Investigation of Fish-Eye Lenses for Small-UAV Aerial Photography

Aerial photography obtained by unmanned aerial vehicles (UAVs) is a rising market for their civil application. Small UAVs are believed to close gaps in niche markets, such as acquiring airborne image data for remote sensing purposes. Small UAVs can fly at low altitudes, in dangerous environments, and over long periods of time. However, their small lightweight construction leads to new problems, such as higher agility and more susceptibility to turbulence, which has a big impact on the quality of the data and their suitability for aerial photography. This paper investigates the use of fish-eye lenses to overcome field-of-view (FOV) issues for highly agile UAV platforms susceptible to turbulence. The fish-eye lens has the benefit of a large observation area (large FOV) and does not add additional weight to the aircraft, such as traditional mechanical stabilizing systems. We present the implementation of a fish-eye lens for aerial photography and mapping purposes, with potential use in remote sensing applications. We describe a detailed investigation from the fish-eye lens distortion to the registering of the images. Results of the process are presented using low-quality sensors typically found on small UAVs. The system was flown on a midsize platform (a more stable Cessna aircraft) and also on ARCAA's small ( $≪10$ kg) UAV platform. The effectiveness of the approach is compared for the two sized platforms.      

不同大气条件下红外成像效果模拟

红外成像仿真技术是解决实际应用中对红外图像数据源需求的重要途径。大气传输是红外成像的必经环节,对红外图像质量有着重要影响,大气传输效应模拟能提高成像的真实感。同一场景在不同大气条件下红外成像的模拟能为特定的图像分析提供数据。在大气传输理论的基础上,研究了红外成像大气作用效果的模拟方法,通过飞艇平台获得的红外图像作为数据,利用大气辐射传输模型进行大气修正得到地面辐亮度基准图像,在此基础上进行了不同大气模式、温度和水汽含量下的红外图像仿真实验,并对实验结果进行了评价,取得了较为理想的仿真效果,为大气效应模拟提供了一种有效的方法。     

地面景物边缘特性分析

地面景物边缘轮廓是其红外图像和可见光图像的共有特征,边缘信息量和边缘连续性是评价图像边缘特性的重要指标,也是预测图像匹配性能的依据.提出了一种评价红外场景边缘连续性的改进计算方法,利用该方法和POE指标,对机载试验采集的不同类型场景、不同时段、不同气象条件下红外图像与可见光图像边缘特性及其变化规律进行了统计研究.试验表明:地面景物红外图像和可见光图像的边缘信息量和边缘连续性,与图像匹配概率和定位精度存在正比关系.提出的景物边缘信息量和边缘连续性指标的评价方法有效,能够作为预测场景可匹配性、场景成像稳定性的根据.     

机动飞行环境无人机航拍图像拼接技术研究

以实战环境下无人机航拍图像的全景拼接为研究目的,提出了一种适用于无人机在机动飞行条件下的航空图像拼接算法,该算法采用空间变换、特征识别、匹配相关和信息融合等图像处理技术,可实现序列图像空间旋转、变形、尺度变换等特殊情况下的无缝拼接,通过真实使用环境试验测试,该算法具有在多种机动飞行环境下航拍图像拼接准确的特点,取得了良好的效果。     

A lightweight multi-scale aggregated model for detecting aerial images captured by UAVs

Detecting the objects of interesting from aerial images captured by UAVs is one of the core modules in the UAV-based applications. However, it is very difficult to detection objects from aerial images. The reason is that the scale of objects in the aerial images captured by UAVs varies greatly and needs to meet certain real-time performance in detection. To deal with these challenges, we proposed a lightweight model named DSYolov3. We made the following improvements to the Yolov3 model: 1) multiple scale-aware decision discrimination network to detect objects in different scales, 2) a multi-scale fusion-based channel attention model to exploit the channel-wise information complementation, 3) a sparsity-based channel pruning to compress the model. Extensive experimental evaluation has demonstrated the effectiveness and efficiency of our approach. By the proposed approach, we could not only achieve better performance than most existing detectors but also ensure the models practicable on the UAVs.     

