Chengyi Wang

Remote Sensing Scene Classification Based on Convolutional Neural Networks Pre-Trained Using Attention-Guided Sparse Filters

Semantic-level land-use scene classification is a challenging problem, in which deep learning methods, e.g., convolutional neural networks (CNNs), have shown remarkable capacity. However, a lack of sufficient labeled images has proved a hindrance to increasing the land-use scene classification accuracy of CNNs. Aiming at this problem, this paper proposes a CNN pre-training method under the guidance of a human visual attention mechanism. Specifically, a computational visual attention model is used to automatically extract salient regions in unlabeled images. Then, sparse filters are adopted to learn features from these salient regions, with the learnt parameters used to initialize the convolutional layers of the CNN. Finally, the CNN is further fine-tuned on labeled images. Experiments are performed on the UCMerced and AID datasets, which show that when combined with a demonstrative CNN, our method can achieve 2.24% higher accuracy than a plain CNN and can obtain an overall accuracy of 92.43% when combined with AlexNet. The results indicate that the proposed method can effectively improve CNN performance using easy-to-access unlabeled images and thus will enhance the performance of land-use scene classification especially when a large-scale labeled dataset is unavailable.

A cloud detection method based on color model and undecimated wavelet transformation

A new cloud detection method based on color model and undecimated wavelet transform was proposed for the basic properties of the cloud area on remote sensing images and band features. First of all, modified HSI Color model transformation was applied to original images combined with the band information in order to extract approximate boundary of cloud area. Secondly, as in binary sampling process of wavelet decomposition, there was losing spectral information and texture information problems. In order to solve this, we used undecimated wavelet transform and the normalized double threshold value method to determine the exact boundary of cloud area. At last, our results were assessed using False Recognition Rate and Accuracy. The assessment was compared with cloud detection methods based on wavelet transform and single threshold. The Result means that proposed algorithm has high detection precision.

Contrast pyramid based image fusion scheme for infrared image and visible image

In this research, a new fusion scheme based on improved regional energy contrast pyramid algorithm with respect to the human visual characteristics is presented, the infrared and visible data from HJ1-B satellite, ASTER were performed in the experiments. First of all, the source data are decomposed by contrast pyramid transform. Second, the regional energy, standard deviation and similarity were calculated, then the regional fusion operator was determined by threshold and standard deviation. Finally, the fused image was reconstructed by inverse contrast pyramid transform. Moreover, the improved regional energy contrast pyramid based, Laplacian Pyramid based, Gradient Pyramid based and Wavelet based image fusion algorithms were evaluated and compared by means of the fusion evaluation indexes, namely the entropy, root mean square error and PSNR. The experimental results showed that the image fusion algorithm proposed in this research is more effective.

Long Short-Term Memory Neural Networks for Online Disturbance Detection in Satellite Image Time Series

A satellite image time series (SITS) contains a significant amount of temporal information. By analysing this type of data, the pattern of the changes in the object of concern can be explored. The natural change in the Earth’s surface is relatively slow and exhibits a pronounced pattern. Some natural events (for example, fires, floods, plant diseases, and insect pests) and human activities (for example, deforestation and urbanisation) will disturb this pattern and cause a relatively profound change on the Earth’s surface. These events are usually referred to as disturbances. However, disturbances in ecosystems are not easy to detect from SITS data, because SITS contain combined information on disturbances, phenological variations and noise in remote sensing data. In this paper, a novel framework is proposed for online disturbance detection from SITS. The framework is based on long short-term memory (LSTM) networks. First, LSTM networks are trained by historical SITS. The trained LSTM networks are then used to predict new time series data. Last, the predicted data are compared with real data, and the noticeable deviations reveal disturbances. Experimental results using 16-day compositions of the moderate resolution imaging spectroradiometer (MOD13Q1) illustrate the effectiveness and stability of the proposed approach for online disturbance detection.

Building outline extraction from airborne laser scanning data over urban areas

Urban building extraction is an important research topic in urban studies. We present a three-step method to detect the outline of buildings, Firstly, DEM (Digital Elevation Model) is separate from DSM (Digital Surface Model), in our algorithm, and surface based method is adopted. The second step is to classify buildings and other off-terrain objects. Texture characters are selected to classify them. Four parameters (Contrast, Energy, Entropy, and Homogeneity) are defined to describe textures. Rough set method is used to distinguish between buildings and non-buildings based on knowledge gained from training data. Finally, we convert images which buildings are detected to polygons, building outlines are obtained. The data set we use in this paper is located in Ada County of Idaho State, USA. Experiments show building detection rate with our method is more than 85%. It shows the method adopted in this paper is feasible.

