Efficient graph attentional network for 3D object detection from Frustum-based LiDAR point clouds

LiDAR-based 3D object detection is important for autonomous driving scene perception, but point clouds produced by LiDAR are irregular and unstructured in nature, and cannot be adopted by the conventional Convolutional Neural Networks (CNN). Recently, Graph Convolutional Networks (GCN) has been proved as an ideal way to handle non-Euclidean structure data, as well as for point cloud processing. However, GCN involves massive computation for searching adjacent nodes, and the heavy computational cost limits its applications in processing large-scale LiDAR point cloud in autonomous driving. In this work, we adopt a frustum-based point cloud-image fusion scheme to reduce the amount of LiDAR point clouds, thus making the GCN-based large-scale LiDAR point clouds feature learning feasible. On this basis, we propose an efficient graph attentional network to accomplish the goal of 3D object detection in autonomous driving, which can learn features from raw LiDAR point cloud directly without any conversions. We evaluate the model on the public KITTI benchmark dataset, the 3D detection mAP is 63.72% on KITTI Cars, Pedestrian and Cyclists, and the inference speed achieves 7.9 fps on a single GPU, which is faster than other methods of the same type.     

Motion detection in moving camera videos using background modeling and FlowNet

Real-time moving object detection is challenging for moving cameras due to the moving background. Many studies use homography matrix to compensate for global motion by warping the background model to the current frame. Then, the pixel difference between the current frame and the background model is used for background subtraction. Moving pixels are extracted by applying adaptive threshold and some post-processing techniques. On the other hand, deep learning-based dense optical flow can be efficient enough to extract the moving pixels, but it increases computational cost. This study proposes a method to enhance a classical background modeling method with deep learning-based dense optical flow. The main contribution of this paper is to propose a fusing algorithm for dense optical flow and background modeling approach. The background modeling methods are error-prone, especially with continuous camera movement, while the optical flow method alone may not always be efficient. Our hybrid method fuses both techniques to improve the detection accuracy. We propose a software architecture to run background modeling and dense optical flow methods in parallel processes. The proposed implementation approach significantly increases the method’s working speed, while the proposed fusion and combining strategy improve detection results. The experimental results show that the proposed method can run at high speed and has satisfying performance against the methods in the literature.     

Effective electromagnetic and chiral parameters of chiral composite material

The effective parameters of chiral composite are studied using a simple model, that is, randomly oriented non-interacting wire helices embedded in a nonchiral host medium. It is found that both the effective permittivity and permeability are independent on the handedness of the chiral objects while the effective chirality admittance is dependent. It is also found that when the ratio of the radius of the chiral helix to its pitch is about 0.23, maximum chirality admittance is achieved. The effective parameters of equichiral sample are also discussed.     

Bistatic scattering by arbitrarily shaped objects with rough surface at optical and infrared frequencies

The scattering cross sections for arbitrarily shaped dielectric objects with rough surface are determined for optical and infrared frequencies using the Kirchhoff approximation. The formula of the coherent scattering cross section is derived, and numerical method of incoherent scattering cross section is given. As a specific example, the infrared laser scattering cross sections of rough spheres are calculated at 1.06 m.     

基于极坐标中蛇模型的类圆目标轮廓提取技术研究

提出了转化到极坐标中的蛇模型.通过把蛇模型转化到极坐标中,使轮廓的候选点得以更有序的排列.由于采用了动态规划法并在整个能量空间中搜索能量泛函的极值,算法对能量泛函的局部极值有较强的鲁棒性.所提出的模型不需要确定初始轮廓,可以用非迭代方法直接求解.与传统的动态规划法和贪婪算法进行了比较实验.结果表明,所提出的算法对极坐标中极点的位置不是很敏感.     

目标基视频编码中的运动目标提取与跟踪新算法

自动、快速的视频目标提取与跟踪是目标基视频编码中的一项关键技术.本文提出一种运动目标提取与跟踪新算法.首先,根据多帧运动信息和高阶统计检测方法得到二值运动掩模图像,然后提出一种改进分水岭算法对运动区域及其周围部分进行分割.将二者所得结果进行投影运算,得到最终运动目标.最后提出一种运动目标跟踪新算法,能对目标进行有效的跟踪.实验结果说明了本文算法的有效性.     

FTO客体3m闪光照相的Monte Carlo研究

 研究了客体模型FTO的闪光照相系统X光输运过程，给出了直穿照射量、散射照射量、直散比、直穿照射量能谱、散射照射量能谱、直穿X光通量能谱和散射X光通量能谱在记录平面的空间分布。结果表明：后锥是照射量散射成分的主要来源，后锥照射量占总散射量97%；后锥也是造成散射的空间分布不均匀的主要器件，这一不均匀性高达58%。照相系统的最小直散比非常小，表明锥造成的散射已经严重地淹没了直穿（轫致辐射）信号。计算中使用高空间分辨率记录法进行分点，合成图像对吸收系数的复原结果与国外报道的结果相符。     

Unsupervised cell identification on multidimensional X‐ray fluorescence datasets

A novel approach to locate, identify and refine positions and whole areas of cell structures based on elemental contents measured by X‐ray fluorescence microscopy is introduced. It is shown that, by initializing with only a handful of prototypical cell regions, this approach can obtain consistent identification of whole cells, even when cells are overlapping, without training by explicit annotation. It is robust both to different measurements on the same sample and to different initializations. This effort provides a versatile framework to identify targeted cellular structures from datasets too complex for manual analysis, like most X‐ray fluorescence microscopy data. Possible future extensions are also discussed.     

Robust techniques for abandoned and removed object detection based on Markov random field

This paper presents a novel framework for detecting abandoned objects by introducing a fully-automatic GrabCut object segmentation. GrabCut seed initialization is treated as a background (BG) modelling problem that focuses only on unhanded objects and objects that become immobile. The BG distribution is constructed with dual Gaussian mixtures that are comprised of high and low learning rate models. We propose a primitive BG model-based removed object validation and Haar feature-based cascade classifier for still-people detection once a candidate for a released object has been detected. Our system can obtain more robust and accurate results for real environments based on evaluations of realistic scenes from CAVIAR, PETS2006, CDnet 2014, and our own datasets.