Lecture batch (2 Lectures), Date: 17th June 2020
15. Deep Semantic Image Segmentation 19:30-20:15 EEST

16. CVML software development tools 20:15-21:00 EEST

(Lecture batch is part of the CVML web course ‘Computer vision and machine learning for autonomous systems’, to be delivered April-June 2020).


LECTURE 15: Deep Semantic Image Segmentation

Wednesday 17th June 2020 , 19:30-20:15 EEST

Summary: Semantic image segmentation is a very important computer vision task with several applications in autonomous systems perception, robotic vision and medical imaging. Recent semantic image segmentation methods rely on deep neural networks and aim to assign a specific class label to each pixel of the input image. This lecture overviews the topic and addresses some of the semantic image segmentation challenges, notably: Deep semantic Image Segmentation architectures. Skip connections. U-nets. BiSeNet. Semantic image segmentation performance, computational complexity and generalization.

Sample lecture material

 – sample slides DOWNLOAD

Related Literature:

  1. I. Pitas, “Digital image processing algorithms and applications”, Wiley 2000.
  2. Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062. 2014 Dec 22.

Lecture 16: CVML software development tools

Wednesday 17th June 2020 , 20:15-21:00 EEST

Summary: This lecture overviews the various SW tools, libraries and environments used in computer vision and machine learning: Robotic Operating System (ROS). Libraries (OpenCV, BLAS, cuBLAS, MKL DNN, cuDNN), DNN Frameworks (Neon, Tensorflow, Pytortch, Keras, MXNet), Distributed/cloud computing (MapReduce programming model, Apache Spark), Collaborative SW Development tools (GitHub, Bitbucket).


Sample lecture material
 – sample slides

Related Literature

  1. Bradski G, Kaehler A. Learning OpenCV: Computer vision with the OpenCV library. » O’Reilly Media, Inc.»; 2008 Sep 24.
  2. Kirk DB, Wen-Mei WH. Programming massively parallel processors: a hands-on approach. Morgan kaufmann; 2016.
  3. Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M. Tensorflow: A system for large-scale machine learning. In12th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 16) 2016 (pp. 265-283).



Prof. Ioannis Pitas (IEEE fellow, IEEE Distinguished Lecturer, EURASIP fellow) received the Diploma and PhD degree in Electrical Engineering, both from the Aristotle University of Thessaloniki, Greece. Since 1994, he has been a Professor at the Department of Informatics of the same University.

His current interests are in the areas of machine learning, computer vision, intelligent digital media, human centered interfaces, affective computing, 3D imaging and biomedical imaging. He has published over 860 papers, contributed in 44 books in his areas of interest and edited or (co-)authored another 11 books. He has also been member of the program committee of many scientific conferences and workshops. In the past he served as Associate Editor or co-Editor of 9 international journals and General or Technical Chair of 4 international conferences. He participated in 69 R&D projects, primarily funded by the European Union and is/was principal investigator/researcher in 41 such projects.

He has 31000+ citations to his work and h-index 83+ (Google Scholar)

Prof. Pitas lead the big European H2020 R&D project MULTIDRONE: https://multidrone.eu/ and is principal investigator (AUTH)  in H2020 projects Aerial Core and AI4Media. He is chair of the Autonomous Systems initiative https://ieeeasi.signalprocessingsociety.org/.

Lecturing record of Prof. I. Pitas: He was Visiting/Adjunct/Honorary Professor/Researcher and lectured at several Universities: University of Toronto (Canada), University of British Columbia (Canada), EPFL (Switzerland), Chinese Academy of Sciences (China),  University of Bristol (UK), Tampere University of Technology (Finland), Yonsei University (Korea), Erlangen-Nurnberg University (Germany), National University of Malaysia, Henan University (China). He delivered 90 invited/keynote lectures in prestigious international Conferences and top Universities worldwide. He run 17 short courses and tutorials on Autonomous Systems, Computer Vision and Machine Learning, most of them in the past 3 years in many countries, e.g., USA, UK, Italy, Finland, Greece, Australia, N. Zealand, Korea, Taiwan, Sri Lanka, Bhutan.

Relevant links:

http:// https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=en










Register Now!

If by clicking the <<Register Now!>> button the page opens in Greek language, please find on the upper right part of the page the option to change it in English. (it is next to the search field).