轻小型面阵摆扫热红外成像系统研究

研制了一套轻小型面阵摆扫热红外成像系统,采用面阵探测器并结合系统光学元件在翼展方向的摆扫实现了宽视场、高分辨率成像,利用环架反向补偿纠正了横滚姿态扰动导致的视场偏移。通过功能验证试验,获取了视场无偏移的宽视场高分辨率图像。系统光机结构简单,体积、重量优势明显,在轻小型无人机热红外遥感方面应用前景广阔。研究成果对推动无人机载热成像技术向宽视场、高分辨率方向发展具有一定的参考价值。     

临近空间高分辨率偏振成像仪

偏振成像技术在大气探测、环境监测、资源普查和军事侦察应用中具有十分重要的作用,该技术在航空遥感和空间遥感中已经开始使用。临近空间飞行器的发展为偏振成像遥感提供了新的应用舞台,并显示出了明显的优势。本文介绍偏振原理、偏振探测和成像方式,针对临近空间飞行器给出了一种凝视式高分辨率偏振成像系统的方案,并通过论证和分析性能得出了该方案实现的可行性。     

Mining discriminative spatial cues for aerial image quality assessment towards big data

Evaluating massive-scale aerial/satellite images quality is useful in computer vision and intelligent applications. Traditional local features-based algorithms have achieved impressive performance. However, spatial cues, i.e., geometric property and topological structure, have not been exploited effectively and explicitly. Thus, in this paper, we propose a novel method for image quality assessment towards aerial/satellite images, where discriminative spatial cues are well encoded. More specifically, in order to mine inherent spatial structure of aerial images, each image is segmented into several basic components such as buildings, airport and playground. Afterwards, a weighted region adjacency graph (RAG) is built based on the basic components to represent the spatial feature of each aerial image. We integrate the spatial feature with other transform domain features, and train a support vector regression model to achieve image quality assessment. Experiments demonstrate that our method shows competitive or even better performance compared with several state-of-the-art algorithms.     

Deep quality assessment toward defogged aerial images

In order to improve the visual appearance of defogged of aerial images, in this work, a novel defogging algorithm based on conditional generative adversarial network is proposed. More specifically, the training process is carried out through an end-to-end trainable deep neural network. In detail, we upgrade the traditional adversarial loss function by incorporating an L1-regularized gradient to encode a rich set of detailed visual information inside each aerial image. In practice, to our best knowledge, existing image quality assessment algorithms might have deviation and supersaturation distortion on aerial images. To alleviate this problem, we leverage a random forest classification model to learn the mapping relationship between aerial image features and the quality ranking results. Subsequently, we transform the objective of defogged image quality assessment into a classification problem. Comprehensive experimental results on our compiled fogged aerial images quality data set have clearly demonstrated the effectiveness of our proposed algorithm.     

White and narrow band image compressor based on a new color space for capsule endoscopy

In this paper, we present the design of a low power and hardware efficient image compressor integrated circuit for wireless capsule endoscopy application. The proposed compression algorithm supports dual-band imaging, that is, works on both white-band imaging (WBI) and narrow-band imaging (NBI). The scheme uses a novel color-space and simple predictive coding for optimized performance. Based on the nature of the narrow- and white-band endoscopic images and video sequences, several sub-sampling schemes are introduced. The proposed dual-band compressor is designed in such as way that it can easily be interfaced with any commercial low power image sensor that outputs RGB image pixels in a raster scan fashion, eliminating the need of large buffer memory and temporary storage. Both NBI and WBI reconstructed images have been verified by medical doctors for acceptability. Compared to other designs targeted to video capsule endoscopy, the proposed algorithm performs strongly with a compression ratio of 80.4% (for WBI) and 79.2% (for NBI), and a high reconstruction peak-signal-to-noise-ratio (over 43.7 dB for both bands). The results of the fabricated chip are also presented.     

