Guido Tascini

Imaging approach to real-time tracking of submarine pipeline

The work presents a real-time underwater imaging system for identification and tracking of a submarine pipeline on a sequence of recorded images. The main novelty of this work relies on adopting an automatic approach that is entirely based on the analysis and interpretation of visual data, in spite of the various limitations upon the ability to image underwater objects. The analysis of the data is performed starting from image processing operations (like filtering, profile analysis, feature enhancement) implemented on a dedicated board. Then, the system employs an efficient dynamic process for recognizing the two contours of the pipeline. In each frame the system is able to determine the equations of the two straight lines corresponding to the pipeline contours. The system reaches satisfactory performances in real time operation: up to eight frames per second on a Pentium based PC. The results of this work are somewhat more meaningful as the input images were acquired by three cameras, mounted on a remotely operated vehicle travelling at one nautical mile an hour, without any attention either to illumination conditions or stability of cameras. This work is originated from the interest of Snamprogetti in enhancing the level of automation in submarine pipeline inspection.

Retina vascular network recognition

The analysis of morphological and structural modifications of the retina vascular network is an interesting investigation method in the study of diabetes and hypertension. Normally this analysis is carried out by qualitative evaluations, according to standardized criteria, though medical research attaches great importance to quantitative analysis of vessel color, shape and dimensions. The paper describes a system which automatically segments and recognizes the ocular fundus circulation and micro circulation network, and extracts a set of features related to morphometric aspects of vessels. For this class of images the classical segmentation methods seem weak. We propose a computer vision system in which segmentation and recognition phases are strictly connected. The system is hierarchically organized in four modules. Firstly the Image Enhancement Module (IEM) operates a set of custom image enhancements to remove blur and to prepare data for subsequent segmentation and recognition processes. Secondly the Papilla Border Analysis Module (PBAM) automatically recognizes number, position and local diameter of blood vessels departing from optical papilla. Then the Vessel Tracking Module (VTM) analyses vessels comparing the results of body and edge tracking and detects branches and crossings. Finally the Feature Extraction Module evaluates PBAM and VTM output data and extracts some numerical indexes. Used algorithms appear to be robust and have been successfully tested on various ocular fundus images.

Detour Behaviour in Evolving Robots: Are Internal Representations Necessary?

Internal representations of the environment are often invoked to explain performance in tasks in which an organism must make a detour around an obstacle to reach a target and the organism can lose sight of the target along the path to the target. By simulating a detour task in evolving populations of robots (Khepera) we show that neural networks with memory units perform better than networks without memory units in this task. However, the content of the memory units need not be interpreted as an internal representation of the position of target. The memory units send a time-varying internally generated input to the networks hidden units that allows the network to generate the appropriate behavior even when there is no external input. Networks without memory units do not have this internal input and this explains their inferior performance.

Real-time inspection by submarine images

A real-time application of computer vision concerning tracking and inspection of a submarine pipeline is described. The objective is to develop automatic procedures for supporting human operators in the real-time analysis of images acquired by means of cameras mounted on underwater remotely operated vehicles (ROV). Implementation of such procedures gives rise to a human- machine system for underwater pipeline inspection that can auto- matically detect and signal the presence of the pipe, of its structural or accessory elements, and of dangerous or alien objects in its neighborhood. The possibility of modifying the image acquisition rate in the simulations performed on video-recorded images is used to prove that the system performs all necessary processing with an acceptable robustness working in real-time up to a speed of about 2.5 kn, widely greater than that the actual ROVs and the security features allow.

Navigation with memory in a partially observable environment

Abstract The paper presents an architecture that allows the reactive visual navigation via an unsupervised reinforcement learning. This objective is reached using Q -learning and a hierarchical approach to the developed architecture. Using these techniques requires a deviation from the Partially Observable Markov Decision Processes (POMDP) and some innovations: heuristic techniques for generalizing the experience and for treating the partial observability; a technique for the speed adjournment of the Q function; the definition of a special reinforcement policy adequate for learning a complex task without supervision. The result is a satisfactory learning of the navigation assignment in a simulated environment.

Self-Organizing Maps versus Growing Neural Gas in a Robotic Application

The paper proposes a method for visual based self-localisation of a mobile agent in indoor environment. The images acquired by the camera constitute an implicit topological representation of the environment. The environment is a priori unknown and so the implemented architecture is entirely unsupervised. To compare the performance of some self-organising neural networks, a similar neural network architecture of both Self-Organizing Map (SOM) and Growing Neural Gas (GNG) has been realized. Extensive simulations are provided to characterise the effectiveness of the GNG model in recognition speed, classification tasks and in particular topology preserving as compared to the SOM model. This behaviour depends on the following fact: a network (GNG) that adds nodes into map space can approximate the input space more accurately than a network with a predefined structure and size (SOM). The work shows that the GNG network is able to correctly reconstruct the environment topological map.