Separate registration is needed for each lecture batch (two 45 min lectures).

Registration fee (per lecture batch): 15 Euros
Maximum number of registrants: 50, on a first-come-first-serve basis.
Registration cutoff date: Wednesdays 15:00 EEST.
After successful registration, you will receive infos on how to join the web lecture by email (usually a couple hours before the lecture starts).
If you haven’t received the invitation mail to join the lecture until then, please contact


You can now also register to access past Lecture material: a) lecture ppt/pdf, b) recorded video, c) lecture understanding questionnaire
c) lecture evaluation form.

If you are interested of multiple past Lectures you need to change the «quantity» option accordingly and let us know about which ones.

Separate registration is needed το access each lecture batch (two 45 min lectures).
Registration fee (per lecture batch): 15 Euros

After you have registered you will receive the all corresponding material of it. .

Cancellation: If a 2-lecture batch is cancelled at lecturer’s fault, full reimbursement will be made to registrants. No reimbursement is allowed, in case a registrant decides not to attend.

Fee Policy: Lecture Batch registration fees may change without warning for future lectures.







Computer Vision and Machine Learning (CVML) Live Web Lecture Series

Artificial Intelligence and Information analysis (AIIA) Lab, AUTH is proud to launch the live CVML Web lecture series that will cover very important topics Computer vision/machine learning. Lectures will be delivered by Prof. Ioannis Pitas (Head of AIIA Lab, IEEE Fellow, IEEE Distinguished speaker, EURASIP fellow), aiming at providing in-depth knowledge on various CVML topics. Also top scientists internationally may occasionally deliver some lectures, A lecture batch (two consecutive 45 min lectures) will take place on Wednesdays, to avoid conflicts with other intended registrant schedules/duties:

Wednesdays 17:00-18:30 EEST (7:00-8:30 am California time, 10:00-11:30 am New York time, 22:00-23:30 Beijing time).

 (Lectures 15 and 16 will be delivered at 19:30-21:00 EEST on June 17th)

Each lecture batch will be announced at least 1 week in advance  in the CVML web lecture series www page (this one) and also in various relevant email lists. Each lecture will be self-sufficient and may be attended by registrants independently from other lectures, if so desired. Lectures will be selected and announced from the attached ‘Tentative CVML Web Lecture List’ (see below), which will be steadily enriched with new lecture topics. Of course, regular participation in the CVML web lecture series will facilitate understanding the entire CVML domain and its subdomains.

Due to multiple requests (as a result of different time zones), asynchronous Web Lecture Series is now foreseen: You can now register to access and study at your pace previous lecture batch material:

a) lecture ppt/pdf,

b) recorded video,

c) lecture understanding questionnaire

d) lecture evaluation form.

Questions on lecture material can also be sent off-line to orestiss@csd.auth.gr. All other CVML web lecture series rules apply also to the asynchronous mode.

Lectures will be selected and presented in such a way so that 14 consecutive lectures (7 lecture batches) form a CVML web course, roughly corresponding to one semester senior undergraduate or graduate ECE/CS/EE course. The CVML web course Computer vision and machine learning for autonomous systems’ (see below) will be delivered on Wednesdays April-June 2020.

Lectures will consist primarily of live lecture streaming and PPT slides. Attendees (registrants) need no special computer equipment for attending the lecture. They will receive the lecture PDF before each lecture and will have the ability to ask questions real-time. Audience should have basic University-level undergraduate knowledge of any science or engineering department (calculus, probabilities, programming, that are typical e.g., in any ECE, CS, EE undergraduate program). More advanced knowledge (signals and systems, optimization theory, machine learning) is very helpful but nor required.

The CVML web lecture series content, lecture timing and exact lecture topics may vary from the above ones depending on intended audience interest and lecturer availability.

The CVML web lecture series is expected to last till 30th August 2020 (end of the academic year 2019-2020). It will contain max 42 lectures (max 3×13 weeks), organized in batches of 2 lectures per week (lasting 1 1/2 consecutive hours per batch). A new series will start on September 2020 for the  academic year 2020-2021.






Computer vision and machine learning for autonomous systems’

16 lectures. One lecture batch (two 45 min lectures) each Wednesday 17:00-18:30 EEST (7:00-8:30 am California time, 10:00-11:30 am New York time, 22:00-23:30 Beijing time).

