A Hierarchical and Contextual Model for Aerial Image Parsing

In this paper we present a hierarchical and contextual model for aerial image understanding. Our model organizes objects (cars, roofs, roads, trees, parking lots) in aerial scenes into hierarchical groups whose appearances and configurations are determined by statistical constraints (e.g. relative position, relative scale, etc.). Our hierarchy is a non-recursive grammar for objects in aerial images comprised of layers of nodes that can each decompose into a number of different configurations. This allows us to generate and recognize a vast number of scenes with relatively few rules. We present a minimax entropy framework for learning the statistical constraints between objects and show that this learned context allows us to rule out unlikely scene configurations and hallucinate undetected objects during inference. A similar algorithm was proposed for texture synthesis (Zhu et al. in Int. J. Comput. Vis. 2:107–126, 1998) but didn’t incorporate hierarchical information. We use a range of different bottom-up detectors (AdaBoost, TextonBoost, Compositional Boosting (Freund and Schapire in J. Comput. Syst. Sci. 55, 1997; Shotton et al. in Proceedings of the European Conference on Computer Vision, pp. 1–15, 2006; Wu et al. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8, 2007)) to propose locations of objects in new aerial images and employ a cluster sampling algorithm (C4 (Porway and Zhu, 2009)) to choose the subset of detections that best explains the image according to our learned prior model. The C4 algorithm can quickly and efficiently switch between alternate competing sub-solutions, for example whether an image patch is better explained by a parking lot with cars or by a building with vents. We also show that our model can predict the locations of objects our detectors missed. We conclude by presenting parsed aerial images and experimental results showing that our cluster sampling and top-down prediction algorithms use the learned contextual cues from our model to improve detection results over traditional bottom-up detectors alone.     

基于无抽样小波变换和MCE训练的纹理分类

提出了一种新的纹理分类的方法,该方法把基于无抽样小波变换的特征提取器和基于欧几里得距离的分类器进行了合并。把方差、偏态系数、峰态系数、三者的联合及谱直方图作为描述纹理图像不相重叠的图像窗的特征。一个使用线性转换矩阵的特征提取器对分类导向的特征做进一步的提取。利用基于欧几里得距离的分类器,每个纹理图像不相重叠的图像窗被确定到属于它的那一类。基于最小分类错误训练方法的特征提取器和分类器设计的合并使分类错误达到了最小化。使用该方法对25类BrodTex纹理图像进行了评估,分类精确度达到90%以上。     

Color texture segmentation based on image pixel classification

Image segmentation partitions an image into nonoverlapping regions, which ideally should be meaningful for a certain purpose. Thus, image segmentation plays an important role in many multimedia applications. In recent years, many image segmentation algorithms have been developed, but they are often very complex and some undesired results occur frequently. By combination of Fuzzy Support Vector Machine (FSVM) and Fuzzy C-Means (FCM), a color texture segmentation based on image pixel classification is proposed in this paper. Specifically, we first extract the pixel-level color feature and texture feature of the image via the local spatial similarity measure model and localized Fourier transform, which is used as input of FSVM model (classifier). We then train the FSVM model (classifier) by using FCM with the extracted pixel-level features. Color image segmentation can be then performed through the trained FSVM model (classifier). Compared with three other segmentation algorithms, the results show that the proposed algorithm is more effective in color image segmentation.     

Simultaneous egomotion estimation,segmentation, and moving object detection

Robust egomotion estimation is a key prerequisite for making a robot truly autonomous. In previous work, a multimodel extension of random sample consensus (RANSAC) was introduced to deal with environments with rapid changes by incorporating moving object information. A multiscale matching algorithm was also proposed to resolve the issue of imperfect segmentation. In this paper, we present a novel specialization of RANSAC that extends the previous work. A unified framework is introduced to achieve simultaneously egomotion estimation, multiscale segmentation, and moving object detection in the RANSAC paradigm. The motivation of this work is to provide a robust real‐time solution to the problem of egomotion estimation, segmentation, and moving object detection in highly dynamic environments. The idea is to augment the discriminative power of spatial and temporal appearances of objects by the spatiotemporal consistency. The objective is twofold. First, split mismerged segments and distinguish nonstationary objects from stationary objects by the spatial consistency. Second, merge oversegmented segments and differentiate moving objects from outlying objects by the temporal consistency. Moving objects of considerably different sizes, from pedestrians to trucks, can be properly segmented and correctly detected. We also show that the performance of egomotion estimation can be further improved by taking into account both stationary and moving object information. Our approach is extensively evaluated on challenging data sets and compared to the state of the art. The experiments also show that our approach serves as a general framework that works well with various planar range data. © 2011 Wiley Periodicals, Inc.     

