Wheel-terrain interaction plays a critical role for vehicle mobility on natural terrain, such as in agricultural, planetary exploration and off-road settings. Estimation of the terrain characteristics and the way they...
详细信息
ISBN:
(数字)9781510644052
ISBN:
(纸本)9781510644052
Wheel-terrain interaction plays a critical role for vehicle mobility on natural terrain, such as in agricultural, planetary exploration and off-road settings. Estimation of the terrain characteristics and the way they affect traversability is essential for the vehicle to better plan its safest and energy-efficient path. This work proposes a novel approach to learn and predict from a distance the motion resistance encountered by a robotic vehicle, while traversing natural soil, by using visual information from a stereovision device. To this end, terrain appearance and geometry information are first correlated to resistance torque measurements during a learning phase via two alternative regression approaches, namely Least-Squares Boosting and Long-Short Term Memory Recurrent Neural Network. Then, such a relationship is exploited to predict motion resistance remotely, based on visual data only. Results obtained in preliminary experimental tests on ploughed and compact terrain are presented to show the feasibility of the proposed method.
multi-sensordata fusion method has been widely investigated in recent years. This article presents a novel fusion algorithm based on regional characteristics for combining infrared and visible light images in order t...
详细信息
multi-sensordata fusion method has been widely investigated in recent years. This article presents a novel fusion algorithm based on regional characteristics for combining infrared and visible light images in order to achieve an image with clear objects and high-resolution scene. First, infrared objects are extracted by region growing and guided filter. Second, the whole scene is divided into the objects region, the smooth region, and the texture region according to different regional characteristics. Third, the non-subsampled contourlet transform is used on infrared and visible images. Then, different fusion rules are applied to different regions, respectively. Finally, the fused image is constructed by the inverse non-subsampled contourlet transform with all coefficients. Experimental results demonstrate that the proposed objects extraction algorithm and the fusion algorithm have good performance in objective and subjective assessments.
The increased availability of multi-sensordata, and elevation information in particular, leads to the need of advanced processing methods. In the context of landscape modeling tasks, we concentrate on one central com...
详细信息
The increased availability of multi-sensordata, and elevation information in particular, leads to the need of advanced processing methods. In the context of landscape modeling tasks, we concentrate on one central component, the extraction of terrain surface from a Digital Surface Model (DSM). In contrast to conventional mathematical grey value morphology approaches (filtering methods) or to stochastical procedures, we propose an alternative methodology for this task by applying a region-based and multi-scale approach. It consists of segmentation and follow-up fuzzy logic classification based on several features derived from elevation and multi-spectral image data. The satisfying results obtained with a multi-sensor as well as with other datasets show the applicability of the approach. (C) 2003 Elsevier Science B.V. All rights reserved.
The increased availability of multi-sensordata, and elevation information in particular, leads to the need of advanced processing methods. In the context of landscape modeling tasks, we concentrate on one central com...
详细信息
The increased availability of multi-sensordata, and elevation information in particular, leads to the need of advanced processing methods. In the context of landscape modeling tasks, we concentrate on one central component, the extraction of terrain surface from a Digital Surface Model (DSM). In contrast to conventional mathematical grey value morphology approaches (filtering methods) or to stochastical procedures, we propose an alternative methodology for this task by applying a region-based and multi-scale approach. It consists of segmentation and follow-up fuzzy logic classification based on several features derived from elevation and multi-spectral image data. The satisfying results obtained with a multi-sensor as well as with other datasets show the applicability of the approach. (C) 2003 Elsevier Science B.V. All rights reserved.
暂无评论