Stereoscopic Camera-Sensor Model for the Development of Highly Automated Driving Functions within a Virtual Test Environment

The need for efficient and reproducible development processes for sensor and perception systems is growing with their increased use in modern vehicles. Such processes can be achieved by using virtual test environments and virtual sensor models. In the context of this, the present paper documents the development of a sensor model for depth estimation of virtual three-dimensional scenarios. For this purpose, the geometric and algorithmic principles of stereoscopic camera systems are recreated in a virtual form. The model is implemented as a subroutine in the Epic Games Unreal Engine, which is one of the most common Game Engines. Its architecture consists of several independent procedures that enable a local depth estimation, but also a reconstruction of a whole three-dimensional scenery. In addition, a separate programme for calibrating the model is presented. In addition to the basic principles, the architecture and the implementation, this work also documents the evaluation of the model created. It is shown that the model meets specifically defined requirements for real-time capability and the accuracy of the evaluation. Thus, it is suitable for the virtual testing of common algorithms and highly automated driving functions.

Integration of Lab model and EHOG for human appearance matching across disjoint camera views

The integration of the Lab model with the extended histogram of oriented gradients （EHOG） is proposed to improve the accuracy of human appearance matching across disjoint camera views under perturbations such as illumination changes and different viewing angles. For the Lab model that describes the global information of observations, a sorted nearest neighbor clustering method is proposed for color clustering and then a partitioned color matching method is used to calculate the color similarity between observations. The Bhattacharya distance is employed for the textural similarity calculation of the EHOG which describes the local information. The global information, which is robust to different viewing angles and scale changes, describes the observations well. Meanwhile, the use of local information, which is robust to illumination changes, can strengthen the discriminative ability of the method. The integration of global and local information improves the accuracy and robustness of the proposed matching approach. Experiments are carried out indoors, and the results show a high matching accuracy of the proposed method.

Estimation of Fractional Vegetation Cover Based on Digital Camera Survey Data and a Remote Sensing Model

The objective of this paper is to improve the monitoring speed and precision of fractional vegetation cover (fc). It mainly focuses on fc estimation when fcmax and fcmin are not approximately equal to 100% and 0%, respectively due to using remote sensing image with medium or low spatial resolution. Meanwhile, we present a new method of fc estimation based on a random set of fc maximum and minimum values from digital camera (DC) survey data and a di- midiate pixel model. The results show that this is a convenient, efficient and accurate method for fc monitoring, with the maximum error -0.172 and correlation coefficient of 0.974 between DC survey data and the estimated value of the remote sensing model. The remaining DC survey data can be used as verification data for the precision of the fc estimation. In general, the estimation of fc based on DC survey data and a remote sensing model is a brand-new development trend and deserves further extensive utilization.

Survey of 3D modeling using depth cameras

Three-dimensional(3D)modeling is an important topic in computer graphics and computer vision.In recent years,the introduction of consumer-grade depth cameras has resulted in profound advances in 3D modeling.Starting with the basic data structure,this survey reviews the latest developments of 3D modeling based on depth cameras,including research works on camera tracking,3D object and scene reconstruction,and high-quality texture reconstruction.We also discuss the future work and possible solutions for 3D modeling based on the depth camera.

Modeling Camera Image Formation Using a Feedforward Neural Network

One fundamental problem in computer vision and image processing is modeling the image formation of a camera, i.e., mapping a point in three-dimensional space to its projected position on the camera’s image plane. If the relationship between the space and the image plane is assumed to be linear, the relationship can be expressed in terms of a transfor-mation matrix and the matrix is often identified by regression. In this paper, we show that the space-to-image relation-ship in a camera can be modeled by a simple neural network. Unlike most other cases employing neural networks, the structure of the network is optimized so as for each link between neurons to have a physical meaning. This makes it possible to effectively initialize link weights and quickly train the network.

3D Model Construction and Ecological Environment Investigation on a Regional Scale Using UAV Remote Sensing

The acquisition of digital regional-scale information and ecological environmental data has high requirements for structural texture,spatial res-olution,and multiple parameter categories,which is challenging to achieve using satellite remote sensing.Considering the convenient,facilitative,and flexible characteristics of UAV(unmanned air vehicle)remote sensing tech-nology,this study selects a campus as a typical research area and uses the Pegasus D2000 equipped with a D-MSPC2000 multi-spectral camera and a CAM3000 aerial camera to acquire oblique images and multi-spectral data.Using professional software,including Context Capture,ENVI,and ArcGIS,a 3D(three-dimensional)campus model,a digital orthophoto map,and multi-spectral remote sensing map drawing are realized,and the geometric accuracy of typical feature selection is evaluated.Based on a quantitative remote sensing model,the campus ecological environment assessment is performed from the perspectives of vegetation and water body.The results presented in this study could be of great significance to the scientific management and sustainable development of regional natural resources.

