Mapping dry/wet snow cover in the Indian Himalayas using IRS multispectral imagery

Application of remote sensing data has been made to differentiate between dry/wet snows in a glacierized basin. The present study has been carried out in the Gangotri glacier, Himalayas, using IRS-LISS-III multispectral data for the period March-November 2000 and the digital elevation model. The methodology involves conversion of satellite sensor data into reflectance values, computation of NDSI, determination of the boundary between dry/wet snows from spectral response data, and threshold slicing of the image data. The areas of dry snow cover and wet snow cover for different dates of satellite overpasses have been computed. The dry snow area has been compared with non-melting area obtained from the temperature lapse rate method, and the two are found to be in close mutual correspondence (< 15%). It is observed that there occur four water-bearing zones in the glacierized basin: dry snow zone, wet snow zone, exposed glacial ice and moraine-covered glacial ice, each of which possesses unique hydrological characteristics and can be distinguished and mapped from satellite sensor data. It is suggested that input of data on the position and extent of specifically wet snow and exposed glacial ice, which can be directly derived from remote sensing, should improve hydrological simulation of such basins.     

Role of geological and geomorphological factors in ground water exploration: a study using IRS LISS data

Various geological and geomorphical factors play a major role at different levels in the occurrence and movement of ground water in any terrain, especially in hard rock crystalline formations. In the present study three different test sites in the form of drainage basins representing diverse geological set ups in parts of Karnataka, India have been chosen to compare and evaluate the various factors that govern the ground water occurrence and also to assess the utility of Indian Remote Sensing Satellite (IRS) sensor data in ground water mapping and condition assessment. Selected digitally enhanced products were generated and utilized for extraction of relevant details on lithology, structure and landforms by their distinct image characteristics. The integration of the details extracted from digitally enhanced products along with morphometric parameters derived from the drainage maps, helped in the assessment of ground water conditions in each basin. The comparative assessment of the ground water controlling factors of all the three drainage basins has shown that, though similar types of hydrogeomor-phic landforms have developed over these drainage basins, they vary in terms of their characteristic behaviour and spatial distribution. The results obtained encourage the use of IRS sensor data for ground water targeting especially in hard rock terrain, where it is more complex and difficult.     

Requirements for labelling forest polygons in an object-based image analysis classification

The ability to spatially quantify changes in the landscape and create land-cover maps is one of the most powerful uses of remote sensing. Recent advances in object-based image analysis (OBIA) have also improved classification techniques for developing land-cover maps. However, when using an OBIA technique, collecting ground data to label reference units may not be straightforward, since these segments generally contain a variable number of pixels as well as a variety of pixel values, which may reflect variation in land-cover composition. Accurate classification of reference units can be particularly difficult in forested land-cover types, since these classes can be quite variable on the ground. This study evaluates how many prism sample locations are needed to attain an acceptable level of accuracy within forested reference units in southeastern New Hampshire (NH). Typical forest inventory guidelines suggest at least 10 prism samples per stand, depending on the stand area and stand type. However, because OBIA segments group pixels based on the variance of the pixels, fewer prism samples may be necessary in a segment to properly estimate the stand composition. A bootstrapping statistical technique was used to find the necessary number of prism samples to limit the variance associated with estimating the species composition of a segment. Allowing for the lowest acceptable variance, a maximum of only six prism samples was necessary to label forested reference units. All polygons needed at least two prism samples for classification.     

用于数字图像传感器的脉冲宽度调制读出方法研究

为提高数字像素图像传感器的动态范围,提出了一种具有自适应参考电压的脉冲宽度调制读出方法。该方法将像素阵列分成包含相同数目像素的像素块,通过参考电压产生模块使每个像素块的参考电压和像素块内光照强度相关,理论上这种结构能够将数字像素图像传感器的动态范围从48 dB提升至96 dB,实际仿真结果为88.16 dB。分析了像素分块内主要的噪声来源和参考电压产生模块的采样电容引入的偏差。采用65 nm CMOS工艺实现了4×4的像素块电路,在高光强和弱光强条件下分别将电路输出同理论计算值相比较,并分析了产生误差的原因。     

Study of digital image processing techniques for leaf disease detection and classification

Multimedia Tools and Applications - In this paper, we address a comprehensive study on disease recognition and classification of plant leafs using image processing methods. The traditional manual...     

