Some applications of computer vision in transport engineering: Computer vision research has been making steady progress for the last 20 years or so. Its practical applications are many and many of them are becoming established such as automatic licence plate recognition, smartphone camera control, simple surveillance, highway traffic flow and more recently autonomous driving. The talk will present some examples of what computer vision systems can do in applications such as passenger monitoring in public transport networks and vehicle monitoring in urban traffic and especially on detecting motorbikes, a mode of transport popular in emerging countries but whose riders are involved in many fatal transport accidents.

Applications of vector-valued image processing in brain imaging: Since the discovery of X-rays in 1895, medical imaging has known a very strong development that has accelerated in the last decades, leading to various imaging modalities such as Positron Emission Tomography, Magnetic Resonance Imaging or Raman spectroscopy. The increasing complexity and variety of the data has created a challenge to obtain meaningful insights from the information that is available. In particular, most of these new imaging modalities provide vector-valued data for which specific image processing approaches need to be developed. In this talk, I will present three recent works for PET image reconstruction, analysis and MRI tractography validation based on variationnal models, spectral unmixing, and stereo vision with haptic rendering.

Introduction to Word Embedding Models: Word embedding involves a set of language modelling and feature learning techniques in Natural Language Processing (NLP) where words or phrases from the vocabulary are mapped into vectors of real numbers. Classical methods to generate this mapping include neural networks-based techniques (i.e., Word2vec, Skip-Gram), Lexical Semantics based on dimensionality reduction, probabilistic models, etc. Word embeddings have shown to improve the performance in many NLP tasks such as sentiment analysis, semantic tagging, etc. In this talk, I will provide a brief introduction to word embedding techniques (i.e., LSA, Word2vec, Skip-gram, etc), current problems and challenges and applications in NLP and data analytics.

X-ray Computer Vision for Baggage Inspection: X-ray screening systems have been used to safeguard environments in which access control is of paramount importance. Security checkpoints have been placed at the entrances to many public places to detect prohibited items such as handguns and explosives. Generally, human operators are in charge of these tasks as automated recognition in baggage inspection is still far from perfect. Research and development on X-ray testing is,however, exploring new approaches based on computer vision that can be used to aid human operators. In this talk, we present the state of the art in computer vision for baggage inspection: several methods will be explained and evaluated. They are based on bag of words, sparse representations, deep learning and classic pattern recognition schemes among others. For each method, we i) present a brief explanation, ii) show experimental results on the same database, and iii) provide concluding remarks discussing pros and cons of each method.