Fast detection of changed blocks in land use map

Using remote sensing images to monitor land use information, extract changed information, which has a wide range of research value and is the key technologies in the field of land use monitoring. The article analyses the current methods of change detection and designs a fast detection method of changed blocks in land use map with the before and after remote sensing images. The method uses the spirit of object-oriented technology, and makes the polygons in the land use map directly as the objects for research. Then calculates the feature value(mean value of layer 1 and layer 2, NDVI, GLCM Homogeneity of layer 3 and layer 4 used in this article ) of each objects in the before and after remote sensing images. After normalized processing for feature value, calculates the Euclidean distance between feature vectors. Finally, extracts the changed polygons in land use map according to the threshold. The experiment proves that the articles method can fast and accurately detect the changed blocks in land use map.

Improved registration method for infrared and visible remote sensing image using NSCT and SIFT

This paper introduces an improved image registration method for infrared and visible remote sensing image based on NSCT and SIFT algorithm. As the infrared and visible spectral characteristics of remote sensing images are inconsistent, the gray difference between these two images are quite distinct, so there are less matching points by using SIFT algorithm directly. The method of NSCT can decompose the image to a series of frequency channels and high frequency channels contain the edge details of the original image. It could get more matching points and improve the matching rate and the accuracy of registration by using SIFT registration method between two high frequency channels of decomposed images.

Decision tree coupled with feature optimization for object-based classification of ZY-1-02C satellite images

The Separability and Thresholds (SEaTH) algorithm calculates the the SEparability and the corresponding THresholds of object classes for any number of given features. However, it is applicable only to the normally distributed training data. To cope with the problem, The Classification And Regression Tree (CART) coupled with SEaTH for object-based classification approach is proposed in the paper. The idea of this method is derived from the merits of the CART which can effectively analyze the non-normally distributed data and automatically create the classification tree. A comparison of classification results demonstrate that the solution for object-based classification proposed in this article can be used to obtain a higher classification accuracy than SEaTH classification.

Practical Bottom-up Golf Course Detection Using Multispectral Remote Sensing Imagery

The rapid growth of golf course has constituted a nonnegligible threat to conservation of cropland and water resource in China. To monitor golf course at a large scale with low cost, a practical bottom-up golf course detection approach using multispectral remote sensing imagery is proposed. First of all, turfgrass, water-body and bunker are determined as the basic elements based on analyzing golf course land-use characteristics. Secondly, turfgrass and water-body are extracted using spectral indexes and these two basic elements are combined as region-of-interest under guidance of prior-knowledge. Afterwards, bunker is extracted by spectral mixture analysis restricted to region-of-interest. Finally, fuzzy C-means is adopted to recognize golf course using landscape metrics. A SPOT-5 HRG multispectral image of Beijing is used to validate the proposed method, and detection rate and false alarm rate are 86.67% and 38.10% respectively.

Knowledge-guided golf course detection using a convolutional neural network fine-tuned on temporally augmented data

Abstract. The tremendous success of deep learning models such as convolutional neural networks (CNNs) in computer vision provides a method for similar problems in the field of remote sensing. Although research on repurposing pretrained CNN to remote sensing tasks is emerging, the scarcity of labeled samples and the complexity of remote sensing imagery still pose challenges. We developed a knowledge-guided golf course detection approach using a CNN fine-tuned on temporally augmented data. The proposed approach is a combination of knowledge-driven region proposal, data-driven detection based on CNN, and knowledge-driven postprocessing. To confront data complexity, knowledge-derived cooccurrence, composition, and area-based rules are applied sequentially to propose candidate golf regions. To confront sample scarcity, we employed data augmentation in the temporal domain, which extracts samples from multitemporal images. The augmented samples were then used to fine-tune a pretrained CNN for golf detection. Finally, commission error was further suppressed by postprocessing. Experiments conducted on GF-1 imagery prove the effectiveness of the proposed approach.