面向车载相机采集图像的智能汽车测试场景关键性量化模型

车载相机图像是构建智能汽车测试场景库的主要数据来源,但其中关键测试场景发生概率低,大部分场景的测试价值小,若将其直接应用于智能汽车测试会浪费大量测试资源。本文提出一种面向车载相机采集图像的智能汽车测试场景关键性量化模型。首先,基于实车相机参数对实车采集的图像进行处理,输出对行车安全具有影响的参数;其次,基于风险场理论将参数整合,输出测试场景关键性量化结果;最后,对实车采集的图像进行测试场景关键性量化验证,结果表明本文模型可以精确输出测试场景关键性的具体数值,进而对比不同场景的测试价值,证明本文提出的模型可以有效筛选智能汽车关键测试场景。

随机噪声平板下光学复眼内外参联合标定

光学复眼在无人系统的精确定位制导、避障导航等任务中得到了越来越广泛的应用,其中光学复眼的高精度标定是保障上述任务质量的前提。通常经典的张氏棋盘格标定法要求光学复眼的每个子眼都必须观测到完整的棋盘格,然而,由于光学复眼结构的复杂性,在实际标定过程中难以满足这一要求。为解决张氏标定法的局限性,该文提出一种基于随机噪声平板的光学复眼内外参联合标定算法,该算法通过子眼拍摄随机噪声平板的局部信息,可简单快速地实现任意构型和子眼数量的光学复眼内外参联合标定。为了提高光学复眼标定的稳定性,设置多阈值匹配机制解决子眼视场特征点数量稀疏导致图像匹配失效的问题。同时,给出了光学复眼内外参联合标定的误差模型,用来衡量所提出算法的精确度。在与张氏棋盘格标定法进行实验对比中,验证所提算法的稳定性和鲁棒性,并在光学复眼实物系统中,验证了所提联合标定算法具有较高的精度。

车载视觉环视系统实验平台

为了帮助驾驶员更好地感知盲区和障碍物,提升驾驶的安全性与便捷性,提出了一种车载视觉环视系统实验平台。利用安装在车辆前、后、左、右的多台鱼眼相机实时采集车辆周边视频数据,生成以车辆为参考中心的环视鸟瞰图,为驾驶员提供360°无死角的环境视觉信息。最后,通过实物实验验证了所提方法的有效性。

基于XGBoost算法的人—虎共存区域风险等级划分

以2014—2019年珲春地区红外相机拍摄的东北虎数据为基础,基于XGBoost算法构建了虎出没区域风险等级划分模型。由模型检验可知:模型的准确率为93.51%,精确率为93.85%,召回率为93.08%,F1值为93.31%,Cohen s Kappa统计系数为90.2%。研究结果表明:基于XGBoost算法构建的人-虎共存区域风险等级划分模型分类效果好、预测准确度高,运用该模型对人-虎共存区域进行风险等级划分是可行的。

三维场景下高速公路事件检测摄像机布设探讨

由于智慧高速上交通事件检测设施的布设较传统做法更密集,其布设需考虑高速公路的平纵线形、公路沿线布设的交通标志牌、上跨桥等对检测摄像机监控范围的影响。通过建立反映高速公路设计和其沿线设施布置的三维模型和摄像机在三维空间中的有效监控范围模型,在三维场景下分析交通事件视频检测摄像机的布设问题,以期为设计提供指导。

