A review on strategies for recognizing natural objects in colour images ofoutdoor scenes

This paper surveys some significant vision systems dealing with the recogni tion of natural objects in outdoor environments. The main goal of the paper is to discuss the way in which the segmentation and recognition processes are performed: the classical bottom-up, top-down and hybrid approaches are discussed by reviewing the strategies of some key outdoor scene understandi ng systems. Advantages and drawbacks of the three strategies are presented. Considering that outdoor scenes are especially complex to treat in terms o f lighting conditions, emphasis is placed on the way systems use colour for segmentation and characterization proposals. After this study of state-of- the-art strategies, the lack of a consolidated colour space is noted, as we ll as the suitability of the hybrid approach for handling particular proble ms of outdoor scene understanding. (C) 2000 Elsevier Science B.V. All right s reserved.