We discuss a definition of Morphological Cellular Neural Networks (MCNN) where the state change operator are Auto-associative Morphological Memories (AMM). The fast convergence properties of AMM and the shape of its fixed point set make the MCNN dynamics trivial. However, segmentation results are poor. We propose a Morphological Cellular Automata (MCA) with assured convergence to a state charac...

Spatiotemporal feature learning in videos is a fundamental and difficult problem in computer vision. This paper presents a new architecture, termed as Appearanceand-Relation Network (ARTNet), to learn video representation in an end-to-end manner. ARTNets are constructed by stacking multiple generic building blocks, called as SMART, whose goal is to simultaneously model appearance and relation f...

This paper describes most recent development and demonstration of a VCSEL-based smart pixel array (SPA) technology for chip-to-chip interconnect. This technology is based on Honeywell's commercial successful 850nm VCSEL components, incorporates both monolithic and hybrid integration techniques, and aims to address anticipated interconnect bottleneck in networking interconnect fabric and between...

Optical transimpedance receivers implemented in CMOS VLSI technologies are modeled and optimized for freespace optoelectronic interconnections. Sensitivity, bandwidth, power dissipation, and circuit area are analyzed for receivers using three different submicron CMOS processes. A comparison with the circuit noise limited optical power indicates that, for digital computing applications, the rece...

Smart lock-in pixels for real-time range imaging have been developed at CSEM during the last few years. These pixels, based on a combined CCD/CMOS process, are capable of demodulating intensity-modulated optical signals in parallel. By integrating some hundreds or thousands of them on one single chip, real-time 3D-imaging becomes possible by indirectly measuring the time-of-flight. The basic ch...

Computer-assisted vision plays an important role in our society, in various fields such as personal and goods safety, industrial production, telecommunications, robotics, etc. However, technical developments are still rare and slowed down by various factors linked to sensor cost, lack of system flexibility, difficulty of rapidly developing complex and robust applications, and lack of interactio...

For most sub-Saharan African (SSA) cities, in order to control the historically unplanned urban growth and stimulate sustainable future urban development, there is a need for accurate identification of the past and present urban land use (ULU). However, studies addressing ULU classification in SSA cities are lacking. In this study, we developed an integrated approach of remote sensing and Geogr...