基于多特征提取的越野智能车辆环境探测

Environment Detection Method for Cross-country Intelligent Vehicle Based on Multi-feature Extraction

为实时获取越野智能车辆前方的地形信息并有效检测出可能存在的障碍物,本文提出一种基于立体视觉传感器的环境探测方法。该方法首先对图像进行局部对比度增强,以减弱光照变化对立体匹配的影响并保证角点特征提取的均匀性。其次研究图像中障碍物的边缘特征提取方法,以避免障碍物的漏检。然后提出基于多特征提取的立体匹配流程,其中采用了随机采样序列方法计算基础矩阵,将基于边缘的匹配与基于角点的匹配独立进行以避免干扰,并引入连续性约束来剔除误匹配。最后,通过不同光照越野场景的环境重构实验验证算法的鲁棒性。

To obtain real-time terrain information in front of the cross-cotmtry intelligent vehicle and effectively detect the possible obstacles, an environment detection method on the basis of stereo vision sensor was presented. Firstly, local image enhancement technology was proposed to weaken the influence of varying illumination and guarantee that the comer features could be extracted with uniform distribution. Secondly, edge features were extracted to avoid miss-detection of obstacles. Thirdly, stereo matching flow based on multi-feature extraction was presented. Fundamental matrix was calculated based on Random Sample Consensus （RANSAC） method. Comer-based matching scheme and edge-based matching scheme were implemented independently to avoid disturbance. Continuity constraint was studied to eliminate pseudo matching. Finally, different cross-country scenes with varying illuminations were collected to test the robust performance of the method.