video | 2015A | |
| Using Epson augmented reality glasses | 3D | 2014C | |
| Detection of distress in speech | Speech | cMeSafe | 2014B |
| Analysis of pied kingfisher foraging pattern in space | 3D | Univ. of Haifa | 2014B |
| Registration of point clouds* | 3D | 2014B | |
| Speech narration quality assessment | Speech | Blindvoices | 2014A |
| Distance estimation of marine vehicles | Video | RAFAEL | 2014A |
| Background modeling in video | Video | 2014A | |
| Fast HEVC quad-tree partitioning for GPU parallelization | Video | Harmonic | 2014A |
| Object segmentation using Intel RealSense 3D camera | 3D | Intel | 2014A |
| Fast High Efficiency Video Coding (HEVC) | Video | 2013B | |
| Video coding for underwater transmission | Video | Rafael | 2013B |
| Transcoder video quality assessment | Video | Harmonic | 2013B |
| Audio matching in a mobile environment | Audio | Telequid | 2013A |
| Part-based human detection in Video | Image | DVTel | 2013A |
| Video quality assessment improvements | Video | 2013A | |
| Augmented reality pinball | Video | 2013A | |
| Bilateral filtering and morphological gradient for SIPER | Image | 2012C | |
| Nonlocal Means image denoising for SIPER | Image | 2012C | |
| Cloud detection in color aerial images | Image | MOD | 2012B |
| Analysis of fish behavior in video | Video | Cornfeed | 2012B |
| Video quality assessment system | Video | IDF | 2012B |
| Image denoising using nonlinear tone-mapping | Image | IDC | 2012A |
| Tone mapping for SWIR face images | Image | MOD | 2012A |
| Moving object detection in compressed aerial video | Video | Elbit | 2012A |
| High Efficiency Video Coding (HEVC) | Video | 2012A | |
| Image skeletonization for SIPER | Image | 2011C | |
| Grouping pixels perceptually into contours for SIPER | Image | 2011C | |
| Synthetic speech with synchronized lip movement for robotic head | Speech | CRML | 2011B |
| Reduced-reference surveillance video quality assessment | Video | IDF | 2011B |
| Human detection and tracking | Video | DVTel | 2011B |
| Augmented reality Pinball game | Video | 2011B | |
| Image processing for photoelastic stress analysis | Image | Vishay | 2011A |
| Shadow detection in aerial images* | Image | Elbit | 2011A |
| Moving objects detection in compressed domain | Video | Elbit | 2011A |
| Augmented reality using PlayStation Eye* | Video | 2011A | |
| Music composition using multitouch interface | Video, Music | 2011A | |
| Hough transform for SIPER | Image | 2010C | |
| Saliency detection for SIPER | Image | 2010C | |
| Surveillance video quality assessment | Video | IDF | 2010B |
| Multitouch Tangram | Video | CRL Lab | 2010B |
| Cast shadow detection for Texas Instruments DM642* | Video, DSP | IDC | 2010B |
| Audio query by tapping* | Audio | 2010A | |
| G.711.1 wideband speech coding for Texas Instruments C55xx* | Speech, DSP | 2010A | |
| Cast shadow detection in video | Video | IDC | 2010A |
| Multi-camera tracking in crowd | Video | Mate | 2010A |
| Face detection for SIPER | Image | 2009C | |
| Robust keystroke identification using IR | Video | MOD | 2009C |
| Reduced-reference video quality assessment | Video | 2009B | |
| Shape recognition for a multi-touch surface | Video | CRL | 2009B |
| Voice scrambling for Atmel DIOPSIS 940HF* | Speech, DSP | Atmel | 2009A |
| Speech coding using Simulink for DSP | Speech, DSP | 2009A | |
| Abnormal event detection in compressed video | Video | Nice | 2009A |
| Fast object detection in multi-camera video | Video | Mate | 2009A |
| Object tracking and classification for Texas Instruments DM642 | Video, DSP | 2009A | |
| Texture synthesis for SIPER | Image | 2008C | |
| Digital Audio Effects using Simulink for DSP* | Audio, DSP | 2008B | |
| Small target detection in IR video* | Video | SensoOptics | 2008B |
| Keystroke identification using IR | Video | MOD | 2008B |
| JPEG image compression for SIPER | Image | 2008A | |
| Edge detection for SIPER | Image | 2008A | |
| Intra prediction for SIPER | Image | 2008A | |
| Parallel Hough transform | Image | 2008A | |
| Objects reidentification in multi-camera video* | Video | Mate | 2008A |
| Video background modeling for an embedded system | Video | 2008A | |
| Video quality assessment | Video | MOD | 2008A |
| Image thresholding for SIPER | Image | 2007C | |
| Image quantization for SIPER* | Image | 2007C | |
| Pedestrian tracking for Texas Instruments C6455 and DM642 | Video, DSP | 2007B | |
| Scene cut detection in aerial video | Video | Elbit | 2007B |
| Post-processing for aerial video | Video | Elbit | 2007B |
