Real-Time Traversable Surface Detection by Colour Space Fusion and Temporal Analysis

Abstract

We present a real-time approach for traversable surface detection using a low-cost monocular camera mounted on an autonomous vehicle. The proposed methodology extracts colour and texture information from various channels of the HSL, YCbCr and LAB colourspaces by temporal analysis in order to create a traversability map. On this map lighting and water artifacts are eliminated including shadows, reections and water prints. Additionally, camera vibration is compensated by temporal ltering leading to robust path edge detection in blurry images.The performance of this approach is extensively evaluated over varying terrain and environmental conditions and the eect of colourspace fusion on the system's precision is analysed. The results show a mean accuracy of 97% over this comprehensive test set.

Indoor/outdoor navigation system based on possibilistic traversable area segmentation for visually impaired people

“…An accuracy of 98% was achieved when applying the possibility based approach on this dataset [26]. The computation time is 20 frames per second.…”

“…The execution time is 25 frames per second. The mean accuracy of this method is 97% (applied on the outdoor environment [26]). …”

“…Two public dataset such as indoor [25] and outdoor environment [26] were used to achieve such comparison.…”

“…Katramados et al [26] have proposed a real-time approach for traversable surface detection using monocular camera mounted on an autonomous vehicle. Detection of traversable area is performed by fusing color and texture information from HSL, YCbCr and LAB colour spaces.…”

“…The data was recorded at full frame rate (30 Hz) and sensor resolution (640480). Then, from the second database, selection of 300 images corresponding to outdoor environment [26] is done, based on a video dataset comprising sequences captured under a wide range of environmental conditions and different ground types (cf. Figure 1).…”