Classification-Based Probabilistic Modeling of Texture Transition for Fast Line Search Tracking and Delineation

We introduce a classification-based approach to finding occluding texture boundaries. The classifier is composed of a set of weak learners which operate on image intensity discriminative features which are defined on small patches and fast to compute. A database which is designed to simulate digitized occluding contours of textured objects in natural images is used to train the weak learners. The trained classifier score is then used to obtain a probabilistic model for the presence of texture transitions which can readily be used for line search texture boundary detection in the direction normal to an initial boundary estimate. This method is fast and therefore suitable for real-time and interactive applications. It works as a robust estimator which requires a ribbon like search region and can handle complex texture structures without requiring a large number of observations. We demonstrate results both in the context of interactive 2-D delineation and fast 3-D tracking and compare its performance with other existing methods for line search boundary detection.     

A comparative study of existing metrics for 3D-mesh segmentation evaluation

In this paper, we present an extensive experimental comparison of existing similarity metrics addressing the quality assessment problem of mesh segmentation. We introduce a new metric, named the 3D Normalized Probabilistic Rand Index (3D-NPRI), which outperforms the others in terms of properties and discriminative power. This comparative study includes a subjective experiment with human observers and is based on a corpus of manually segmented models. This corpus is an improved version of our previous one (Benhabiles et al. in IEEE International Conference on Shape Modeling and Application (SMI), 2009). It is composed of a set of 3D-mesh models grouped in different classes associated with several manual ground-truth segmentations. Finally the 3D-NPRI is applied to evaluate six recent segmentation algorithms using our corpus and the Chen et al.’s (ACM Trans. Graph. (SIGGRAPH), 28(3), 2009) corpus.     

Color image segmentation using automatic pixel classification with support vector machine

Automatic segmentation of images is a very challenging fundamental task in computer vision and one of the most crucial steps toward image understanding. In this paper, we present a color image segmentation using automatic pixel classification with support vector machine (SVM). First, the pixel-level color feature is extracted in consideration of human visual sensitivity for color pattern variations, and the image pixel's texture feature is represented via steerable filter. Both the pixel-level color feature and texture feature are used as input of SVM model (classifier). Then, the SVM model (classifier) is trained by using fuzzy c-means clustering (FCM) with the extracted pixel-level features. Finally, the color image is segmented with the trained SVM model (classifier). This image segmentation not only can fully take advantage of the local information of color image, but also the ability of SVM classifier. Experimental evidence shows that the proposed method has a very effective segmentation results and computational behavior, and decreases the time and increases the quality of color image segmentation in compare with the state-of-the-art segmentation methods recently proposed in the literature.     

Texture classification and segmentation using wavelet packet frame and Gaussian mixture model

In this paper, we propose a scheme for texture classification and segmentation. The methodology involves an extraction of texture features using the wavelet packet frame decomposition. This is followed by a Gaussian-mixture-based classifier which assigns each pixel to the class. Each subnet of the classifier is modeled by a Gaussian mixture model and each texture image is assigned to the class to which pixels of the image most belong. This scheme shows high recognition accuracy in the classification of Brodatz texture images. It can also be expanded to an unsupervised texture segmentation using a Kullback-Leibler divergence between two Gaussian mixtures. The proposed method was successfully applied to Brodatz mosaic image segmentation and fabric defect detection.     

