Concept for a Compound Analysis in Active Learning for Remote Sensing

Wuttke, Sebastian; Middelmann, Wolfgang; Stilla, Uwe

doi:10.5194/isprsarchives-xl-3-w2-273-2015

Cited by 3 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is particularly a concern for regional-scale HR datasets. While certain innovative methods such as active learning have been proposed to reduce sampling costs [21,22], these methods are complex to implement and are beyond the scope of this study. An alternative is localizing sample selection to a single subset area of the region of interest.…”

Section: Background On Sample Selection In Remote Sensingmentioning

confidence: 99%

Evaluation of Sampling and Cross-Validation Tuning Strategies for Regional-Scale Machine Learning Classification

2019

View full text Add to dashboard Cite

High spatial resolution (1–5 m) remotely sensed datasets are increasingly being used to map land covers over large geographic areas using supervised machine learning algorithms. Although many studies have compared machine learning classification methods, sample selection methods for acquiring training and validation data for machine learning, and cross-validation techniques for tuning classifier parameters are rarely investigated, particularly on large, high spatial resolution datasets. This work, therefore, examines four sample selection methods—simple random, proportional stratified random, disproportional stratified random, and deliberative sampling—as well as three cross-validation tuning approaches—k-fold, leave-one-out, and Monte Carlo methods. In addition, the effect on the accuracy of localizing sample selections to a small geographic subset of the entire area, an approach that is sometimes used to reduce costs associated with training data collection, is investigated. These methods are investigated in the context of support vector machines (SVM) classification and geographic object-based image analysis (GEOBIA), using high spatial resolution National Agricultural Imagery Program (NAIP) orthoimagery and LIDAR-derived rasters, covering a 2,609 km2 regional-scale area in northeastern West Virginia, USA. Stratified-statistical-based sampling methods were found to generate the highest classification accuracy. Using a small number of training samples collected from only a subset of the study area provided a similar level of overall accuracy to a sample of equivalent size collected in a dispersed manner across the entire regional-scale dataset. There were minimal differences in accuracy for the different cross-validation tuning methods. The processing time for Monte Carlo and leave-one-out cross-validation were high, especially with large training sets. For this reason, k-fold cross-validation appears to be a good choice. Classifications trained with samples collected deliberately (i.e., not randomly) were less accurate than classifiers trained from statistical-based samples. This may be due to the high positive spatial autocorrelation in the deliberative training set. Thus, if possible, samples for training should be selected randomly; deliberative samples should be avoided.

show abstract

Section: Background On Sample Selection In Remote Sensingmentioning

confidence: 99%

Evaluation of Sampling and Cross-Validation Tuning Strategies for Regional-Scale Machine Learning Classification

2019

View full text Add to dashboard Cite

show abstract

“…The selection and training process is done iteratively. Wuttke et al (2015) present a method, how the usefulness for each unlabeled training sample can be rated. They create a hypothesis based on analyses of the following three components.…”

Section: State Of the Artmentioning

confidence: 99%

Image Based Recognition of Dynamic Traffic Situations by Evaluating the Exterior Surrounding and Interior Space of Vehicles

Hanel¹,

Kloden

Hoegner³

et al. 2015

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

Self Cite

View full text Add to dashboard Cite

ABSTRACT:Today, cameras mounted in vehicles are used to observe the driver as well as the objects around a vehicle. In this article, an outline of a concept for image based recognition of dynamic traffic situations is shown. A dynamic traffic situation will be described by road users and their intentions. Images will be taken by a vehicle fleet and aggregated on a server. On these images, new strategies for machine learning will be applied iteratively when new data has arrived on the server. The results of the learning process will be models describing the traffic situation and will be transmitted back to the recording vehicles. The recognition will be performed as a standalone function in the vehicles and will use the received models. It can be expected, that this method can make the detection and classification of objects around the vehicles more reliable. In addition, the prediction of their actions for the next seconds should be possible. As one example how this concept is used, a method to recognize the illumination situation of a traffic scene is described. This allows to handle different appearances of objects depending on the illumination of the scene. Different illumination classes will be defined to distinguish different illumination situations. Intensity based features are extracted from the images and used by a classifier to assign an image to an illumination class. This method is being tested for a real data set of daytime and nighttime images. It can be shown, that the illumination class can be classified correctly for more than 80% of the images.

show abstract

Improving Active Queries With a Local Segmentation Step and Application to Land Cover Classification

Wuttke

Middelmann

Stilla³

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

Self Cite

View full text Add to dashboard Cite

ABSTRACT:Active queries is an active learning method used for classification of remote sensing images. It consists of three steps: hierarchical clustering, dendrogram division, and active label selection. The goal of active learning is to reduce the needed amount of labeled data while preserving classification accuracy. We propose to apply local segmentation as a new step preceding the hierarchical clustering. We are using the SLIC (simple linear iterative clustering) algorithm for dedicated image segmentation. This incorporates spatial knowledge which leads to an increased learning rate and reduces classification error. The proposed method is applied to six different areas of the Vaihingen dataset.

show abstract

Concept for a Compound Analysis in Active Learning for Remote Sensing

Cited by 3 publications

References 25 publications

Evaluation of Sampling and Cross-Validation Tuning Strategies for Regional-Scale Machine Learning Classification

Evaluation of Sampling and Cross-Validation Tuning Strategies for Regional-Scale Machine Learning Classification

Image Based Recognition of Dynamic Traffic Situations by Evaluating the Exterior Surrounding and Interior Space of Vehicles

Improving Active Queries With a Local Segmentation Step and Application to Land Cover Classification

Contact Info

Product

Resources

About