 (Lectures 15 and 16 will be delivered at 19:30-21:00 EEST on June 17th)

Lecture list

  1. Introduction to autonomous systems  (delivered 25th April 2020)
  2. Introduction to computer vision   (delivered 25th April 2020)
  3. Image acquisition, camera geometry   (delivered 2nd May 2020)
  4. Stereo and Multiview imaging   (delivered 2nd May 2020)
  5. Structure from Motion (delivered 9th May 2020)
  6. 2D convolution and correlation (delivered 9th May 2020)
  7. Motion estimation (delivered 20th May 2020)
  8. Introduction to Machine Learning  (delivered 20th May 2020)
  9. Artificial Neural Networks, Perceptron (delivered 27th May 2020)
  10. Multilayer perceptron, Backpropagation (delivered 27th May 2020)
  11. Deep Learning. Convolutional Neural Networks (delivered 3rd June 2020)
  12. Deep Object Detection (delivered3rd June 2020)
  13. Object tracking (delivered 10th June 2020)
  14. Localization and mapping (delivered 10th June 2020)
  15. Deep Semantic Image Segmentation (delivered 17th June 2020) 
  16. CVML software development tools  (delivered 17th June 2020) 






After the registration cutoff date/time, you will receive a link on how to attend the web lecture,
also containing:

a) lecture PDF
b) lecture questionnaire
c) lecture evaluation form.

Each lecture has a) a main lecturer, b) a tutor and c) administrator.
Lecture language will be English.

The tool ‘Skype for Business’ will be used for web lecturing (PDF+live lecturer video+ questions using chat/audio).
It is strongly recommended you join the lecture 10 min before its formal start, to have an informal chat with the lecturer and other attendants on general topics and have the feeling of a real live class.
During lecture, you can ask questions any time by chat to be replied by the lecture tutor, or afterwards by email, in case they are many. Live audio questions will be allowed in the middle and the end of the lecture (around min 25 and min 40). Live discussion on general topics will follow for another 10 min after the formal end of the lecture batch.

If you want to receive a certificate of lecture attendance with mark (in the range 0-10, 10 being the best mark, 5 being the pass mark), you have to submit to the lecture administrator (orestiss@csd.auth.gr) within 48 hours after formal lecture end:
a) your replies to lecture questionnaire: very short replies (1-2 text lines) to each of 10 questions.
You should have no problem replying them within 5-10 min, if you understood the lecture topics

b) your filled lecture evaluation form.

If Asynchronous  Web Lecture Series is chosen, you can now register to access and study the lectures at your own pace. Questions on lecture material can also be sent off-line to orestiss@csd.auth.gr.

If somebody attends at least 12 of the 14 lectures of a CVML web course and delivers (a) above for all of them, she/he can get a certificate of attendance of each course mark (in the range 0-10, 10 being the best mark, 5 being the pass mark).

Registrants to each 14-lectures CVML web-course can be credited 2 ECTS.







Mathematical foundations of CV and ML

  1. Mathematical Analysis
  2. Geometry
  3. Linear Algebra
  4. Set theory
  5. Probability Theory
  6. Statistics

CVML programming

  1. GPU and multicore CPU architectures and computing
  2. CUDA
  3. CVML software development tools

Computer vision

  1. Introduction to computer vision
  2. Digital images and videos
  3. Image acquisition, camera geometry
  4. Computational optics
  5. Stereo vision
  6. Stereo and Multiview imaging
  7. Structure from Motion
  8. Shape from X
  9. Active and passive 3D reconstruction methods
  10. 3D Shape Representations
  11. 3D Robot Localization and Mapping
  12. Semantic 3D world mapping 
  13. 3D object localization
  14. Multiview object detection and tracking
  15. Shot types in cinematography
  16. Object pose estimation

Machine Learning

  1. Introduction to Machine Learning
  2. Data Clustering
  3. Distance based classification
  4. Bayesian Learning
  5. Parameter estimation
  6. Dimensionality reduction
  7. Graph-based Dimensionality reduction
  8. Semi-supervised learning/Label propogation
  9. Decision surfaces. Support Vector Machines
  10. Kernel methods
  11. Syntactic pattern recognition
  12. Artificial Neural Networks. Perceptron
  13. Multilayer perceptron. Backpropagation.
  14. Convolutional Neural Networks
  15. Spiking Neural Networks
  16. Recurrent Neural Networks
  17. Deep Reinforcement Learning
  18. Object Detection
  19. Advanced Object Detection
  20. Few shot object recognition
  21. Deep Autoencoders
  22. Deep Semantic Image Segmentation
  23. Generative Adversarial Networks
  24. Synthetic map generation
  25. DNN privacy protection
  26. ML for image indexing and retrieval
  27. Deep segmentation