森林病虫害监测中的无人机图像分割算法比较

以错分率、相对最终测量精度以及运行时间为评价标准,利用无人机采集的油松及沙棘正射图像为测试图像,对6种基于像素聚类及分水岭的图像分割算法的性能进行了定性分析及定量比较。实验结果表明,受灾林区图像的分割算法的性能与图像拍摄高度、噪声等因素密切相关。最后,给出了受灾林区无人机正射图像分割算法应用的指导性建议。     

Object-aware image thumbnailing using image classification and enhanced detection of ROI

Thumbnail images are used to display a large collection of photos in various digital devices. It aims for people to browse and search the image collection effectively. The provided thumbnail images are expressed in a much lower resolution compared to the resolution of the original image. Thus, it faces a significant problem of how to represent the content of a given image effectively in a tiny thumbnail image. Many image thumbnailing methods have been presented in literature for this purpose. However, the existing thumbnailing methods are designed to use a single method to all kinds of images, regardless of image contents. On the other hand, the proposed method employs two different thumbnail generation methods either of which is applied according to corresponding image context. To achieve this, we first classify images into two groups by detecting the object existence. Then, an ROI cropping method using a saliency map is presented for images with objects, in order to represent the important region of images in the thumbnail. Images without any interesting objects, such as landscape images, are considered to be resized by using a simple scaling method to maintain the whole image context. Experimental results show that the proposed method yields comparable performance on a variety of datasets.     

Ensemble of feature sets and classification algorithms for sentiment classification

In this paper, we make a comparative study of the effectiveness of ensemble technique for sentiment classification. The ensemble framework is applied to sentiment classification tasks, with the aim of efficiently integrating different feature sets and classification algorithms to synthesize a more accurate classification procedure. First, two types of feature sets are designed for sentiment classification, namely the part-of-speech based feature sets and the word-relation based feature sets. Second, three well-known text classification algorithms, namely na?¨ve Bayes, maximum entropy and support vector machines, are employed as base-classifiers for each of the feature sets. Third, three types of ensemble methods, namely the fixed combination, weighted combination and meta-classifier combination, are evaluated for three ensemble strategies. A wide range of comparative experiments are conducted on five widely-used datasets in sentiment classification. Finally, some in-depth discussion is presented and conclusions are drawn about the effectiveness of ensemble technique for sentiment classification.     

Detection of cracks using image processing algorithms implemented in hardware

Cracks originate in a multitude of industrial artefacts and their detection is of considerable social and economic importance. The article discusses various image processing algorithms for recognizing cracks and their implementation in fast electronic hardware. The authors maintain that this inspection task is so important that it would be well worthwhile building equipment specifically for detecting cracks. With suitable optics, it should be applicable to a wide range of industries.     

Evaluation of supervised classification algorithms for identifying crops using airborne hyperspectral data

Sufficient training data must be acquired to classify areas of interest using a supervised classification method and hyperspectral data. However, the relatively small size of agricultural plots in Japan means that there is no training area large enough to represent a feature of interest. In this study, a new method for identifying crops using hyperspectral remotely sensed data has been proposed in order to resolve the problem of identifying training areas in agricultural crops. This method was then compared with conventional methods. The proposed method was found to be most effective for identifying crops using hyperspectral data in an agricultural land area.     

Intrinsic evolvable hardware platform for digital circuit design and repair using genetic algorithms

A hardware/software platform for intrinsic evolvable hardware is designed and evaluated for digital circuit design and repair on Xilinx Field Programmable Gate Arrays (FPGAs). Dynamic bitstream compilation for mutation and crossover operators is achieved by directly manipulating the bitstream using a layered framework. Experimental results on a case study have shown that benchmark circuit evolution from an unseeded initial population, as well as a complete recovery of a stuck-at fault is achievable using this platform. An average of 0.47 μs is required to perform the genetic mutation, 4.2 μs to perform the single point conventional crossover, 3.1 μs to perform Partial Match Crossover (PMX) as well as Order Crossover (OX), 2.8 μs to perform Cycle Crossover (CX), and 1.1 ms for one input pattern intrinsic evaluation. These represent a performance advantage of three orders of magnitude over the JBITS software framework and more than seven orders of magnitude over the Xilinx design tool driven flow for realizing intrinsic genetic operators on Xilinx Virtex Family devices.     

