No abstract

This paper presents our approach to retrieve a dependable three-dimensional description of a partially known indoor environment. W e describe the way the sensor data f r o m a video camera is preprocessed b y contour tracing to extract the boundary lines of the objects and how this information is transformed into a three-dimensional environmental model of the world. W e introduce a dynamic map that operates in a closed loop with various sensor systems improving their performance by filtering and contributing certain knowledge. The filtering relies on the capability of a mobile robot to gather sensor readings f r o m different positions. A n important part of our approach is the interaction between the dynamic map, storing and filtering the incoming information, and a module predicting missing sensor features based on structures andreference objects. This interaction helps to generate a more accurate model containing also poor detectable features, that are impossible to extract from a single sensor view. 0-7803-3612-7-4/97 $5.00 0 1997 IEEE

No abstract

Robust and rapid object recognition in unprepared environments and under poor illumination conditions is a major task in computer vision. The presented approach integrates proven techniques and original approaches to one robust and fast 3 0 model-based recognition system.A speedy recognition is achieved by operating on a stream of filtered 30 sensor features, reconstructed for navigation tasks of the robot, instead of using a separate sensor data processing. Furthermore, simple, inexpensive recognition strategies are applied. Robustness is obtained by integrating complementary recognition strategies: four indexing techniques and two ( 2 0 and 3 0 ) matching methods for verification, are completed by a hypothesis promotion, based on feedback of information to the sensor system. All strategies differ in their requirements, reliability, selectivity, and temporal constraints. Hypotheses are integrated using fusion, ruling out, and aging techniques. The approach is evaluated in more than one-thousand experiments with varying calibration errors, scene complexity, and sensing conditions.

No abstract