Fingerprints Recognition Using Minutiae Extraction: a Fuzzy Approach.

The aim of this paper is to study the fingerprint verification based on local ridge discontinuities features (minutiae) only using grey scale images. We extract minutiae using two algorithms those following ridge lines and then recording ridge endings and bifurcations. Moreover we use a third algorithm able to develop a minutiae verification processing a local area using a neural network ( multilayer perceptron). Fingerprint distortion is filtered using a minutiae whole representation based on regular invariant moments. The results of the three minutiae extraction algorithms are joined during the minutiae pattern matching phase for fingerprint verification. Here we propose a new method of matching that use fuzzy operator to bypass the problem of different numbers of minutiae extracted from the algorithms. Experimental evidences show fingerprint recognition up to 95%.

Neural Networks for Region Detection

The paper proposes a neural network organized in three structures , each of which is constituted by a set of levels . The lower structure is made up of two layer groups the first one filters the high frequency noise , while the second one is sensitive to scarcely lighted images . Finally the third structure detects contour and position of regions . The network uses neurons of C , S and V type in analogy to Fukushima Neo-Cognitron . A simulation program has been implemented, which shows good throughput in spite of network complexity.

Image sequence recognition

Image sequence recognition is an interesting problem involved in various situations of the Computer Vision field and in particular in mobile robot vision. Typical for this purpose is the motion estimation from a series of frames. Many techniques of motion estimation are described in literature 10, 13, 22 The approaches are normally divided in two categories: pixel based methods and feature based methods. In both the motion is estimated in two steps: 1) 2D motion analysis (feature based) or estimation (pixel based), 2) 3D motion estimation. The pixel based, or flow based, method uses local changes in light intensity to compute optical flow at each image point and then derives 3D motion parameters . The feature based method, on which it falls our choice, firstly extracts the features (as corners, point of curvature, lines, etc.). They are used as features: sharp changes in curvature 15, global properties of moving objects 18, lines and curves 16, centroids 6 Secondly it establishes the correspondences of these features between two successive frames (correspondence problem), and finally it computes motion parameters and object structure from correspondences (structure from motion problem). The motion correspondence is the most difficult problem. Occlusion masks the features and noise creates difficulties. Given n frames taken at different time instants and m points in each frame, the motion correspondence maps a point in one frame to another point in the next frame such that no two points map on the same point. The combinatorial explosiveness of the problem has to be constrained; in Rangarajan and Sah 19 it is proposed the proximal uniformity constraint: given a location of a point in a frame, its location in the next frame lies in the proximity of its previous location. Even tough the problem has not yet been solved, many solutions are proposed for 3D motion estimation, assuming that the correspondences has been established 12, 13, 24 Regularization theory has also been proposed for the numerical improvement of the solution of both feature based and pixel based problems . From the human stand point a vision system may be viewed as performing the following tasks in sequence: detection, tracking and recognition. The detection rises at cortex level; then it follows the tracking of objects contemporary attempting to recognize them. From the machine stand point the movement detection phase may be viewed as a useful mean to focus the system attention so reducing the search space of the recognition algorithms. Particular attention has to be reserved in detecting moving objects in presence of moving background, from monocular image sequence. Several researchers have faced the problem 14, 21 When we take the images from a moving vehicle (for instance with translational movement) it is necessary to distinguish between real and apparent movement. The stationary objects of the scene appear to move along paths radiating from the point toward which we are moving (focus of expansion). By operating a transformation on the image, called Complex Logarithmic Mapping (see Frazier-Nevatia 8), it is possible to convert the problem from one of detecting motion along both the X and Y axes to one of detecting motion from along an angular axis. After executing an horizontal edge detection, if we observe the motion of edges in the vertical direction we can conclude that there is a moving object in the scene. Our approach is feature based and a series of considerations are necessary to understand the solution adopted. We regard as features edges, corners or whole regions. The choice of a feature depends on the facility of retrieving it in the successive frames, forming a correspondence chain. The corner detection may be based on revealing the sharply direction change of intensity gradient. In Rangarajan et al. 20 it is described the construction of a set of operators to detect corners. Being the corners the mainly used features particular attention has been devoted to correspondences among points. For these they may be adopted two approaches: 1) with matching, in which two point patterns, from two consecutive images, are matched (elastic matching 25); 2) without matching, by using the criteria of proximity and regularity of point trajectories. Our approach uses two types of matching: geometric and relational. The geometric matching uses parametrized geometric models and may be viewed as a parametrized optimization problem. The relational matching uses relational representations and may be viewed as the problem of detecting the isomorphism among graphs.

Scale Free Graphs in Dynamic Knowledge Acquisition

Classical representation forms are not suited to represent knowledge as human mind does. In tasks as discourse comprehension knowledge stuctures have to adapt themselves on the basis of the objectives, the past experiences and the particular context. So we have developed a modular knowledge acquisition system based on cognitive criteria, that dynamically updates a representation by the use of a scale free graph model.