基于分数阶微分视频融合的森林烟火检测算法

森林火灾检测是国内外林业应用研究的重要课题之一。及时准确地检测到森林火灾,对于森林健康及环境安全意义重大。现有的利用视频技术检测森林火灾的方法大多针对单一波段,如可见光波段或红外波段的视频信息进行分析,然而在实际应用过程中,由于森林环境复杂,基于单一波段视频信息检测火灾的结果欠佳。现阶段,基于多个波段的森林火灾检测方法非常少。本文综合利用红外及可见光视频特征,提出了一种基于分数阶微分视频融合的森林烟火检测算法,将分数阶微分理论引入红外视频和可见光视频融合中,利用分数阶微分算子对两个波段视频进行融合,然后利用背景去除法检测融合视频中的异常帧,且对异常帧图像及其与背景帧的差分图像分别进行图像分割,最终得到检测出的森林烟火区域。采用空间频率、平均梯度、森林火灾检测准确率和森林火灾检测时间误差度4个测度对本文算法和基于区域能量融合算法、基于窗口方差融合算法、基于HSI变换融合算法进行定量分析和比较。结果表明,本文算法的融合视频的融合效果最佳,并且森林火灾检测准确率和森林火灾检测时间误差均明显优于其他3种算法,说明本文提出的算法具有较好的有效性和准确性,为森林火灾检测提供了有利的新途径。      

秦岭林区森林火灾起火点查找方法探讨

从火灾痕迹出发,依据秦岭林区林木的生长特点和人类活动规律、森林火灾发生发展机理探讨发现,火灾遗迹能够确定起火点。     

森林火灾遥感探测技术研究进展

森林火灾是陆地生态系统重要的自然干扰之一,也是森林面临的主要自然灾害。多源遥感技术在森林火灾探测中应用,使得森林火灾的早期探测与实时监测成为可能,遥感技术已成为森林火灾监测和防控的重要手段。本研究综述了遥感技术在森林火灾相关研究方面的应用进展,从灾前、灾时、灾后3个阶段,分析了遥感技术和方法在森林可燃物调查及载量评估、火场态势监测、火险等级预测预报、火烧迹地识别、火后森林受害评估以及植被修复等方面的应用,总结了现有研究方法中存在的问题,展望了未来森林火灾探测技术的发展方向。多源多尺度遥感探测技术如将无人机、雷达、航空遥感与航天遥感等互相结合,多方位进行森林火前火后监测,为火险等级预报、森林火灾防控、火后森林结构和功能的恢复提供依据。     

基于可见光视频的森林火灾识别算法

以森林火灾远程视频预警监控工程为依托,对森林火灾发生、发展的可见光视频图象进行研究,提出森林火灾识别算法,并进行处理。分析了基于视频的森林火灾火焰特征,指出火焰特征主要包括颜色变化、面积变化、边缘变化、形体变化、闪动规律和整体移动等。在此基础上,提出了视频图像中的森林火灾区域检测方法与森林火灾识别方法;根据图像区域分割匹配算法,以火焰颜色特征和面积变化为火灾判别依据,统计疑似火灾区域面积,定时地对其进行两两匹配,实现对森林火灾图像的实时检测和识别。经实际验证,该算法的查全率与查确率分别达到72.22%和92.86%。     

建阳市森林火灾时空分布特征

收集建阳市1985-2008年林火统计数据,包括火灾地点、起火时间、熄火时间、过火面积、受害森林面积和起火原因等因子,统计分析研究区域内森林火灾发生的时空分布规律。结果表明,森林火灾的发生与气候变化及不当的人类活动相关,并提出防范森林火灾的有关对策与建议。     

基于红外探测的地面林火目标自动检测与追踪系统设计

针对红外林火图像的特点,从实际应用的角度出发,在FPGA+DSP构建的硬件平台上,实现了森林灰度图像的正确采集和进行有无火点的判断,并提出了图像边缘检测和自适应阈值相结合提取林火目标的方法,达到了林火目标的自动检测;然后利用通信协议和算法控制云台转动,使热像仪的光学系统主光轴始终对准最大灰度值点,达到追踪的效果.在多种...     