Autonomous systems

  1. Introduction to autonomous systems
  2. Introduction to ROS
  3. Autonomous systems sensors
  4. Drone and robot swarms
  5. Privacy protection, ethics and regulations in AS
  6. 5G/IoT for autonomous systems communications

Autonomous cars

  1. Introduction to autonomous car vision
  2. 3D Road Surface Reconstruction
  3. Road condition assessment
  4. Street environment perception
  5. Road traffic monitoring
  6. Autonomous car control

Autonomous drones

  1. Introduction to UAV multicopters
  2. Multiple drone mission planning and control
  3. Multiple drone Imaging for media production
  4. Drone cinematography
  5. Drone HCI
  6. Multiple drone system architecture
  7. Multiple Drone Communications
  8. Cinematography Issues in sports filming
  9. Imaging for Drone Safety
  10. Drone regulatory issues
  11. Drone mission simulations
  12. Multiple Drone media production
  13. Multidrone Datasets
  14. UAV infrastructure inspection

Autonomous Marine Systems

  1. Autonomous marine surface vessels
  2. Autonomous underwater vessels

Signal and systems

  1. Fast convolution algorithms

Image processing

  1. Introduction to Image Processing
  2. Image sampling
  3. 2D systems
  4. 2D Digital Filter Design and Realization
  5. Fast 2D convolution algorithms
  6. Image transforms
  7. Digital Image Formation
  8. Image Perception
  9. Color Theory
  10. Image quality
  11. Computational aesthetics
  12. Digital Image Filtering
  13. Image compression
  14. Edge detection
  15. Region segmentation
  16. Image Features
  17. Shape description
  18. Mathematical Morphology

3D Image processing

  1. Introduction to 3D Image Processing
  2. Medical image acquisition
  3. 3D Image and Video Quality
  4. 3D Data Processing
  5. 3D Image and Shape Compression
  6. 3D Video Coding And Broadcasting
  7. 3D Image and Video Analysis
  8. Image/volume registration
  9. Image Rendering and View Synthesis
  10. 3D Video Content Description
  11. 3D Display Technologies
  12. Immersion in Virtual Reality

Video processing

  1. Introduction to Video Processing
  2. Fast 3D convolutions for deep video analysis
  3. Video Digitization
  4. Moving Image Perception
  5. Video Filtering
  6. Video streaming
  7. Motion Estimation
  8. 2D visual object tracking
  9. Joint Detection and Tracking
  10. Τransform video compression
  11. Video indexing and retrieval
  12. Video Description
  13. 2D/3D Video Production

Human centered computing

  1. Introduction to human centered computing
  2. Face/Head Detection
  3. Person Detection. Pedestrian detection.
  4. Crowd detection
  5. Face Recognition
  6. Face Verification and clustering
  7. Facial expression recognition
  8. Human Action Recognition
  9. Gesture recognition
  10. Ηuman body pose estimation
  11. Facial Features Detection
  12. Visual speech recognition
  13. Sports  video analysis
  14. Athlete motion analysis
  15. Anthropocentric video description schemes

Social media analysis

  1. Graphs in social and digital media
  2. Algebraic graph analysis
  3. Web search based on ranking
  4. Information diffusion
  5. Graph signal processing
  6. Matrix and Tensor Factorization for Recommendation Systems
  7. Big Data Analytics for Social Networks
  8. Big Graph Storage, Processing and Visualization







  1. Prof. I. Pitas Google scholar: https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=el
  2. AERIAL-CORE R&D Project (AERIAL COgnitive integrated multi-task Robotic system with Extended operation range and safety) funded by the EU (2019-2), within the scope of the H2020 framework. URL: https://aerial-core.eu/
  3. Multidrone R&D Project (MULTIple DRONE platform for media production), funded by the EU (2017-19), within the scope of the H2020 framework. URL: https://multidrone.eu/
  4. Artificial Intelligence and Information analysis (AIIA) Lab www.aiia.csd.auth.gr