Building facade detection,segmentation, and parameter estimation for mobile robot stereo vision

Building facade detection is an important problem in computer vision, with applications in mobile robotics and semantic scene understanding. In particular, mobile platform localization and guidance in urban environments can be enabled with accurate models of the various building facades in a scene. Toward that end, we present a system for detection, segmentation, and parameter estimation of building facades in stereo imagery. The proposed method incorporates multilevel appearance and disparity features in a binary discriminative model, and generates a set of candidate planes by sampling and clustering points from the image with Random Sample Consensus (RANSAC), using local normal estimates derived from Principal Component Analysis (PCA) to inform the planar models. These two models are incorporated into a two-layer Markov Random Field (MRF): an appearance- and disparity-based discriminative classifier at the mid-level, and a geometric model to segment the building pixels into facades at the high-level. By using object-specific stereo features, our discriminative classifier is able to achieve substantially higher accuracy than standard boosting or modeling with only appearance-based features. Furthermore, the results of our MRF classification indicate a strong improvement in accuracy for the binary building detection problem and the labeled planar surface models provide a good approximation to the ground truth planes.     

基于卷积神经网络与集成学习的交通标志识别

为提高复杂情况（如遮挡、透视畸变等）下交通标志识别的精度,提出一种有效的基于卷积神经网络(Convolutional Neural Network, CNN)与集成学习的交通标志识别方法。首先通过融合颜色分割、形态学处理、形状检测等多种方法分割出交通标志,然后利用卷积神经网络对其特征进行提取并分别采用支持向量机(Support Vector Machine, SVM)和Softmax多类分类器对其进行识别,最后将2种分类结果进行集成作为最终的识别结果。实验结果表明,本文算法可有效提高复杂情况下交通标志识别精度,整体上具有较高的性能。     

Discriminative training approaches to fabric defect classification based on wavelet transform

Wavelet transform is able to characterize the fabric texture at multiscale and multiorientation, which provides a promising way to the classification of fabric defects. For the objective of minimum error rate in the defect classification, this paper compares six wavelet transform-based classification methods, using different discriminative training approaches to the design of the feature extractor and classifier. These six classification methods are: methods of using an Euclidean distance classifier and a neural network classifier trained by maximum likelihood method and backpropagation algorithm, respectively; methods of using an Euclidean distance classifier and a neural network classifier trained by minimum classification error method, respectively; method of using a linear transformation matrix-based feature extractor and an Euclidean distance classifier, designed by discriminative feature extraction (DFE) method; method of using an adaptive wavelet-based feature extractor and an Euclidean distance classifier, designed by the DFE method. These six approaches have been evaluated on the classification of 466 defect samples containing eight classes of fabric defects, and 434 nondefect samples. The DFE training approach using adaptive wavelet has been shown to outperform the other approaches, where 95.8% classification accuracy was achieved.     

Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model

Precise segmentation and identification of thoracic vertebrae is important for many medical imaging applications though it remains challenging due to the vertebra’s complex shape and varied neighboring structures. In this paper, a new method based on learned bone-structure edge detectors and a coarse-to-fine deformable surface model is proposed to segment and identify vertebrae in 3D CT thoracic images. In the training stage, a discriminative classifier for object-specific edge detection is trained using steerable features and statistical shape models for 12 thoracic vertebrae are also learned. For the run-time testing, we design a new coarse-to-fine, two-stage segmentation strategy: subregions of a vertebra first deform together as a group; then vertebra mesh vertices in a smaller neighborhood move group-wise to progressively drive the deformable model towards edge response maps by optimizing a probability cost function. In this manner, the smoothness and topology of vertebrae shapes are guaranteed. This algorithm performs successfully with reliable mean point-to-surface errors 0.95 ± 0.91 mm on 40 volumes. Consequently a vertebra identification scheme is also proposed via mean surface mesh matching. We achieve a success rate of 73.1% using a single vertebra, and over 95% for 8 or more vertebra which is comparable or slightly better than state-of-the-art [5].     

