Andrea Zanela

Sensing the third dimension in stereo vision systems: a cellular neural networks approach

Abstract In this paper the use of the cellular neural network (CNN) paradigm is investigated for the vision-based real-time guidance of robots. This paradigm is employed in recovering information on the tridimensional structure of the environment, through the resolution of the static and the lateral motion stereo vision problems. The proposed approaches exploit the spontaneous internal energy decrease of the CNN, coding the problem in terms of an optimisation task. Results of computer simulations on some test cases for the two different issues are provided. The performance of a hardware implementation of these networks for the tasks presented is outlined.

Cellular neural networks for the stereo matching problem

The applicability of the cellular neural network (CNN) paradigm to the problem of recovering information on the 3D structure of the environment is investigated. The approach proposed is the stereo matching of video images. The starting point of this work is the Zhou-Chellappa neural network implementation (1992) for the same problem. The CNN based system we present here yields the same results as the previous approach, but without the many existing drawbacks.

Cellular neural networks: a genetic algorithm for parameters optimization in artificial vision applications

An optimization method for some of the CNNs parameters, based on evolutionary strategies, is proposed. The new class of feedback template found is more effective in extracting features from the images that an autonomous vehicle acquires, than in the previous CNNs literature.

A dedicated hardware system for CNN stereo vision

The stereo vision algorithm is a very promising technique in autonomous robotics to sense the environment. A successful implementation of this algorithm on Cellular Neural Networks (CNN) has been proposed. In this paper an analogue CNN hardware system able to perform such an algorithm is presented. This new system will be installed directly onto the robot and plays the role of a parallel analogue coprocessor.

A cellular neural network stereo vision system for autonomous robot navigation

A complex sensor based control system is presented. The sensor used is a pair of TV cameras providing a stereogram for a stereo vision system based on a cellular neural network. The information thus extracted is used to perform indoor navigation of a robotised platform. Experimental data are provided for a simulated version of the CNN employed. Details of the in progress hardware implementation of the neural system are given.

Improving a Real-Time Neural-Based Stereo Vision System

Refinements of the energy expression of a real-time neural-based stereo vision system are presented. The neural network optimizes a scalar functional, that represents an area-based stereo matching algorithm. The neural system is reviewed and its performances presented. The proposed improvements are in terms of the exploitation of the image chromatic content and of local pixel information relative to the distance from an image feature. Experimental results showing the performance improvements are presented on synthetic and on real images. The hardware implementation currently in progress will straightforwardly benefit from these improvements.

A practical use of cellular neural networks: the stereo-vision problem as an optimisation

Abstract. A variational way of deriving the relevant parameters of a cellular neural network (CNN) is introduced. The approach exploits the CNN spontaneous internal-energy decrease and is applicable when a given problem can be expressed in terms of an optimisation task. The presented approach is fully mathematical as compared with the typical heuristic search for the correct parameters in the literature on CNNs. This method is practically employed in recovering information on the three-dimensional structure of the environment, through the stereo vision problem. A CNN able to find the conjugate points in a stereogram is fully derived in the proposed framework. Results of computer simulations on several test cases are provided.

A robustness study of a CNN based stereo vision algorithm

The development of an effective system for autonomous robot navigation can find a valid support from the CNN approach. In the paper some measurements of the robustness of a stereo vision algorithm based on the CNN paradigm are presented. The sensitivity of the algorithm to the difference in luminosity and contrast of the images in the stereo pair, the presence of noise corrupting the images and problems of misalignment in the experimental set-up are investigated.

A cellular neural network based optical range finder

An optical range finder based on the CNN paradigm is presented. It exploits a variational formulation of the stereo-vision problem. The device characteristics are assessed and some experiments are presented relative to two robotic tasks: the self-localization of an autonomous vehicle and an obstacle detection system. Copyright

Neural-based system for obstacle detection and scene reconstruction

A stereo vision based obstacle detection system is presented. The matching process on the input stereogram is performed as an optimisation of an energy functional through a variational approach yielding dense disparity maps. The energy minimisation is implemented by a Cellular Neural Network. The state of the art of the hardware implementation of the system is presented. Some experiments on the use of the system in outdoors applications are shown. These tests demonstrate the feasibility of an obstacle detection system for an autonomous surveillance robotic platform. The real time characteristics of the hardwired version of the algorithm will allow the temporal, and spatial, integration of data, with a considerable reduction in other otherwise unavoidable data noise.