Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

A random forest (RF) classifier is an ensemble classifier that produces multiple decision trees, using a randomly selected subset of training samples and variables. This classifier has become popular within the remote sensing community due to the accuracy of its classifications. The overall objective of this work was to review the utilization of RF classifier in remote sensing. This review has revealed that RF classifier can successfully handle high data dimensionality and multicolinearity, being both fast and insensitive to overfitting. It is, however, sensitive to the sampling design. The variable importance (VI) measurement provided by the RF classifier has been extensively exploited in different scenarios, for example to reduce the number of dimensions of hyperspectral data, to identify the most relevant multisource remote sensing and geographic data, and to select the most suitable season to classify particular target classes. Further investigations are required into less commonly exploited uses of this classifier, such as for sample proximity analysis to detect and remove outliers in the training samples.

Random forest in remote sensing: A review of applications and future directions

We evaluate 179 classifiers arising from 17 families (discriminant analysis, Bayesian, neural networks, support vector machines, decision trees, rule-based classifiers, boosting, bagging, stacking, random forests and other ensembles, generalized linear models, nearest-neighbors, partial least squares and principal component regression, logistic and multinomial regression, multiple adaptive regression splines and other methods), implemented in Weka, R (with and without the caret package), C and Matlab, including all the relevant classifiers available today. We use 121 data sets, which represent the whole UCI data base (excluding the large-scale problems) and other own real problems, in order to achieve significant conclusions about the classifier behavior, not dependent on the data set collection. The classifiers most likely to be the bests are the random forest (RF) versions, the best of which (implemented in R and accessed via caret) achieves 94.1% of the maximum accuracy overcoming 90% in the 84.3% of the data sets. However, the difference is not statistically significant with the second best, the SVM with Gaussian kernel implemented in C using LibSVM, which achieves 92.3% of the maximum accuracy. A few models are clearly better than the remaining ones: random forest, SVM with Gaussian and polynomial kernels, extreme learning machine with Gaussian kernel, C5.0 and avNNet (a committee of multi-layer perceptrons implemented in R with the caret package). The random forest is clearly the best family of classifiers (3 out of 5 bests classifiers are RF), followed by SVM (4 classifiers in the top-10), neural networks and boosting ensembles (5 and 3 members in the top-20, respectively).

/pdf/do-we-need-hundreds-of-classifiers-to-solve-real-world-1igtahh9y9.pdf

Do we need hundreds of classifiers to solve real world classification problems

In this paper we present an automatic algorithm to detect basic shapes in unorganized point clouds. The algorithm decomposes the point cloud into a concise, hybrid structure of inherent shapes and a set of remaining points. Each detected shape serves as a proxy for a set of corresponding points. Our method is based on random sampling and detects planes, spheres, cylinders, cones and tori. For models with surfaces composed of these basic shapes only, for example, CAD models, we automatically obtain a representation solely consisting of shape proxies. We demonstrate that the algorithm is robust even in the presence of many outliers and a high degree of noise. The proposed method scales well with respect to the size of the input point cloud and the number and size of the shapes within the data. Even point sets with several millions of samples are robustly decomposed within less than a minute. Moreover, the algorithm is conceptually simple and easy to implement. Application areas include measurement of physical parameters, scan registration, surface compression, hybrid rendering, shape classification, meshing, simplification, approximation and reverse engineering.

Efficient RANSAC for Point-Cloud Shape Detection

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Over the past years, several filters have been developed to extract bare-Earth points from point clouds. ISPRS Working Group III/3 conducted a test to determine the performance of these filters and the influence of point density thereon, and to identify directions for future research. Twelve selected datasets have been processed by eight participants. In this paper, the test results are presented. The paper describes the characteristics of the provided datasets and the used filter approaches. The filter performance is analysed both qualitatively and quantitatively. All filters perform well in smooth rural landscapes, but all produce errors in complex urban areas and rough terrain with vegetation. In general, filters that estimate local surfaces are found to perform best. The influence of point density could not well be determined in this experiment. Future research should be directed towards the usage of additional data sources, segment-based classification, and self-diagnosis of filter algorithms.

Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds

Whittles Publishing is delighted to announce that Airborne and Terrestrial Laser Scanning has been awarded the Karl Kraus Medal by the ISPRS with the presentation being made on 31st August at the XXII Congress in Melbourne We are also very pleased for all the authors who have contributed to the book and especially to George Vosselman and Hans-Gerd Maas for their commitment and expertise which has resulted in such an acclaimed and highly successful book It is gratifying that our growing list of geomatics titles continues to receive recognition and we are endeavouring to create more books that will be equally well-received and useful

	Written by a team of international experts, this book provides a comprehensive overview of the major applications of airborne and terrestrial laser scanning The book focuses on principles and methods and presents an integrated treatment of airborne and terrestrial laser scanning technology

	Laser scanning is a relatively young 3D measurement technique offering much potential in the acquisition of precise and reliable 3D geodata and object geometries However, there are many terrestrial and airborne scanners on the market, accompanied by numerous software packages that handle data acquisition, processing and visualization, yet existing knowledge is fragmented over a wide variety of publications, whether printed or electronic

	This book brings together the various facets of the subject in a coherent text that will be relevant for advanced students, academics and practitioners After consideration of the technology and processing methods, the book turns to applications The primary use thus far has been the extraction of digital terrain models from airborne laser scanning data, but many other applications are considered including engineering, forestry, cultural heritage, extraction of 3D building models and mobile mapping

Airborne and Terrestrial Laser Scanning

Laser altimetry is becoming the prime method for large scale acquisition of height data. Although laser altimetry is full integrated into processes for the production of digital elevation models in different countries, the derivation of DEM's from the raw laser altimetry measurements still causes problems. In particular the laser pulses reflected on the ground surface need to be distinguished from those reflecting on buildings and vegetation. In this paper a new method is proposed for filtering laser data. This method is closely related to the erosion operator used for mathematical grey scale morphology. Based on height differences in a representative training dataset, filter functions are derived that either preserve important terrain characteristics or minimise the number of classification errors. In experiments it is shown that the latter filter causes smaller errors in the resulting digital elevation models. In general the performance of the filters deteriorates with a decreasing point density.

Slope based filtering of laser altimetry data

Airborne laser altimetry has become a very popular technique for the acquisition of digital elevation models. The high point density that can be achieved with this technique enables applications of laser data for many other purposes. This paper deals with the construction of 3D models of the urban environment. A three-dimensional version o f the well-known Hough transform is used for the e xtraction o f planar faces from the irregularly distributed point clouds. To support the 3D reconstruction usage is made of available ground plans of the buildings. Two different strategies are explored to reconstruct building models from the detected planar faces and segmented ground plans. Whereas the first strategy tries to detect intersection lines and height jump edges, the second one assumes that all detected planar faces should model some part of the building. Experiments show that the second strategy is able to reconstruct more buildings and more details of this buildings, but that it sometimes leads to additional parts of the model that do not exist. When restricted to buildings with rectangular segments of the ground plan, the second strategy was able to reconstruct 83 buildings out of a dataset with 94 buildings.

https://www.isprs.org/proceedings/XXXIV/3-W4/pdf/Vosselman.pdf

3d building model reconstruction from point clouds and ground plans

For automatic processing of point clouds their segmentation is one of the most important processes. The methods based on curvature and other higher level derivatives often lead to over segmentation, which later needs a lot of manual editing. We present a method for segmentation of point clouds using smoothness constraint, which finds smoothly connected areas in point clouds. It uses only local surface normals and point connectivity which can be enforced using either k-nearest or fixed distance neighbours. The presented method requires a small number of intuitive parameters, which provide a tradeoff between underand over-segmentation. The application of the presented algorithm on industrial point clouds shows its effectiveness compared to curvature based approaches.

https://www.isprs.org/proceedings/XXXVI/part5/paper/RABB_639.pdf

George Vosselman

Papers

Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds

Airborne and Terrestrial Laser Scanning

Slope based filtering of laser altimetry data

3d building model reconstruction from point clouds and ground plans

Segmentation of point clouds using smoothness constraints