亚热带森林小麂的空间分布及活动节律的区域性差异

小麂(Muntiacus reevesi)是偶蹄目鹿科麂属动物,在我国种群数量丰富,分布广泛,但关于小麂在不同区域的空间分布及活动节律的差异性研究相对较少。为掌握小麂的活动节律及其影响因素,2018年3月至2019年2月利用红外相机技术对江西省桃红岭梅花鹿国家级自然保护区、九岭山国家级自然保护区和齐云山国家级自然保护区的小麂进行了监测,每个保护区的红外相机数量均为60台,相机工作日分别为9692、9659、14582 d,小麂的独立有效照片数分别为603、665、1032张,并运用单季节占域模型估算了各地区小麂的占域率和探测率,分析了海拔、坡度、植被覆盖度以及距水源地距离等环境变量对小麂活动规律以及分布范围的影响。结果表明,桃红岭保护区和九岭山保护区的小麂偏好于海拔较低、坡度较小、植被指数较低、距水源地距离较近的区域;齐云山保护区的小麂偏好于海拔较高、坡度较大、植被指数较高、距水源地距离较近的区域。小麂为明显的晨昏性动物,日活动高峰出现在06:00—08:00和17:00—19:00。其日活动节律在齐云山存在显著季节差异,桃红岭保护区和九岭山保护区则无显著季节差异,各保护区之间的年活动节律不存在显著差异。该研究结果有助于进一步了解小麂的活动节律模式及其季节性变化,进一步了解小麂在自然状态下的生态习性,为这一物种的保护和管理提供数据支撑。

Human tracking in camera network with non-overlapping FOVs

An adaptive human tracking method across spatially separated surveillance cameras with non-overlapping fields of views （FOVs） is proposed. The method relies on the two cues of the human appearance model and spatio-temporal information between cameras. For the human appearance model, an HSV color histogram is extracted from different human body parts （head, torso, and legs）, then a weighted algorithm is used to compute the similarity distance of two people. Finally, a similarity sorting algorithm with two thresholds is exploited to find the correspondence. The spatio- temporal information is established in the learning phase and is updated incrementally according to the latest correspondence. The experimental results prove that the proposed human tracking method is effective without requiring camera calibration and it becomes more accurate over time as new observations are accumulated.

唐家河国家级自然保护区同域分布六种偶蹄类动物的活动节律与空间利用

了解群落中具有相似生态位的同域分布物种的时空分布是群落生态学研究的主要内容之一。本研究于2021年1—12月在四川唐家河国家级自然保护区境内应用红外相机技术进行大中型哺乳动物的监测,共布设红外相机82台,总相机工作日为18710 d。采用核密度估计法(Kernel density estimation)和占域模型(Occupancy model)分析冷季和暖季该保护区内6种偶蹄类的时空分布。研究结果表明:(1)毛冠鹿(Elaphodus cephalophus)和小麂(Muntiacus reevesi)在冷季和暖季的日活动节律高度重叠(△≥0.80),中华扭角羚(Budorcas tibetana)、中华斑羚(Naemorhedus griseus)、中华鬣羚(Capricornis milneedwardsii)和野猪(Sus scrofa)为中度重叠(△值为0.50~0.80);(2)毛冠鹿、小麂、中华扭角羚、中华斑羚和野猪的日活动模式均为双峰型,且都具有晨昏习性,中华鬣羚偏夜行性,日活动模式为多峰型;(3)在冷季,中华扭角羚的占域率最高(0.70),在暖季,中华斑羚的占域率最高(0.96),中华鬣羚在冷季和暖季的占域率均最低,分别是0.18和0.19;(4)海拔、坡度、坡向、距水源地距离及距道路距离是影响这6种偶蹄类空间分布的重要因子。研究显示,唐家河国家级自然保护区内6种偶蹄类动物的活动节律与空间利用在冷季和暖季具有一定的差异性。本研究结果初步揭示了不同季节偶蹄类动物的时空分布特征及影响因素,为今后该区域制定针对性的保护管理措施提供科学依据。

大视场相机最优投影模型识别及星光标定方法

针对在轨摄影测量中近距离大尺寸测量需求,提出利用星光约束的大视场角摄影测量相机最优投影模型识别及标定方法。首先,构建了具备调节系数的星光几何投影分段函数模型。随后,针对分段星光投影模型开发多站位自标定光束平差算法。通过将光束平差算法与北方苍鹰寻优策略相结合,对投影模型调节系数、相机内方位参数、相机外方位参数及镜头畸变系数同步优化,直到星点像面重投影均方根误差达到全局最小,得到最优投影模型及其参数。实测实验表明,大视场角相机星光标定后,星点像面坐标的重投影均方根误差为1/9 pixel。在连续帧星光标定实验中,通过卡尔曼滤波算法对相机参数随机误差进行了有效消除。该方法可在相机星光标定过程中识别最优投影模型并标定全部成像参数,具备连续帧标定及参数校准能力。