| Adaptive pattern matching using Gray-Code-Kernels* | Image | 2007B | |
| Audio retrieval using computer vision tools | Audio, Image | 2007A | |
| G.726 speech coding using Simulink for Texas Instruments C67xx | Speech, DSP | 2007A | |
| Geometry-adaptive block partitioning for H.264 video coding | Video | 2007A | |
| Fast motion estimation using GCK for Texas Instruments DM6437 | Video, DSP | 2007A | |
| Texture synthesis | Video | 2007A | |
| Morphological image processing for SIPER | Image | 2006C | |
| Feature matching for widely-separated views | Video | 2006B | |
| Accelerated video decoding using an NVidia GPU* | Video | Elbit | 2006B |
| Packet-loss concealment detection for video based on image content | Video | RadVision | 2006B |
| Video face detection for Texas Instruments DM642 | Video, DSP | 2006B | |
| MPEG-7 audio descriptors for SPDemo | Audio | 2006B | |
| Image coding using lapped transforms* | Image | 2006A | |
| Speech data embedding for SPDemo* | Speech | 2006A | |
| Single-ended objective speech quality assessment for SPDemo* | Speech | 2006A | |
| Audio retrieval | Audio | Mobixell | 2006A |
| Scalable video coding using MCTF for H.264/AVC* | Video | 2006A | |
| Multi-view video coding for H.264/AVC | Video | 2006A | |
| Bit-rate control for multithreaded H.264/AVC encoder* | Video | Oplus/Intel | 2006A |
| Video logo Insertion in compressed domain for Texas Instruments C67xx | Video, DSP | NeGeV | 2006A |
| Pedestrian tracking for Texas Instruments DM642 | Video, DSP | MOD | 2006A |
| Post-processing for flicker reduction in H.264/AVC | Video | Oplus/Intel | 2005B |
| Very low bitrate H.264/AVC implementation for Texas Instruments C67xx | Video, DSP | Tadiran | 2005B |
| H.264/AVC implementation for Texas Instrument DaVinci | Video, DSP | Elbit | 2005B |
| Fast motion estimation using GCK for Texas Instrument DM642 | Video, DSP | 2005B | |
| Video retrieval using motion features | Video | 2005B | |
| 3D image reconstruction for Texas Instrument DaVinci* | Image, DSP | GIP | 2005B |
| Advanced variable-size FFT for Texas Instruments C67xx | DSP | 2005A | |
| Video pre-processing using morphological tools | Video | Comverse | 2005A |
| Text detection in video | Video | 2005A | |
| Video retrieval using color features | Video | 2005A | |
| Multithreaded H.264/AVC encoding | Video | Intel | 2005A |
| Video shot boundary detection using pixel-based methods | Video | 2004C | |
| Video shot boundary detection using block-based methods | Video | 2004C | |
| Fingerprint authentication using TI FADT* | Image, DSP | 2004C | |
| Low-complexity face detection in images | Image | 2004C | |
| Speech bandwidth extension for Atmel DIOPSIS D740* | Speech, DSP | Atmel | 2004C |
| Video error concealment for H.264 | Video | 2004B | |
| Video face detection for Texas Instruments DM642 | Video, DSP | 2004B | |
| Fast pattern recognition using Gray-Code-Kernels | Image | 2004B | |
| AAC audio coding for SPDemo | Audio | 2004A | |
| JPEG to MPEG transcoding | Image, Video | Adimos | 2004A |
| Very low bit-rate video compression | Video | Tadiran | 2004A |
| Arbitrary size FFT for Texas Instruments C67xx | DSP | 2003C | |
| Low-complexity image retrieval in the spatial domain | Image | 2003C | |
| Low-complexity image retrieval in the DCT domain | Image | 2003C | |
| Fast Intra Prediction for H.264 video coding | Video | 2003B | |
| TDHS for SPDemo | Speech | 2003B | |
| MP3 audio coding for Texas Instrument C64xx | Audio, DSP | 2003A | |
| Voice Activity Detector for Texas Instruments C54xx | Speech, DSP | 2003A | |
| WSOLA for Texas Instruments C54xx and for SPDemo | Speech, DSP | 2003A | |
| Speech features extraction for SPDemo | Speech | 2003A | |
| H.264 video coding for Texas Instruments DM642 | Video, DSP | 2003A | |
| H.264 video coding for Freescale StarCore 8101 | Video, DSP | 2003A | |
| H.264 video coding for Analog Devices Blackfin | Video, DSP | 2003A | |
| G.711 packet loss concealment for SPDemo* | Speech | 2002B | |
| Digital watermarking of MIDI files* | Audio | Mobixell | 2002B |
| H.264 video coding for VCDemo* | Video | 2002A | |
| MP3 audio coding for SPDemo | Audio | 2002A | |
| Voice scrambling for SPDemo* | Speech | 2002A | |
| FFT for Analog Devices ADSP-21160 | DSP | 2001C | |
| H.26L implementation for Texas Instruments IDK | Video, DSP | 2001C | |
| Independent hand-drawn sketch recognition for an electronic tablet | Image | 2001C | |
| A tool for subjective assessment of image quality | Image | 2001B |