周宁县森林防火关键期气象因子分析

该文运用比较分析的方法,对周宁县近10年的森林火灾和气象数据进行了研究分析。结果表明:(1)周宁县在每年的3、4月是发生森林火灾的高风险期,也是森林防火的关键期;(2)在3、4月森林火灾发生较多的年份,降雨量明显少于其他年份,相对湿度也明显小于其他年份,而气温高于其他年份;(3)风速与森林火灾起火的对应关系不明显,对其影响相对较小。     

基于非参数检验方法吉林省重特大森林火灾影响因素分析

根据吉林省1969—1980年的重特大森林火灾的统计数据,借助SPSS17.0统计软件,运用非参数检验的方法,分析了不同地区、起火月份、起火时间、林型、林龄、疏密度、气温、风速等因素对受害森林面积和过火总面积的影响。结果表明:不同地区的过火总面积之间存在极其显著性差异,延边地区的起火次数最多(127次),过火总面积的均值最大(528.878 9 hm2);不同起火月份的受害森林面积之间存在显著性差异,3月份受害森林面积的均值最大(572.021 4 hm2),而起火次数较多的月份主要集中在4、5、9、10月份,应注意春、秋两季的重特大森林火灾预防。     

天水市秦州区森林防火浅谈

通过分析森林火灾的危害、起火原因及影响火灾的因素,提出了森林火灾扑救及预防与治理的措施。     

基于ZigBee无线传感器网络的森林火灾监测系统的研究

该文在探讨森林起火因素的基础上,构建了一种基于ZigBee无线传感器网络的森林火灾实时监测系统.该系统给出了森林火灾无线传感器网络监测系统的体系结构,重点设计了基于CC2430芯片的网络节点硬件电路,详尽地讨论了网络的数据传输流程;该系统能够监测林区温湿度等相关环境参数的变化,为有关部门采取相应的防火或灭火措施提供决策依据.      

Evaluating high resolution SPOT 5 satellite imagery for crop identification

High resolution satellite imagery offers new opportunities for crop monitoring and assessment. A SPOT 5 image acquired in May 2006 with four spectral bands (green, red, near-infrared, and short-wave infrared) and 10-m pixel size covering intensively cropped areas in south Texas was evaluated for crop identification. Two images with pixel sizes of 20 m and 30 m were also generated from the original image to simulate coarser resolution satellite imagery. Two subset images covering a variety of crops with different growth stages were extracted from the satellite image and five supervised classification techniques, including minimum distance, Mahalanobis distance, maximum likelihood, spectral angle mapper (SAM), and support vector machine (SVM), were applied to the 10-m subset images and the two coarser resolution images to identify crop types. The effects of the short-wave infrared band and pixel size on classification results were also examined. Kappa analysis showed that maximum likelihood and SVM performed better than the other three classifiers, though there were no statistical differences between the two best classifiers. Accuracy assessment showed that the 10-m, four-band images based on maximum likelihood resulted in the best overall accuracy values of 91% and 87% for the two respective sites. The inclusion of the short-wave infrared band statistically significantly increased the overall accuracy from 82% to 91% for site 1 and from 75% to 87% for site 2. The increase in pixel size from 10 m to 20 m or 30 m did not significantly affect the classification accuracy for crop identification. These results indicate that SPOT 5 multispectral imagery in conjunction with maximum likelihood and SVM classification techniques can be used for identifying crop types and estimating crop areas.     

Archeological methodology and remote sensing

We have shown that the different spectral surveying techniques and the resultant imagery vary in their applicability to archeological prediction and exploration, but their applications are far broader than we have indicated. Their full potential, to a considerable extent, still remains unexplored. Table 1 is a chart of the more common sensor systems useful to archeological investigators. Several kinds of photography, thermal infrared imagery, and radar imagery are listed. Checks in various categories of direct and indirect utility in archeological research indicate that the different systems do provide varying degrees of input for studies in these areas. Photography and multispectral photography have the broadest applications in this field. Standard black-and-white aerial photography generally serves the purposes of archeological exploration and site analysis better than infrared scanner imagery, radar, or color photography. However, the real value of remotesensing experimentation lies in the utilization of different instruments and in the comparison and correlation of their data output. It can be stated without doubt that there is no one all-purpose remotesensing device on which the archeologist can rely that will reveal all evidence of human occupations. Remote-sensing data will not replace the traditional ground-based site survey, but, used judiciously, data gathered from aerial reconnaissance can reveal many cultural features unsuspected from the ground. The spectral properties of sites distinguishable by various types of remote sensors may perhaps be one of their most characteristic features, and yet the meaning of the differential discrimnination of features has not been determined for the most part, since such spectral properties are poorly understood at this date. The difficulty in isolating the causes of acceptable definition in certain portion of the spectrum and the lack of acceptable definition in others suggests that the evaluation of remote-sensing devices discussed in this article is not always applicable to all environmental zones at all times and for all types of cultural features. The uncontrollable variables of terrain, ground cover, weather, types of archeological manifestations, and other factors all play an important role in the utility of the imagery to the archeologist. Factors within the control of the photographer or archeolgist, such as altitude, position of the sun, and the direction of flight, can greatly influence the utility of the sensor data. In addition, the variables should not be considered solely as they affect resolution. Resolution, per se, although an important photogrammetric parameter of remote-sensing imagery, is by no means the only important factor in data analysis. The synoptic overview, which is provided by aerial imagery, is frequently as necessary in interpretation as the spotting and identification of individual cultural features. Stated more simply, we might say: "To understand, one most certainly must see the forest as well as the individual trees." For maximum data retrieval, it is necessary that the archeologist attempt to utilize as many different types of remote-sensing devices under as many variable seasonal and climatic conditions as his resources and skill will allow. Only then he can select the most efficient system for the purpose in his area of study.     

