Maciej Polanczyk

A remote guidance system for the blind

This paper explains the concept and reports tests of a remote guidance system for the blind. The system comprises two parts - a remote operators terminal and a blind persons mobile terminal. The mobile terminal is a small electronic device which consists of a digital camera, GPS receiver and a headset. The two terminals are wirelessly connected via GSM and the Internet. The link transmits video from the blind traveller, GPS data and provides duplex audio communication between the terminals. The GPS location of the blind traveller and real time video captured from the mobile camera are displayed on the remote operators terminal. The remote operator can navigate the traveller to a destination point and warn him of dangerous obstacles. System trials were carried out in an urban environment. As the system is in the development stage, mainly emphatic trials have been conducted so far. In this paper we list the main functional features of the system, its advantages and current shortcomings.

Programming Symbian Smartphones for the Blind and Visually Impaired

A set of software procedures for the Symbian OS mobile smartphone making the device more easily usable for a blind user is described in the paper. The application was written in the Carbide C++ environment, tested both on the S60 series phone emulator and the phone platform itself. The main task was to create a dedicated speech enabled menu, rather than a simple screen reader. Along with ordinary phone functions (calls, SMSs) the programmed phone can be used as a speech recorder, a web browser (RSS feeds are used), and a colour recognizer in images captured by the phone’s camera. Added functionality makes the smartphone a very useful personal assistance tool for the blind who tested the developed application.

Stereovision-based obstacle avoidance procedure for autonomous mobile platforms

The paper presents a procedure for collision-free guidance of autonomous mobile platforms through unknown environments. |Stereovision images are used to determine and keep track of an obstacle map, which provides a basis for path-planning The main problem that has to be solved in obstacle map derivation is elimination of artifacts resulting from depth estimation. We propose a two-step artifact filtering procedure, which exploits both withinframe spatial correlations as well as temporal, between-frame correlations to do this task. Experiment results prove efficiency of the adopted approach for platform operation in real environments, where both static and moving obstacles are present.

Lee-algorithm based path replanner for dynamic environments

The presented paper introduces a new procedure, based on well-known Lees algorithm, for vehicle collisionless path determination in dynamically-changing environments. Such routes need to be updated on-the-fly to take into account moving obstacles or newly detected objects. The main idea of the proposed approach is to first, identify regions where environment has changed and to execute a procedure of selective path updates. As a result, an optimal path can be derived at a computational expense comparable to the heuristic Lifelong A* search.

Road Lane Detection with Elimination of High-Curvature Edges

The following paper proposes a procedure for an automatic detection of road-lanes, which involves three main steps: two-category scene segmentation, a detection of lane segment candidates and decision making. The main contribution of the paper is an introduction of a new step - high-curvature edge filtering - into a typical road image processing. This step substantially reduces an amount of noise and yields an improved lane detection performance. The remaining two steps of lane detection are dynamic programming-based selection of line segments, and Hough transform-based selection of the most consistent segments. The proposed approach proved to produce good results for a variety of real-traffic conditions, including correct detection in heavily shadowed road images.

Disparity Map Based Procedure for Collision-Free Guidance through Unknown Environments

The paper presents an algorithm for building a map of obstacles and guiding an autonomous mobile platform in an unknown and changing environment. Depth images captured from a stereovision camera are used to detect objects and denote their location on the obstacle map. The depth images acquired from the stereocamera are encumbered with artefacts which poses the main problem in detecting obstacles. We propose a two-step filtering algorithm which is based on morphological operations and Bayesian inference. Experimental results proved the efficiency of the solution in the real environment wherein both static and mobile obstacles are present.

Lee path replanner for partially-known environments

This paper presents a new routing algorithm based on Lees algorithm. The latter was developed with view to designing printed circuit boards (PCB). It can also be adapted for seeking collisionless routes for unmanned vehicles moving in an unknown environment. Such routes need to be updated on-the-fly, taking into account changes in the environment, e.g. moving obstacles, newly detected objects. The proposed algorithm uses results from the calculations carried out in the previous steps. Hence, computations in the following steps are only required for the areas that were subject to change. Tests showed that the presented route replanner is, on average, twice as fast as Lees algorithm.