The GEOBIA (GEOgraphic Object-Based Image Analysis) approach persists to reveal its effectiveness in remote sensing data analysis, which provides paradigms that integrate analyst’s expert knowledge to generate semantically meaningful image-segments. These segments might contribute to the reduction of problems associated with the analysis of the discrete spectral value of a pixel, such as illumination and shaded tree crowns. However, the challenge in this paper is to introduce a GEOBIA as a sophisticated framework toward the automation of forest structural attributes estimate. Optical sensor was examined to develop models for the estimation of forest attributes. Analyses were performed over a forested selected site in the Blue Nile region of Sudan. The framework of the present research involved; segment extraction, field sample selection, forest attributes generalization, model validation, and mapping the predicted attributes. The rationale for incorporating these data is to offer a semi-automatic GEOBIA approach from which forest attribute is acquired through automated segmentation algorithms at the delineated tree crowns or clusters of crowns level. Correlation and regression analyses were applied to identify the relation between a wide range of spectral, textural, contextual metrics, and the field derived forest attributes. Forest structural attribute estimation results acquired from our GEOBIA framework reveal strong relationships and precise estimates. Furthermore, the best fitted models were cross-validated with independent set of field samples, which revealed a high degree of precision.