Feature selection by genetic algorithms in object-based classification of IKONOS imagery for forest mapping in Flanders, Belgium

Obtaining detailed information about the amount of forest cover is an important issue for governmental policy and forest management. This paper presents a new approach to update the Flemish Forest Map using IKONOS imagery. The proposed method is a three-step object-oriented classification routine that involves the integration of 1) image segmentation, 2) feature selection by Genetic Algorithms (GAs) and 3) joint Neural Network (NN) based object-classification. The added value of feature selection and neural network combination is investigated. Results show that, with GA-feature selection, the mean classification accuracy (in terms of Kappa Index of Agreement) is significantly higher (p < 0.01) than without feature selection. On average, the summed output of 50 networks provided a significantly higher (p < 0.01) classification accuracy than the mean output of 50 individual networks. Finally, the proposed classification routine yields a significantly higher (p < 0.01) classification accuracy as compared with a strategy without feature selection and joint network output. In addition, the proposed method showed its potential when few training data were available.     

Texture classification of logged forests in tropical Africa using machine-learning algorithms

This Letter describes a procedure that incorporates textural measures in the classification of logged forests from Landsat Thematic Mapper data. The objective was to increase classification accuracy by applying recently developed algorithms in machine learning that are fast in training. Three voting classification algorithms, Arc-4x, Adaboost and bagging were also tested. Initial results using a decision tree classifier showed that adding selected textural measures increased the accuracy of logged forest classification by almost 40%, although the class accuracy for logged forests was only approximately 50% when using spectral and textural features combined. No further significant increase in the classification of logged forests was obtained by voting classification.     

Improving the performance of convolutional neural network for skin image classification using the response of image analysis filters

Neural Computing and Applications - In this work, we focus in the analysis of dermoscopy images using convolutional neural networks (CNNs). More specifically, we investigate the value of augmenting...     

Screening for diabetic retinopathy using computer based image analysis and statistical classification

Diabetic retinopathy is one of the most common causes of blindness in Europe. However, efficient therapies do exist. An accurate and early diagnosis and correct application of treatment can prevent blindness in more than 50% of all cases. Digital imaging is becoming available as a means of screening for diabetic retinopathy. As well as providing a high quality permanent record of the retinal appearance, which can be used for monitoring of progression or response to treatment, and which can be reviewed by an ophthalmologist, digital images have the potential to be processed by automatic analysis systems. We have described the preliminary development of a tool to provide automatic analysis of digital images taken as part of routine monitoring of diabetic retinopathy in our clinic. Various statistical classifiers, a Bayesian, a Mahalanobis, and a KNN classifier were tested. The system was tested on 134 retinal images. The Mahalanobis classifier had the best results: microaneurysms, haemorrhages, exudates, and cotton wool spots were detected with a sensitivity of 69, 83, 99, and 80%, respectively.     

基于遗传算法的结肠癌基因选择与样本分类

提出了一种基于两轮遗传算法的用于结肠癌微阵列数据基因选择与样本分类的新方法。该方法先根据基因的Bhattacharyya距离指标过滤大部分与分类不相关的基因,而后使用结合了遗传算法和CFS（Correlation-based Feature Selection）的GA/CFS方法选择优秀基因子集,并存档记录这些子集。根据存档子集中基因被选择的频率选择进一步搜索的候选子集,最后以结合了遗传算法和SVM的GA/SVM从候选基因子集中选择分类特征子集。把这种GA/CFS-GA/SVM方法应用到结肠癌微阵列数据,实验结果及与文献的比较表明了该方法效果良好。     

Exploring the synergistic use of multi-scale image object metrics for land-use/land-cover mapping using an object-based approach

This study presents a new method for the synergistic use of multi-scale image object metrics for land-use/land-cover mapping using an object-based classification approach. This new method can integrate an object with its super-objects’ metrics. The entire classification involves two object hierarchies: (1) a five-level object hierarchy to extract object metrics at five scales, and (2) a three-level object hierarchy for the classification process. A five-level object hierarchy was developed through multi-scale segmentation to calculate and extract both spectral and textural metrics. Layers representing the hierarchy at each of the five scales were then intersected by using the overlay tool, an intersected layer was created with metrics from all five scales, and the same geometric elements were retained as those of the objects of the lowest level. A decision tree analysis was then used to build rules for the classification of the intersected layer, which subsequently served as the thematic layer in a three-level object hierarchy to identify shadow regions and produce the final map. The use of multi-scale object metrics yielded improved classification results compared with single-scale metrics, which indicates that multi-scale object metrics provide valuable spatial information. This method can fully utilize metrics at multiple scales and shows promise for use in object-based classification approaches.     

