This study investigates the use of simple, low-cost infrared sensors for the recognition of geometry and surface type of commonly encountered features or targets in indoor environments, such as planes, corners, and edges. The intensity measurements obtained from such sensors are highly dependent on the location, geometry, and surface properties of the reflecting target in a way that cannot be represented by a simple analytical relationship, therefore complicating the localization and recognition process. We employ artificial neural networks to determine the geometry and the surface type of targets and provide experimental verification with three different geometries and three different surface types. The networks are trained with the Levenberg–Marquardt algorithm and pruned with the optimal brain surgeon technique. The geometry and the surface type of targets can be correctly classified with rates of 99 and 78.4%, respectively. An average correct classification rate of 78% is achieved when both geometry and surface type are differentiated. This indicates that the geometrical properties of the targets are more distinctive than their surface properties, and surface determination is the limiting factor in recognizing the patterns. The results demonstrate that processing the data from simple infrared sensors through suitable techniques can help us exploit their full potential and extend their usage beyond well-known applications.
We differentiate surfaces with different properties with simple low-cost IR emitters and detectors in a location-invariant manner. The intensity readings obtained with such sensors are highly dependent on the location and properties of the surface, which complicates the differentiation and localization process. Our approach, which models IR intensity scans parametrically, can distinguish different surfaces independent of their positions. Once the surface type is identified, its position (r,) can also be estimated. The method is verified experimentally with wood; Styrofoam packaging material; white painted matte wall; white and black cloth; and white, brown, and violet paper. A correct differentiation rate of 100% is achieved for six surfaces, and the surfaces are localized within absolute range and azimuth errors of 0.2 cm and 1.1 deg, respectively. The differentiation rate decreases to 86% for seven surfaces and to 73% for eight surfaces. The method demonstrated shows that simple IR sensors, when coupled with appropriate signal processing, can be used to recognize different types of surfaces in a location-invariant manner.
We investigate the use of low-cost infrared (IR) sensors for the simultaneous extraction of geometry and surface properties of commonly encountered features or targets in indoor environments, such as planes, corners, and edges. The intensity measurements obtained from such sensors are highly dependent on the location, geometry, and surface properties of the reflecting target in a way that cannot be represented by a simple analytical relationship, therefore complicating the localization and recognition process. We propose the use of angular intensity scans and present an algorithm to process them to determine the geometry and the surface type of the target and estimate its position. The method is verified experimentally with planes, 90-deg corners, and 90-deg edges covered with aluminum, white cloth, and Styrofoam packaging material. An average correct classification rate of 80% of both geometry and surface over all target types is achieved and targets are localized within absolute range and azimuth errors of 1.5 cm and 1.1 deg, respectively. Taken separately, the geometry and surface type of targets can be correctly classified with rates of 99 and 81%, respectively, which shows that the geometrical properties of the targets are more distinctive than their surface properties, and surface determination is the limiting factor. The method demonstrated shows that simple IR sensors, when coupled with appropriate processing, can be used to extract substantially more information than that for which such devices are commonly employed.
Low-cost infrared emitters and detectors are used for the recognition of surfaces with different properties in a location-invariant manner. The intensity readings obtained with such devices are highly dependent on the location and properties of the surface in a way that cannot be represented in a simple manner, complicating the recognition and localization process. We propose the use of angular intensity scans and present an algorithm to process them. This approach can distinguish different surfaces independently of their positions. Once the surface is identified, its position can also be estimated. The method is verified experimentally with the surfaces aluminum, white painted wall, brown kraft paper, and polystyrene foam packaging material. A correct differentiation rate of 87% is achieved, and the surfaces are localized within absolute range and azimuth errors of 1.2 cm and 1.0 deg, respectively. The method demonstrated shows that simple infrared sensors, when coupled with appropriate processing, can be used to extract a significantly greater amount of information than they are commonly employed for.
We discuss the use of low-cost infrared sensors in differentiating and localizing commonly encountered target primitives in indoor environments, such as planes, corners, edges, and cylinders. Single intensity readings are highly dependent on target location and properties and this dependence cannot be represented simply. We propose a method that can achieve position-invariant target differentiation without relying on absolute intensity readings and verify it experimentally. The correct identification rates for planes, 90° corners and edges, and cylinders are 90%, 100%, 82.5%, and 92.5%, respectively. The distance of the target can be estimated with an average error of 0.59 cm and the azimuth angle can be estimated with an error of 1.58°.
We investigate the pre-processing of sonar signals prior to
using neural networks for robust differentiation of commonly
encountered features in indoor environments. Amplitude and time-of-flight measurement patterns acquired from a real sonar system are pre-processed using various techniques including wavelet transforms, Fourier and fractional Fourier transforms, and Kohonen's self-organizing feature map. Modular and non-modular neural network structures trained with the back-propagation and generating-shrinking algorithms are used to incorporate learning in the identification of parameter relations for target primitives. Networks trained with the generating-shrinking algorithm demonstrate better generalization and interpolation capability and faster convergence rate. The use of neural networks trained with the back-propagation algorithm, usually with fractional Fourier transform or wavelet pre-processing results
in near perfect differentiation, around 85% correct range estimation and around 95% correct azimuth estimation, which would be satisfactory in a wide range of applications. Neural networks can differentiate more targets, employing only a single sensor node,
with a higher correct differentiation percentage than achieved with previously reported methods employing multiple sensor nodes.
The success of the neural network approach shows that the sonar signals do contain sufficient information to differentiate a considerable number of target types, but the previously reported methods are unable to resolve this identifying information.
This work can find application in areas where recognition of patterns
hidden in sonar signals is required. Some examples are system control
based on acoustic signal detection and identification, map building,
navigation, obstacle avoidance, and target-tracking applications
for mobile robots and other intelligent systems.
The performance of a commonly employed linear array of sonar sensors is assessed for point- target localization. Two different methods of combining time-of-flight information from the sensors are described to estimate the range and azimuth of the target: pairwise estimate method and the maximum likelihood estimator. The biases and variances of the methods are investigated and their combined effect is compared to the Cramer-Rao Lower Bound. Simulation studies indicate that in estimating range, both methods perform comparably; in estimating azimuth, maximum likelihood estimate is superior at a cost of extra computation.
The problem of tracking and capturing a moving obstacle in two dimensions by a mobile robot equipped with a wide-beam sonar system is discussed. In a practical system the range and azimuth measurements contain random errors and are available over a limited region. This pursuer/prey problem is treated as a feedback control system for which the pursuer action is dependent on the observed measurements. Two measures of performance are considered: the capture probability and the mean capture time when capture occurs. The lower bound for the mean capture time is determined from game theory, which assumes complete information about the prey. Strategies employing either qualitative (prey is to the left or right) or quantitative (range and azimuth to prey) information are implemented and compared. It is found that qualitative information is sufficient for prey capture, although quantitative information allows more efficient prey capture.