基于彩色立体视觉的障碍物快速检测方法

Real-time obstacle detection method is a key technique for machine vision based mobile robot and au-tonomous land vehicle navigation in unstructured environments. In this paper o considering the real-time requirement for stereo matching algorithm, an adaptive color segmentation method for possible obstacle region detection is first developed based on the color feature, and a simple region based stereo matching algorithm of binocular vision for realobstacle recognition is also introduced. Obstacle detection is implemented by combining the road color adaptive seg-mentation method and region based stereovision method. Lots of experiment results show that the proposed approachcan detect obstacle quickly and effectively, and this algorithm is particularly suited for road environments in which the road is relatively flat and of roughly the same color.     

基于二维熵和轮廓特征的非结构化道路检测

针对非结构化道路场景复杂干扰因素较多、检测困难的问题,提出了一种基于轮廓特征和二维最大熵的道路检测算法。采用融合色彩特征不变量的二次二维最大熵分割算法对道路图像进行分割;利用边界跟踪算法提取分割图像的轮廓特征,根据道路区域的位置和几何特性选取最大轮廓;通过改进Mid-to-side算法进行边缘点搜索,用三阶道路模型重建道路边界,并对道路方向进行判断。实验结果表明,所提算法与传统算法相比,对三类不同场景下非结构化道路的检测准确率可提高25%左右,具有较强抗阴影干扰的能力,并能有效识别道路方向。     

Road intersection detection and classification using hierarchical SVM classifier

In this paper, a hierarchical multi-classification approach using support vector machines (SVM) has been proposed for road intersection detection and classification. Our method has two main steps. The first involves the road detection. For this purpose, an edge-based approach has been developed using the bird’s eye view image which is mapped from the perspective view of the road scene. Then, the concept of vertical spoke has been introduced for road boundary form extraction. The second step deals with the problem of road intersection detection and classification. It consists on building a hierarchical SVM classifier of the extracted road forms using the unbalanced decision tree architecture. Many measures are incorporated for good evaluation of the proposed solution. The obtained results are compared to those of Choi et al. (2007).     

伪彩色空间完全非结构化道路检测方法

完全非结构化道路检测是智能车辆自主行驶所面临的关键技术难题,解决该问题可以增强智能车辆的环境适应能力。以实时道路图像的真彩色信息为研究对象,提出一种三次样条曲线模型和分块子区生长模型相结合的完全非结构化道路检测算法。该算法运用三次样条曲线插值实现了真彩色空间到伪彩色空间的映射,采用主次伪色调和纹理信息相结合的子区生长方法,实现了完全非结构化道路检测。实地图像测试和对比试验表明,该算法对道路区域检测准确性高,对受到阴影、水迹等影响的道路区域具有较强抗干扰能力,实时性好。     

基于小波变换和K-means的非结构化道路检测

道路检测是智能交通视觉系统的一个重要组成部分,为提高复杂环境下非结构化道路检测的实时性、准确性和鲁棒性,提出一种新的道路检测方法。该方法利用高斯金字塔对图像进行降采样,压缩图像数据信息,对图像进行双边滤波,抑制噪声,采用基于小波变换求模极大值的方法对滤波后的图像提取边缘,通过阈值法去除非道路边缘点,给出基于斜率和截距的K-means聚类算法,实现道路方程拟合。实验结果表明,与传统最小二乘法相比,该方法能在道路场景较为复杂的情况下更准确地实现非结构化道路检测,并提高实时性。     

基于迁移学习和显著性检测的盲道识别

为了帮助对视觉障碍患者有效识别道路周围的场景,提出一种基于迁移学习和深度神经网络方法,实现实时盲道场景识别。首先提取盲道障碍物的瓶颈描述子和判别区域集成显著性特征描述子,并进行特征融合,然后训练新的盲道特征表示,用Softmax函数实现盲道场景识别。实验中,对成都不同区域盲道周围障碍物采样,分别采用基于Mobilenet模型不同参数训练和测试了提出的新模型,最后在实际应用场景,实现了盲道周边障碍物的实时分类和报警,实验证明提出的方法具有很高准确率和良好的运行性能。     

基于空间聚集特征的沥青路面裂缝检测方法

沥青路面裂缝自动检测是制约公路养护科学决策的最主要瓶颈.针对现有裂缝检测算法在大规模应用特别是广地域、多路况等复杂环境下算法稳定性、可靠性及实时性等方面存在严重不足问题.本文在观察大量实际工程路面图像基础上, 对路面裂缝特征进行全新定义, 提出了一种基于空间聚集特征的沥青路面裂缝检测方法, 参考裂缝的空间分布、灰度、几何等特征, 以子块图像为处理单元, 采用逐步求精的策略对子块图像进行分割, 快速定位空间聚集区域, 再对聚集区域进行评估得到信度高的裂缝候选区域; 最后以裂缝候选区域为种子区域, 在准确估算裂缝发展趋势的基础上, 结合裂缝片段聚集及相似性等特性, 去除噪声同时合并连接断裂的裂缝, 实现了裂缝区域较为完整的检测.通过测试多路况、多采集环境下近万样本, 并采用不同的方法对测试结果进行评估, 结果显示, 算法对不同类型路面图像中具有不同特征的裂缝区域均具有良好的检测性能, 裂缝定位准确性达到95%以上, 裂缝区域检测的完整性达到90%以上.     