采用非局部均值的连续太赫兹图像去噪处理

太赫兹辐射能够穿透大多数对可见光和近红外光不透明的物质。提高成像质量是成像系统的关键,尤其对探测器性能较低的面阵成像更为重要。通过数字图像处理方法改善成像质量是一条重要的解决途径。应用非局部均值(NLM)分别对真实的透射扫描、反射扫描和透射面阵、反射面阵的太赫兹图像进行了去噪处理,选取不同的控制参数进行了对比分析,同时对比了均值滤波处理结果。实验结果表明:非局部均值能够较好地去除连续太赫兹图像噪声、提高成像质量,对噪声严重的面阵成像去噪效果最明显。非局部均值去噪并保持边缘能力明显好于均值滤波。     

彩色大面阵数字航空遥感相机技术的研究

提出了一种以彩色大面阵CCD探测器作为成像介质的大视场数字航空摄影相机设计技术。采用对称Russar型光学系统,在获得了大视场角的同时最大程度的降低了光学畸变;设计了精确的微位移传动系统移动CCD探测器以补偿前向像移,提高了相机的动态分辨率;设计了一种双叶片的中心式机械快门,获得了宽范围的曝光时间控制,保证了探测器的均匀曝光及合适的图像重叠率。地面及空中成像测试中相机的静态分辨率达到了CCD特征频率的要求,获得了清晰的航拍彩色图像,表明相机的各项技术性能满足要求,该相机技术已应用到国土资源的遥感普查中。     

Exploiting structure in fast aerial image computation forintegrated circuit patterns

Modeling aerial images has recently become a crucial component of semiconductor manufacturing. As all steppers employ partially coherent illumination, such modeling has been computationally intensive for all but elementary patterns. In this paper we describe a fast computational method for calculating aerial images of integrated circuit masks produced by a partially coherent optical projection system. The method described relies on two tools to realize fast computation: (1) coherent decompositions of partially coherent imaging system models as proposed by Pati and Kailath (1994), and (2) the use of “basis” (or building block) images that are well-suited to describe integrated circuit patterns. Examples are presented in which aerial images are computed for large mask areas. The proposed method represents a speed improvement of several orders of magnitude over a more traditional, and more general, approach (SPLAT from the University of California, Berkeley)     

High dynamic range imaging with short- and long-exposures based on artificial remapping using multiscale exposure fusion

High dynamic range imaging (HDRI) is an excellent high-quality image acquisition technique, which can reflect real human visual characteristics from one (or several) captured low dynamic range (LDR) image. However, the input LDR image only provides partial information of the scene. Besides, in traditional HDRI methods that require multiple captured images as input, field of view errors can be induced, which will be difficult to apply it to the emerging image acquisition systems. Here, we propose a novel HDRI method that reconstructs an HDR image from only a pair of short- and long-exposure images based on artificial remapping using multi-scale exposure fusion. Firstly, we introduce a simulated exposure model called artificial remapping to synthesize a multi-exposure image sequence from the input LDR image pairs. Then, weighting maps of the sequence for fusion can be obtained according to the evaluation factors of contrast, saturation, as well as improved exposedness. Finally, we utilize the pyramid based multiscale exposure fusion framework to integrate them into an enhanced HDR image. Comparative experiments, fully implemented on some source images, have been demonstrated that better performance can be realized compared with some competing methods in qualitative and quantitative evaluation. Note that the operation of the proposed method is simple yet effective, which is easy to popularize. The method thus can be potentially applied to the emerging image acquisition systems where two images are captured simultaneously by two image sensors or by one image sensor with a pair of short- and long-exposure setting.     

图像复原基本适用条件的红外成像实验研究

图像复原是提高图像空间分辨率的经典方,首先建立一般的成像模型,通过对图像复原原理进行分析,得出了利用图像复原提高图像空间分辨率的基本适用条件,通过扫描成像实验结果分析,验证了利用图像复原提高图像空间分辨率的基本适用条件的理论分析的正确性,图像复原提高图像空间分辨率基本适用条件的研究,对于遥感成像系统,可以保证获取的图像质量不下降的同时,大大节省系统研制成本。     

