Computational Aspects Of Multi Scale Optical Flow

Computational Aspects of Multi-scale Optical Flow

Front-End Vision and Multi-Scale Image Analysis

Many approaches have been proposed to solve the problem of finding the optic flow field of an image sequence. Three major classes of optic flow computation techniques can discriminated (see for a good overview Beauchemin and Barron IBeauchemin19951): gradient based (or differential) methods; phase based (or frequency domain) methods; correlation based (or area) methods; feature point (or sparse data) tracking methods; In this chapter we compute the optic flow as a dense optic flow field with a multi scale differential method. The method, originally proposed by Florack and Nielsen [Florack1998a] is known as the Multiscale Optic Flow Constrain Equation (MOFCE). This is a scale space version of the well known computer vision implementation of the optic flow constraint equation, as originally proposed by Horn and Schunck [Horn1981]. This scale space variation, as usual, consists of the introduction of the aperture of the observation in the process. The application to stereo has been described by Maas et al. [Maas 1995a, Maas 1996a]. Of course, difficulties arise when structure emerges or disappears, such as with occlusion, cloud formation etc. Then knowledge is needed about the processes and objects involved. In this chapter we focus on the scale space approach to the local measurement of optic flow, as we may expect the visual front end to do. 17. 2 Motion detection with pairs of receptive fields As a biologically motivated start, we begin with discussing some neurophysiological findings in the visual system with respect to motion detection.

Bioinspired Models of Network, Information, and Computing Systems

This volume of LNICST is a collection of the papers of the 4th International Conference on Bio-Inspired Models of Network, Information, and Computing Systems (Bionetics). The event took place in the medieval city of Avignon, known also as the City of the Popes, during December 9 to 11, 2009. Bionetics main objective is to bring b- inspired paradigms into computer engineereing and networking, and to enhance the fruitful interactions between these fields and biology. The program of the conference indeed includes applications of various paradigms that have their origin in biology: population dynamics, branching processes, ant c- ony optimization. The proceedings include 19 papers covering a broad range of - portant issues in areas related to bio-inspired technologies. They correspond to pr- entations at 6 technical sessions. Four papers correspond to an invited session on the Epidemic-type forwarding in DTNs (sparse mobile ad-hoc wireless networks) org- ized by Dr Francesco De Pellegrini, (Italy, CREATE-NET). The following 9 papers (selected out of 15 submissions) correspond to contributions to regular sessions on Bio-inspired security, Bio-Inspired Networking, Bioinspired algorithms and software systems. The remaining 6 papers (selected out of a total of 9 submissions) are de- cated to work in progress. For each paper, we have provided at least two independent reviews, most of which were offered by members of the TPC.