Abstract

C. Siagian, L. Itti, Gist: A Mobile Robotics Application of Context-Based Vision in Outdoor Environment, In: Proc. IEEE-CVPR Workshop on Attention and Performance in Computer Vision (WAPCV'05), San Diego, California, pp. 1-7, Jun 2005. (Cited by 46)

Abstract: We present context-based scene recognition for mobile robotics applications. Our classifier is able to differentiate outdoor scenes without temporal and spatial filtering relatively well from a variety of locations at a college campus using a set of features that together capture the ``gist'' of the scene. We discuss and perform experiments on the accuracy and scalability of the current features. We compare the classification accuracy of a set of scenes from 1551 frames filmed outdoors along a path and dividing them to four and twelve different legs. We obtained a classification rate of 67.96 percent and 48.61 percent, respectively. We also tested the scalability of the features by comparing the classification results from the previous scenes with four legs with a longer path with eleven legs. We obtained a classification rate of 55.08 percent. In the end we also put forth some ideas to improve upon the theoretical strength of the gist features.

Themes: Model of Bottom-Up Saliency-Based Visual Attention, Computational Modeling, Computer Vision