基于Creator和Vega的红外/SAR成像仿真

在此使用Creator软件建立了带纹理的目标三维模型,以及利用Vega的TMM和MAT工具分别对目标纹理和大气环境进行了建模。基于Vega及其扩展模块远红外传感器仿真模块对红外图像进行了仿真;基于Vega及其扩展模块雷达仿真模块对SAR成像进行了仿真。针对同一场景、同一目标的红外/SAR图像融合过程中存在的图像获取问题,提出一种对同一探测目标的半真实半仿真图像获取方法;使用传感器视效模拟模块进行同一时刻、场景和大气条件下的SAR图像和红外图像仿真。使用Cretor和Vega软件生成红外/SAR图像具有周期短、实时性高的特点,可以很好地解决红外/SAR图像获取难的问题,在军事与民用领域中均有广泛的应用。     

基于卷积神经网络的反无人机系统图像识别方法

针对无人机的无证飞行和随意飞行严重影响和威胁公共安全的问题,提出了反无人机系统。识别无人机是反无人机系统实现的关键之一,为此提出了一种基于卷积神经网络的图像识别无人机方法。运用自制光学系统采集设备采集了不同型号的无人机图片以及鸟类图片,设计了针对无人机小样本识别的卷积神经网络和支持向量机。运用设计的卷积神经网络分别对MNIST数据集、无人机图片以及鸟的图片进行了识别,同时也运用支持向量机识别无人机和鸟的图片,进行了对比实验。实验结果表明,设计的卷积神经网络在MNIST数据集上识别准确率为91.3%,识别无人机准确率为95.9%,支持向量机识别准确率为88.4%。对比实验表明,提出的方法可以识别无人机和鸟以及不同类型的无人机并且识别结果优于支持向量机,可用于反无人机系统识别无人机,给同类研究提供了借鉴。     

基于灰度投影法运动估计的成像CCD平移补偿法

为了提高成像质量,得到高分辨率的图像。提出了一种基于灰度投影法运动估计的成像CCD平移补偿法,并给出其系统结构图。然后验证了分辨率标板在各种运动情况下该系统的补偿效果,并给出了评价结果分析,最后拍摄了实物并给出了恢复后的图像及评价。结果:该补偿法可以有效地恢复图像,对慢速运动图像和随机振动图像具有较高的恢复能力。结论:使得系统的整体性能得到了很大的提升,成像的分辨率也大大提升。     

一种适合于目标检测的图像分割方法

在航空图像的目标检测过程中，首先需要把图像中的每个目标都单独地分离开。一般的图像分割方法是把图像分成几大类，同一类目标组成一个个区域。这种分割结果给目标检测造成了很大的困难。本文首先采用最小值滤波对图像进行预处理，尽量地扩大目标之间的间隙。然后用降低分辨率的方法得到初始的分割图像，并用分裂合并法修正分割结果。计算结果显示，分割结果中不同的目标尽管距离很近，也能较好地分离。这个结果对于目标检测有着重要的意义。     

基于暗通道先验原理的偏振图像去雾增强算法研究

在装备试验与测试中,常规光学成像系统极易受气象环境(如雾霾、沙尘等)影响,导致探测距离、成像效果、测量精度等受到大幅限制,从而严重影响目标成像效果及关键参数获取。如何增强雾霾条件下光学探测识别能力及成像质量,成为了当前急需解决的关键问题。本文利用偏振成像优势,结合暗通道先验原理,提出了基于暗通道先验原理的偏振图像去雾增强算法。该算法首先利用采集到的偏振图像提取偏振特征,计算偏振度和偏振角;同时,采用基于区域增长算法自动提取出天空区域,对天空区域进行大气光参数估计,获取大气光偏振度及偏振角相关参数估计;然后,结合暗通道先验原理,获取无穷远处大气光强,进而计算各像素点的大气光强;最后,建立在大气物理退化模型基础上,实现图像去雾增强。实例分析与验证中,通过主观评价与客观评价两种方法,对比本文提出的方法和常见其他方法,实际结果表明,本文算法去雾增强能力较强,能有效提升光学系统的探测识别能力及成像质量,对雾霾条件下武器装备关键参数获取具有重要意义。