基于PCA-SVM准则改进区域生长的非结构化道路识别

针对智能车辆在非结构化道路识别中需要采用众多的特征参数,增加了特征融合识别难度与计算复杂度,并且部分背景与道路区域存在相似性会产生道路识别的误分、误判的问题,提出了一种基于主成分分析的支持向量机（PCA-SVM）准则改进区域生长的非结构化道路识别算法。首先,对非结构化道路颜色、纹理等复杂特征信息进行提取,采用PCA对提取的特征信息进行降维;然后,利用降维后的主元特征对SVM进行训练后作为复杂道路单元格的分类器。利用道路位置、起始单元格等先验知识以及道路边界单元格统计特征改进区域生长方法,在单元格生长时利用分类器判别,排除误判区域。实际道路检测结果表明,所提算法具有较好的鲁棒性,能够有效识别非结构化路面区域。对比结果表明,所提算法在保证准确率的同时,将10余维复杂特征信息压缩为3维主元特征,相比传统算法可缩短计算时间一半以上。针对背景与道路相似区域造成的传统算法10%左右的误判问题,所提算法能够有效排除。在野外环境下基于视觉的局部路径规划与导航方面,所提算法为缩短识别时间、排除背景干扰提供了可行途径。     

Road traffic density estimation using microscopic and macroscopic parameters

In this paper we present a comparative study of two approaches for road traffic density estimation. The first approach uses the microscopic parameters which are extracted using both motion detection and tracking methods from a video sequence, and the second approach uses the macroscopic parameters which are directly estimated by analyzing the global motion in the video scene. The extracted parameters are applied to three classifiers, the K Nearest Neighbor (KNN) classifier, the LVQ classifier and the SVM classifier, in order to classify the road traffic in three categories: light, medium and heavy. The methods are compared based on their robustness to the classification of different road traffic states. The goal of this study is to propose an algorithm for road traffic density estimation with a high precision.     

A comparative study of fuzzy PSO and fuzzy SVD-based RBF neural network for multi-label classification

In multi-label classification problems, every instance is associated with multiple labels at the same time. Binary classification, multi-class classification and ordinal regression problems can be seen as unique cases of multi-label classification where each instance is assigned only one label. Text classification is the main application area of multi-label classification techniques. However, relevant works are found in areas like bioinformatics, medical diagnosis, scene classification and music categorization. There are two approaches to do multi-label classification: The first is an algorithm-independent approach or problem transformation in which multi-label problem is dealt by transforming the original problem into a set of single-label problems, and the second approach is algorithm adaptation, where specific algorithms have been proposed to solve multi-label classification problem. Through our work, we not only investigate various research works that have been conducted under algorithm adaptation for multi-label classification but also perform comparative study of two proposed algorithms. The first proposed algorithm is named as fuzzy PSO-based ML-RBF, which is the hybridization of fuzzy PSO and ML-RBF. The second proposed algorithm is named as FSVD-MLRBF that hybridizes fuzzy c-means clustering along with singular value decomposition. Both the proposed algorithms are applied to real-world datasets, i.e., yeast and scene dataset. The experimental results show that both the proposed algorithms meet or beat ML-RBF and ML-KNN when applied on the test datasets.

     

基于平面反射模型的夜间路面检测

路面检测对于自动驾驶系统具有极其重要的作用,其具体的应用方面包括检测辅助、避障、自动导航等。基于视觉的路面检测主要就是对图像中每一个像素点进行分类,区分其是否为路面。到目前为止大部分的路面检测算法是应用于白天。在本文中,我们集中解决夜间的路面检测。我们利用一个近红外摄像头来采集夜间图像。检测时,首先利用平面反射模型来对图像中的路面部分进行拟合,然后,一个基于像素点的分类方法被用来对图像中的每一个像素点进行分类。在实验部分,我们将我们的算法与区域增长的方法进行了比较。实验证明,我们的算法相对区域增长有一定的优势。     

