YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

Experimental study on the propagation characteristics of hydrogen/methane/air premixed flames in a narrow channel

This work is focused on the explosion characteristics of premixed gas containing different volume fractions of hydrogen in a narrow channel (1000 mm × 50 mm × 10 mm) under the circumstance of stoichiometric ratio. The ignition positions were set in the closed end and the middle of the pipeline respectively. The results showed that when the gas was ignited at the pipeline closed end, the propagating flame was tulip structure for different premixed gas. When the hydrogen volume fraction was less than 40%, the flame propagation speed increased significantly with the rise of hydrogen volume fraction, and the overpressure peak also appeared obviously in advance. However, when the volume fraction of hydrogen was more than 40%, the increase of flame propagation speed and the overpressure peak occurrence time varied slightly. Furthermore, when the ignition position was placed in the middle of the pipeline, the flame propagation speed propagating to the opening end was much faster than that propagating to the closing end, and there was no tulip shape when the flame propagates to the opening end. The flame propagating to the closed end appeared tulip shape under the influence of airflow, and high-frequency flame oscillation occurred during the propagation. This work shows that the hydrogen volume fraction and ignition position significantly affected the flame structure, flame front speed, and explosion overpressure.     

A comprehensive survey on computer vision based concepts,methodologies, analysis and applications for automatic gun/knife detection

The ability to detect gun and gun held in hand or other body parts is a typical human skill. The same problem presents an imperative task for computer vision system. Automatic observer independent detection of hand held gun or gun held in the other body part, whether it is visible or concealed, provides enhance security in vulnerable places and initiates appropriate action there. Compare to the automatic object detection systems, automatic detection of gun has very few successful attempts. In the present scope of this paper, we present an extensive survey on automatic detection of gun and define a taxonomy for this particular detection system. We also describe the inherent difficulties related with this problem. In this survey of published papers, we examine different approaches used in state-of-the-art attempts and compare performances of these approaches. Finally, this paper concludes pointing to the possible research gaps in related fields.     

Organic mesh template-based laminated object manufacturing to fabricate ceramics with regular micron scaled pore structures

A new aqueous slurry-based laminated object manufacturing process for porous ceramics is proposed: firstly, an organic mesh sheet is pre-paved as a pore-forming template before slurry layer scraping; secondly, the 2D pattern is built with laser outline cutting of the dried mesh–ceramic composite layer; finally, the pore structure is formed after degreasing and sintering. Alumina parts with porosities of 51.5 %, round hole diameters of 80 ± 5 μm were fabricated using 70 wt. % solid content slurry and 100 mesh nylon net. Using an organic mesh as the framework and template not only reduces the risk of damage of the green body but also ensures the regularity, uniformity and connectivity of the micron scaled pore network. The layer-by-layer drying method avoids the delamination phenomenon and improves the paving density. The new method can realize the flexible design of the pore structure by using various organic mesh templates.     

A novel intelligent approach for yaw position forecasting in wind energy systems

Yaw control systems orientate the rotor of a wind turbine into the wind direction, optimize the wind power generated by wind turbines and alleviate the mechanical stresses on a wind turbine. Regarding the advantages of yaw control systems, a k-nearest neighbor classifier (k-NN) has been developed in order to forecast the yaw position parameter at 10-min intervals in this study. Air temperature, atmosphere pressure, wind direction, wind speed, rotor speed and wind power parameters are used in 2, 3, 4, 5 and 6-dimensional input spaces. The forecasting model using Manhattan distance metric for k = 3 uncovered the most accurate performance for atmosphere pressure, wind direction, wind speed and rotor speed inputs. However, the forecasting model using Euclidean distance metric for k = 1 brought out the most inconsistent results for atmosphere pressure and wind speed inputs. As a result of multi-tupled analyses, many feasible inferences were achieved for yaw position control systems. In addition, the yaw position forecasting model developed was compared with the persistence model and it surpassed the persistence model significantly in terms of the improvement percent.     

Stream-Based Data Sampling Mechanism for Process Object

Process object is the instance of process. Vertexes and edges are in the graph of process object. There are different types of the object itself and the associations between object. For the large-scale data, there are many changes reflected. Recently, how to find appropriate real-time data for process object becomes a hot research topic. Data sampling is a kind of finding c hanges o f p rocess o bjects. There i s r equirements f or s ampling to be adaptive to underlying distribution of data stream. In this paper, we have proposed a adaptive data sampling mechanism to find a ppropriate d ata t o m odeling. F irst o f all, we use concept drift to make the partition of the life cycle of process object. Then, entity community detection is proposed to find changes. Finally, we propose stream-based real-time optimization of data sampling. Contributions of this paper are concept drift, community detection, and stream-based real-time computing. Experiments show the effectiveness and feasibility of our proposed adaptive data sampling mechanism for process object.     

应用膨胀算法提取目标的直接定位算法

为了解决被动雷达系统中的多发射源定位问题，提出了一种基于多重信号分类(MUSIC)算法和图像膨胀(IE)算法的直接定位方法。该方法结合了谱分析中的MUSIC思想，通过对接收量测协方差矩阵进行特征分析求解目标的位置。首先，在目标个数未知的前提下，利用Akaike信息准则(AIC)来确定模型阶数；然后，推导了基于MUSIC的定位代价函数；之后，利用图像膨胀算法处理得到的代价函数平面；最后，膨胀处理后的输出为目标个数及目标位置的估计值。提出的算法有效地解决了目标检测及提取的问题，能够确定多个目标的位置坐标，为后续的定位性能分析提供可能性，也保证了算法的完整性。进一步地分析了多个临近目标情况下影响目标提取性能的主要因素。     

深度学习识别光网络单元故障的设计与应用

为解决依赖装维上门鉴别光网络单元故障带来的不便,可以从机器视觉入手实现自动化故障识别。近年,ImageNet挑战赛的成功推动了物体识别技术的跨越式发展,特别是基于卷积的深度学习技术在视觉识别方面已经达到人类水平,为光网络单元故障的自动识别提供了技术基础。文章对识别光网络单元的工作状态进行了研究,将设备工作状态分为7个场景,提出了利用手机APP采集图片识别故障的解决方案并投入了实际生产;重点阐述了深度学习模块的设计与实现,提出一种通过算法整合的方式综合运用物体检测和图像分类算法,分3阶段逐步求精,解决了图片过滤,光网络单元型号和状态识别等问题,实现了基于计算机视觉自动识别光网络单元故障。从数据上看产品的端到端准确率超过84%,识别速度达到10 FPS,月均提供服务超过1万人次,在减少用户等待的同时节约了人力资源。     

网络安全等级保护测评中测评结论的度量方法优化

文章分析了网络安全等级保护2.0时期国家标准的新变化对等级测评结论可能产生的影响,并用实际案例和数据论述了以往描述的基于测评指标和基于测评对象的定量分析方法存在的局限性。根据网络安全等级保护国家标准结构和内容的新特点,结合新的等级测评结论表述方法,文章提出了调整和优化定量计算产生等级测评结论的思路,给出了缺陷扣分的原理和缺陷扣分的定量计算方法,并比较了各种定量计算方法在计算结果上的差异,提出了适合新标准的测评结论定量计算公式。