Assessment of forest disturbances by selective logging and forest fires in the Brazilian Amazon using Landsat data

The rapid environmental changes occurring in the Brazilian Amazon due to widespread deforestation have attracted the attention of the scientific community for several decades. A topic of particular interest involves the assessment of the combined impacts of selective logging and forest fires. Forest disturbances by selective logging and forest fires may vary in scale, from local to global changes, mostly related to the increase of carbon dioxide released into the atmosphere. Selective logging activities and forest fires have been reported by several studies as important agents of land-use and land-cover changes. Previous studies have focused on selective logging, but forest fires on a large scale in tropical regions have yet to be properly addressed. This study involved a more comprehensive investigation of temporal and basin-wide changes of forest disturbances by selective logging and forest fires using remotely sensed data acquired in 1992, 1996, and 1999. Landsat imagery and remote-sensing techniques for detecting burned forests and estimating forest canopy cover were applied. We also conducted rigorous ground measurements and observations to validate remote-sensing techniques and to assess canopy-cover impacts by selective logging and forest fires in three different states in the Brazilian Amazon. The results of this study showed a substantial increase in total forested areas impacted by selective logging and forest fires from approximately 11,800 to 35,600 km² in 1992 and 1999, respectively. Selective logging was responsible for 60.4% of this forest disturbance in the studied period. Approximately 33% and 7% of forest disturbances detected in the same period were due to impacts of forest fires only and selective logging and forest fires combined, respectively. Most of the degraded forests (～90%) were detected in the states of Mato Grosso and Pará. Our estimates indicated that approximately 5467, 7618, and 17437 km² were new areas of selective logging and/or forest fires in 1992, 1996, and 1999, respectively. Protected areas seemed to be very effective in constraining these types of forest degradation. Approximately 2.4% and 1.3% of the total detected selectively logged and burned forests, respectively, were geographically located within protected areas. We observed, however, an increasing trend for these anthropogenic activities to occur within the limits of protected areas from 1992 to 1999. Although forest fires impacted the least area of tropical forests in the study region, new areas of burned forests detected in 1996 and 1999 were responsible for the greatest impact on canopy cover, with an estimated canopy loss of 18.8% when compared to undisturbed forests. Selective logging and forest fires combined impacted even more those forest canopies, with an estimated canopy loss of 27.5%. Selectively logged forest only showed the least impact on canopy cover, with an estimated canopy loss of 5%. Finally, we observed that forest canopy cover impacted by selective logging activities can recover faster (up to 3 years) from impact when compared to those forests disturbed by fires (up to 5 years) in the Amazon region.     

Complex approach to choosing algorithms of compression and error-correcting coding in digital image transmission via communication channels

The problem of choosing the algorithms of compression and error-correcting coding for transmission of digital images via communication channels is considered. The quality criteria for output images are analyzed and a technique for simulating errors (faults) in a communication channel is proposed. The possibility of considerable improvement of noise immunity of compressed images is demonstrated for the compression method based on hierarchical grid interpolation. Glumov Nikolai Ivanovich (b. 1962) graduated from Kuibyshev Aviation Institute (now Samara State Aerospace University) in 1985. In 1994, he defended his Ph.D. (engineering) thesis. At present, Glumov is a senior scientist at the Institute of Image Processing Systems, Russian Academy of Sciences. His scientific interests include image processing and recognition, image compression, and simulation of digital image formation systems. He has more than 60 publications, including 20 articles and a monograph (with co-authors). N.I. Glumov is a member of the Russian Association of Image Recognition and Analysis.     

A method for delineating riparian forests using region-based image classification and depth-to-water analysis

Riparian formations are often narrow strips of vegetation near the banks of streams governed by good water availability. With the advent of high-resolution satellite imagery, the study of riparian forests using space-borne remote sensing has gained more attention. However, the sole use of remotely sensed data is seldom sufficient to delineate riparian forests and their special hydrological and geomorphological context should also be considered. In this study, we propose a twofold method to delineate riparian forests in a Brazilian savannah context. Four sites on the banks of the Pandeiros River were used to test our approach, each in a different hydrological context. In our approach, the hydrographic network and a digital surface model are processed using the depth-to-water analysis to create a mask of the riparian zone, then the riparian forests are extracted using region-based image classification. Both steps are fully explained. Three region-based image classification programs (e-Cognition, Sistema de Processamento de Informações Georeferenciadas (SPRING), and MAGIC (map-guided ice classification)) are briefly described and tested. A special validation scheme was created using the independent interpretation of five photo-interpreters to test the accuracy of the results. All three programs achieved a success rate of over 90%. The approach is also tested on a much larger area of the Pandeiros River to assess its applicability in a more operational context. The discussion focuses on methodological issues and the advantages and drawbacks of the approach.