一种大视场红外相机的畸变校正方法

本文针对大视场红外相机的畸变校正过程复杂的问题,提出了一种新的畸变校正方法。首先,选择单参数除法模型(division model,DM)作为相机畸变模型,使用改进的加速特征稳健算法(speed-up robust features,SURF)自动获取两幅有相同场景的畸变红外图像的特征点对,然后利用九点非迭代算法和核密度估计方法获取图像的畸变参数,最后根据求得的畸变参数使用基于边缘保持的灰度插值方法对图像进行畸变校正。在整个过程中,不需要预先知道相机的参数和场景信息,通过输入两幅具有相同场景的图像,完成畸变校正,为大视场红外相机的畸变校正提供了一种新的解决方法。实验结果表明,使用该方法对大视场红外相机进行畸变校正具有可行性和鲁棒性。

基于无人机航拍的苎麻倒伏信息解译研究

茎杆倒伏是苎麻三麻培育中最常见的灾害,传统的监测方法具有耗时耗力、不及时等局限性。提出了一种基于无人机航拍获取苎麻倒伏信息的方法,首先利用Pix4D Mapper软件生成苎麻的冠层正射影像和数字表面模型(digital surface model,DSM),基于正射影像提取苎麻光谱、纹理及形状特征,基于DSM提取苎麻株高指标,最后结合3种机器学习算法构建正常/倒伏苎麻分类模型。结果表明,基于DSM提取的株高信息可以有效代替大田实测株高,模型R2为0.899。倒伏和正常苎麻在光谱、纹理、形状及株高特征上具有差异。在3种机器学习算法中,支持向量机和决策树模型的性能最好,准确率达到99%,能够高效地识别苎麻倒伏地块。以上研究结果为准确、快速评估作物倒伏情况提供了技术支撑。

机器人与双目相机的手眼标定方法

为了得到钻头在激光熔覆机器人坐标系下的模型数据需要机器人与双目相机进行手眼标定,针对这一问题提出了一种手眼标定的方法。改变机器人位姿对同一点进行测量,建立机器人DH模型并利用机器人正运动学方程计算出机器人末端坐标系与双目相机坐标系之间的变换矩阵,完成了手眼测量系统标定。基于此标定方法进行了误差测试与激光熔覆实验,对误差产生的原因进行分析并提出了减小误差的方法。实验结果表明,机器人与双目相机的手眼标定方法有效,可用于PDC钻头激光熔覆系统。

一种街景图像中建筑物高度估算方法

建筑物高度信息是城市三维建模的基础数据,但已有的建筑物高度估算研究多采用LiDAR和SAR等遥感影像。随着计算机和互联网的快速发展,街景数据因采集容易和成本低等特点成为了一种新兴的建筑物高度估算数据源。文章提出一种街景图像中建筑物高度估算方法,首先利用segment anything model实现图像中建筑物像素高度提取;然后利用图像元数据和电子地图数据获取建筑物与相机之间的距离、图像焦距,根据街景图像与建筑物实体的几何关系改进针孔相机模型,构建建筑物高度估算方法;最后选取北京、柏林的Mapillary街景图像开展实验验证。结果表明,与改进前相比,改进后针孔相机模型明显提升了高度估算准确度,RMSE降低了11.31 m,R^(2)提高了0.4,具备实用价值。

基于高斯增强模块的相机模型辨别

在多媒体取证中,高通滤波器是卷积神经网络常用的预处理层之一,用于抑制图像内容的影响,只强调高频特征。但与此同时,其他一些包含取证痕迹的有用信息也将被不加区别地剔除。为了解决这一问题,文中提出了一个简单而高效的高斯增强模块(Gaussian Enhancement Module,GEM)来提取“扩展的”高频特征,即在维持原有特征强度的基础上增强高频细节信息。GEM由两个连续的一维低通高斯滤波器组成,以获得一个模糊版本的特征图,并进一步得到相应的扩展高频残差。通过以高频残差作为空间掩膜,它可以自适应地强化脆弱和细微的低级取证特征,并防止在特征传递过程中出现衰减现象。在相机模型辨别数据集上进行实验,通过将该模块插入多个主流骨干网络,GEM仅仅带来非常轻微的模型复杂度的增加,网络性能和鲁棒性却显著提高,表明该模块支持“即插即用”,与特定的网络架构无关。