Context-based environmental audio event recognition for scene understanding

Automatic audio content recognition has attracted an increasing attention for developing multimedia systems, for which the most popular approaches combine frame-based features with statistic models or discriminative classifiers. The existing methods are effective for clean single-source event detection but may not perform well for unstructured environmental sounds, which have a broad noise-like flat spectrum and a diverse variety of compositions. We present an automatic acoustic scene understanding framework that detects audio events through two hierarchies, acoustic scene recognition and audio event recognition, in which the former is preceded by following dominant audio sources and in turn helps infer non-dominant audio events within the same scene through modeling their occurrence correlations. On the scene recognition hierarchy, we perform adaptive segmentation and feature extraction for every input acoustic scene stream through Eigen-audiospace and an optimized feature subspace, respectively. After filtering background, scene streams are recognized by modeling the observation density of dominant features using a two-level hidden Markov model. On the audio event recognition hierarchy, scene knowledge is characterized by an audio context model that essentially describes the occurrence correlations of dominant and non-dominant audio events within this scene. Monte Carlo integration and gradient descent techniques are employed to maximize the likelihood and correctly tag each audio event. To the best of our knowledge, this is the first work that models event correlations as scene context for robust audio event detection from complex and noisy environments. Note that according to the recent report, the mean accuracy for the acoustic scene classification task by human listeners is only around 71 % on the data collected in office environments from the DCASE dataset. None of the existing methods performs well on all scene categories and the average accuracy of the best performances of the recent 11 methods is 53.8 %. The proposed method averagely achieves an accuracy of 62.3 % on the same dataset. Additionally, we create a 10-CASE dataset by manually collecting 5,250 audio clips of 10 scene types and 21 event categories. Our experimental results on 10-CASE show that the proposed method averagely achieves the enhanced performance of 78.3 %, and the average accuracy of audio event recognition can be effectively improved by capturing dominant audio sources and reasoning non-dominant events from the dominant ones through acoustic context modeling. In the future work, exploring the interactions between acoustic scene recognition and audio event detection, and incorporating other modalities to improve the accuracy are required to further advance the proposed framework.     

基于离散余弦变换的车道识别算法

车道识别技术是自动驾驶领域的研究热点。通过对车载摄像机获取的公路车道线图像特征的分析,提出了一种基于图像频率域特征的车道识别算法。该算法的核心是提取车道线在离散余弦变换域的特征,再结合道路模型的先验知识利用贝叶斯决策原理,识别出路面上的车道线。实验表明,该算法在不同的路面和光照条件下均可得到良好的识别效果。     

Rediscover flowers structurally

Existing methods for flower classification are usually focused on segmentation of the foreground, followed by extraction of features. After extracting the features from the foreground, global pooling is performed for final classification. Although this pipeline can be applied to many recognition tasks, however, these approaches have not explored structural cues of the flowers due to the large variation in their appearances. In this paper, we argue that structural cues are essential for flower recognition. We present a novel approach that explores structural cues to extract features. The proposed method encodes the structure of flowers into the final feature vectors for classification by operating on salient regions, which is robust to appearance variations. In our framework, we first segment the flower accurately by refining the existing segmentation method, and then we generate local features using our approach. We combine our local feature with global-pooled features for classification. Evaluations on the Oxford Flower dataset shows that by introducing the structural cues and locally pooling of some off-the-shelf features, our method outperforms the state-of-the-arts which employ specific designed features and metric learning.     

3-D Depth Reconstruction from a Single Still Image

We consider the task of 3-d depth estimation from a single still image. We take a supervised learning approach to this problem, in which we begin by collecting a training set of monocular images (of unstructured indoor and outdoor environments which include forests, sidewalks, trees, buildings, etc.) and their corresponding ground-truth depthmaps. Then, we apply supervised learning to predict the value of the depthmap as a function of the image. Depth estimation is a challenging problem, since local features alone are insufficient to estimate depth at a point, and one needs to consider the global context of the image. Our model uses a hierarchical, multiscale Markov Random Field (MRF) that incorporates multiscale local- and global-image features, and models the depths and the relation between depths at different points in the image. We show that, even on unstructured scenes, our algorithm is frequently able to recover fairly accurate depthmaps. We further propose a model that incorporates both monocular cues and stereo (triangulation) cues, to obtain significantly more accurate depth estimates than is possible using either monocular or stereo cues alone.     

红外图像中的道路识别与表示

对机器人视觉导航而言，道路识别和表示是一个非常重要的环节，它直接影响到后续的路径规划。该文针对红外道路图像，提出了基于区域方法的一套处理方案，该方法首先通过分割获得道路区域，利用链码跟踪获取道路边缘的链码。采用了一种通用的道路模型，然后基于链码以及该道路模型，设计了一种有效的道路边界拟合方法。在拟合过程中，首先依据一定的准则把链码分为两段，对于每一段再递归执行该分段过程，直到不能分为止，然后用分段直线去描述道路边界。该拟合算法可以有效地处理直道和非直道的情况。文中给出了相关的实验结果。     

Learning motion patterns in unstructured scene based on latent structural information

ContextAs trajectory analysis is widely used in the fields of video surveillance, crowd monitoring, behavioral prediction, and anomaly detection, finding motion patterns is a fundamental task for pedestrian trajectory analysis.ObjectiveIn this paper, we focus on learning dominant motion patterns in unstructured scene.MethodsAs the invisible implicit indicator to scene structure, latent structural information is first defined and learned by clustering source/sink points using CURE algorithm. Considering the basic assumption that most pedestrians would find the similar paths to pass through an unstructured scene if their entry and exit areas are fixed, trajectories are then grouped based on the latent structural information. Finally, the motion patterns are learned for each group, which are characterized by a series of statistical temporal and spatial properties including length, duration and envelopes in polar coordinate space.ResultsExperimental results demonstrate the feasibility and effectiveness of our method, and the learned motion patterns can efficiently describe the statistical spatiotemporal models of the typical pedestrian behaviors in a real scene. Based on the learned motion patterns, abnormal or suspicious trajectories are detected.ConclusionThe performance of our approach shows high spatial accuracy and low computational cost.