Automatic cervical cell segmentation and classification in Pap smears

Cervical cancer is one of the leading causes of cancer death in females worldwide. The disease can be cured if the patient is diagnosed in the pre-cancerous lesion stage or earlier. A common physical examination technique widely used in the screening is Papanicolaou test or Pap test. In this research, a method for automatic cervical cancer cell segmentation and classification is proposed. A single-cell image is segmented into nucleus, cytoplasm, and background, using the fuzzy C-means (FCM) clustering technique. Four cell classes in the ERUDIT and LCH datasets, i.e., normal, low grade squamous intraepithelial lesion (LSIL), high grade squamous intraepithelial lesion (HSIL), and squamous cell carcinoma (SCC), are considered. The 2-class problem can be achieved by grouping the last 3 classes as one abnormal class. Whereas, the Herlev dataset consists of 7 cell classes, i.e., superficial squamous, intermediate squamous, columnar, mild dysplasia, moderate dysplasia, severe dysplasia, and carcinoma in situ. These 7 classes can also be grouped to form a 2-class problem. These 3 datasets were tested on 5 classifiers including Bayesian classifier, linear discriminant analysis (LDA), K-nearest neighbor (KNN), artificial neural networks (ANN), and support vector machine (SVM). For the ERUDIT dataset, ANN with 5 nucleus-based features yielded the accuracies of 96.20% and 97.83% on the 4-class and 2-class problems, respectively. For the Herlev dataset, ANN with 9 cell-based features yielded the accuracies of 93.78% and 99.27% for the 7-class and 2-class problems, respectively. For the LCH dataset, ANN with 9 cell-based features yielded the accuracies of 95.00% and 97.00% for the 4-class and 2-class problems, respectively. The segmentation and classification performances of the proposed method were compared with that of the hard C-means clustering and watershed technique. The results show that the proposed automatic approach yields very good performance and is better than its counterparts.     

Color image segmentation using pixel wise support vector machine classification

Image segmentation is an important tool in image processing and can serve as an efficient front end to sophisticated algorithms and thereby simplify subsequent processing. In this paper, we present a color image segmentation using pixel wise support vector machine (SVM) classification. Firstly, the pixel-level color feature and texture feature of the image, which is used as input of SVM model (classifier), are extracted via the local homogeneity model and Gabor filter. Then, the SVM model (classifier) is trained by using FCM with the extracted pixel-level features. Finally, the color image is segmented with the trained SVM model (classifier). This image segmentation not only can fully take advantage of the local information of color image, but also the ability of SVM classifier. Experimental evidence shows that the proposed method has a very effective segmentation results and computational behavior, and decreases the time and increases the quality of color image segmentation in comparison with the state-of-the-art segmentation methods recently proposed in the literature.     

Identification of beach hydromorphological patterns/forms through image classification techniques applied to remotely sensed data

The evaluation of beach hydromorphological behaviour and its classification is a complex issue. The main objective of this study was to develop new methodologies to identify coastal features/patterns. Pixel-based and object-oriented classification algorithms were used and a new approach was developed based on Principal Components Analysis and Histogram (PCAH) segmentation, to identify and analyse morphological features and hydrodynamic patterns. The PCAH method consists of three stages: preprocessing, PCA and histogram-based segmentation. Both manual and automatic approaches were addressed regarding the identification of the classes obtained from the segmentation stage. The dataset was composed from two aerial photographs and one IKONOS-2 image. The supervised classification algorithms present good results for both aerial photographs and the IKONOS-2 image. For the two aerial photographs the best results were found for the maximum likelihood classifier and for the IKONOS-2 image the best result was achieved with the parallelepiped classifier. The object-oriented classification performance for the aerial photographs and for the IKONOS-2 image also presented good results. The PCAH method led to promising results, with proportions of correctly classified pixels greater than 90% for the classes ‘Sea’, ‘Sediments+breaking zone’ and ‘Beach’.     

基于分形理论和Kohonen神经网络的纹理图像分割方法

分形理论作为描述自然现象的一种模型,受到人们越来越多的重视。该文提出采用分形维数和多重分形广义维数谱q－D（q）作为纹理特征,采用自组织神经网络Kohonen网络作为分类器的图象分割方法。通过对纹理图象的分割实验,结果令人满意,证实该方法的有效性。