Distinguishing blueberry bushes from mixed vegetation land use using high resolution satellite imagery and geospatial techniques

Blueberry orchards for commercial production are increasingly common in Georgia and other southeastern states. The blueberry bushes grow closer to the ground compared to pine trees and other forest plants. It is, therefore, difficult to distinguish blueberry bushes from other trees and shrubs in a farm scenario where tall grasses are abundant and pine trees are in close proximity. The goal of this study was to apply advanced image processing techniques with high resolution multispectral imagery to distinguish blueberries in mixed vegetation. We used high resolution 2.15 m multispectral QuickBird imagery along with high end image processing techniques to identify blueberry bushes of a small orchard, located in Pike County, Georgia. Principal component bands of multispectral QuickBird images, taken on May 22 and June 6, 2006, were classified using an unsupervised ISODATA classification technique and the WARD minimum variance method. Four classes, including forest, blueberry bushes, tall grasses, and cut or dwarf grasses were extracted from the classified images for ground truth and subsequent delineation of spatial cells that represented the blueberry bushes. For the image taken on May 22 the blueberry bushes were distinguished with a 53% producer's accuracy, a 100% user's accuracy, and a kappa statistic of 0.24. This low accuracy was attributed to mixture of the blueberry bushes and the tall grasses that were not cut when the image was acquired. However, the June 6 image proved to be more suitable for distinguishing blueberry bushes from the pine forest and grasses. The producer's accuracy was 100%, the user's accuracy was 94% and the kappa statistic was 0.65. Based on the results from this study it can be concluded that high resolution imagery and high end image processing techniques can be used to help distinguish mature blueberry bushes from a forest and grass land cover if the area is well maintained. The study also suggests that commercial or large scale blueberry orchards can easily be micro-managed with the use of remotely sensed images and geospatial technology.     

Advantage of multispectral imaging with sub-centimeter resolution in precision agriculture: generalization of training for supervised classification

Nowadays it is known how to resolve many questions through satellite imagery such as Landsat 8 and the like, both from the theoretical point of view, i.e. research, as well as from the practical standpoint, e.g. commercial applications. This study evaluated the possibility of generalizing the training for supervised classification of multispectral images with sub-centimeter resolution. Images were taken under uncontrolled conditions of lighting and sun-target-sensor geometry and in the presence of normal interference in the agricultural environment. The images were obtained by the DuncanTech MS3100 camera (Auburn, CA, USA), a multispectral camera (green, red and near infra-red) mounted on a mobile ground platform and transformed into reflectance. For each element present (leaves, stems, spikes, soil, shadows, spectral references and sampling implements), a representative area was delimited in each image. These regions of interest were used, first, to quantify the separability of the classes. The next step was to define groups for cross-validation within these regions of interest; ten-folds were defined randomly with the constraint of a uniform distribution of classes. These folds were used in training and evaluation of the supervised classification using spectral angle mapper, maximum likelihood and decision trees. Spectral angle mapper correctly classified 49.2 % of cases, the maximum likelihood achieved a success rate of 86.8 % and the decision tree correctly classified 99.5 % of the spectral signatures. These results prove that multispectral images taken under uncontrolled conditions can be successfully classified by a generalized model that takes advantage of the higher spatial resolution. This opens a new line in which those pixels that do not correspond to vegetation, which bias the estimates of the crop parameters and complicate the recognition of objects, could be automatically masked.     

Development of a robotic detection system for greenhouse pepper plant diseases

Automation of disease detection and monitoring can facilitate targeted and timely disease control, which can lead to increased yield, improved crop quality and reduction in the quantity of applied pesticides. Further advantages are reduced production costs, reduced exposure to pesticides for farm workers and inspectors and increased sustainability. Symptoms are unique for each disease and crop, and each plant may suffer from multiple threats. Thus, a dedicated integrated disease-detection system and algorithms are required. The development of such a robotic detection system for two major threats of bell pepper plants: powdery mildew (PM) and Tomato spotted wilt virus (TSWV), is presented. Detection algorithms were developed based on principal component analysis using RGB and multispectral NIR-R-G sensors. High accuracy was obtained for pixel classification as diseased or healthy, for both diseases, using RGB imagery (PM: 95%, TSWV: 90%). NIR-R-G multispectral imagery yielded low classification accuracy (PM: 80%, TSWV: 61%). Accordingly, the final sensing apparatus was composed of a RGB sensor and a single-laser-beam distance sensor. A relatively fast cycle time (average 26.7 s per plant) operation cycle for detection of the two diseases was developed and tested. The cycle time was mainly influenced by sub-tasks requiring motion of the manipulator. Among these tasks, the most demanding were the determination of the required detection position and orientation. The time for task completion may be reduced by increasing the robotic work volume and by improving the algorithm for determining position and orientation.     

Phenotyping a diversity panel of quinoa using UAV-retrieved leaf area index,SPAD-based chlorophyll and a random forest approach

Given its high nutritional value and capacity to grow in harsh environments, quinoa has significant potential to address a range of food security concerns. Monitoring the development of phenotypic traits during field trials can provide insights into the varieties best suited to specific environmental conditions and management strategies. Unmanned aerial vehicles (UAVs) provide a promising means for phenotyping and offer the potential for new insights into relative plant performance. During a field trial exploring 141 quinoa accessions, a UAV-based multispectral camera was deployed to retrieve leaf area index (LAI) and SPAD-based chlorophyll across 378 control and 378 saline-irrigated plots using a random forest regression approach based on both individual spectral bands and 25 different vegetation indices (VIs) derived from the multispectral imagery. Results show that most VIs had stronger correlation with the LAI and SPAD-based chlorophyll measurements than individual bands. VIs including the red-edge band had high importance in SPAD-based chlorophyll predictions, while VIs including the near infrared band (but not the red-edge band) improved LAI prediction models. When applied to individual treatments (i.e. control or saline), the models trained using all data (i.e. both control and saline data) achieved high mapping accuracies for LAI (R²?=?0.977–0.980, RMSE?=?0.119–0.167) and SPAD-based chlorophyll (R²?=?0.983–0.986, RMSE?=?2.535–2.861). Overall, the study demonstrated that UAV-based remote sensing is not only useful for retrieving important phenotypic traits of quinoa, but that machine learning models trained on all available measurements can provide robust predictions for abiotic stress experiments.

     

ETM+多光谱遥感影像彩色合成最佳波段选择研究--以顺德区土地遥感图制作为例

随着计算机和遥感技术的不断发展,遥感图像解译方法也不断发展,但目视判读仍然是遥感图像解译中最重要的一种方法.如何从ETM+多光谱影像中选择出3个最佳波段并彩色合成成为遥感图像处理是一个重要的研究课题.首先分析了ETM+多光谱影像的波段特征及常见的波段组合;然后综合运用单波段的亮度差、均值、标准差、信息熵等统计特征方法,波段间相关系数矩阵方法,最佳指数法,联合熵法,典型地物光谱特征曲线法相结合分析顺德区ETM+多光谱影像,并从中选择出最佳波段组合;最后反复测试了6种赋色方案,最终的试验结果表明:对于顺德区这种典型的珠江三角洲河口平原地区的土地,利用遥感制图,ETM+遥感影像的543(RGB)波段组合为最佳目视解译波段组合.     

Evaluating high resolution SPOT 5 satellite imagery to estimate crop yield

High resolution satellite imagery has the potential to map within-field variation in crop growth and yield. This study examined SPOT 5 satellite multispectral imagery for estimating grain sorghum yield. A 60 km × 60 km SPOT 5 scene and yield monitor data from three grain sorghum fields were recorded in south Texas. The satellite scene contained four spectral bands (green, red, near-infrared and mid-infrared) with a 10-m spatial resolution. Subsets were extracted from the scene that covered the three fields. Images with pixel sizes of 20 and 30 m were also generated from the individual field images to simulate coarser resolution satellite imagery. Vegetation indices and principal components were derived from the images at the three spatial resolutions. Grain yield was related to the vegetation indices, the four bands and the principal components for each field, and for all the fields combined. The effect of the mid-infrared band on estimates of yield was examined by comparing the regression results from all four bands with those from the other three bands. Statistical analysis showed that the 10-m, four-band image and the aggregated 20-m and 30-m images explained 68, 76 and 83%, respectively, of the variation in yield for all the fields combined. The coefficient of determination between yield and the imagery increased with pixel size because of the smoothing effect. The inclusion of the mid-infrared band slightly improved the R ² values. These results indicate that high resolution SPOT 5 multispectral imagery can be a useful data source for determining within-field yield variation for crop management.