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.     

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 hybrid homogeneously weighted moving average control chart for process monitoring

Several modifications and enhancements to control charts in increasing the performance of small and moderate process shifts have been introduced in the quality control charting techniques. In this paper, a new hybrid control chart for monitoring process location is proposed by combining two homogeneously weighted moving average (HWMA) control charts. The hybrid homogeneously weighted moving average (HHWMA) statistic is derived using two smoothing constants λ₁ and λ₂ . The average run length (ARL) and the standard deviation of the run length (SDRL) values of the HHWMA control chart are obtained and compared with some existing control charts for monitoring small and moderate shifts in the process location. The results of study show that the HHWMA control chart outperforms the existing control charts in many situations. The application of the HHWMA chart is demonstrated using a simulated data.     

多先验融合的图像显著性目标检测算法

为了更加准确地检测出图像中的显著性目标，提出了多先验融合的显著性目标检测算法。针对传统中心先验对偏离图像中心的显著性目标会出现检测失效的情况，提出在多颜色空间下求显著性目标的最小凸包交集来确定目标的大致位置，以凸包区域中心计算中心先验。同时通过融合策略将凸包区域中心先验、颜色对比先验和背景先验融合并集成到特征矩阵中。最后通过低秩矩阵恢复模型生成结果显著图。在公开数据集MSRA1000和ESSCD上的仿真实验结果表明，MPLRR能够得到清晰高亮的显著性目标视觉效果图，同时F，AUC，MAE等评价指标也比现有的许多方法有明显提升。     

基于张量分解融合RGB-D图像的物体识别

为了充分利用RGB-D图像的深度图像信息，提出了基于张量分解的物体识别方法。首先将RGB-D图像构造成一个四阶张量，然后将该四阶张量分解为一个核心张量和四个因子矩阵，再利用相应的因子矩阵将原张量进行投影，获得融合后的RGB-D数据，最后输入到卷积神经网络中进行识别。RGB-D数据集中三组相似物体的识别结果表明，利用张量分解融合RGB-D图像的物体识别准确率高于未采用张量分解的物体识别准确率，并且单一错分实例的准确率最高可提升99%。     

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.     

一种基于改进NMS的牛脸检测方法

针对牲畜牛身份认证的多牛脸检测场景，本文给出一种基于改进Faster R-CNN的牛脸检测方法。使用Inception v2替换ZF网络作为Faster R-CNN的基础网络，模型精度得到显著提升；针对多牛检测场景对NMS（Non-Maximum Suppression）进行相应优化，使模型的召回率得到显著提升。通过和其他目标检测模型对比实验，本文的改进模型在精确率和召回率上均优于其他模型。     

基于时空的弱点状运动目标检测技术

如何在复杂背景下持续有效地检测目标位置,一直是研究者们需要面对的主要挑战。本文在研究红外点状移动目标特征的基础上,根据目标无纹理,无形状的特性,提出一种改进的形态学目标增强算法,并利用目标连续时空不变性检测目标。首先,建立多尺度的图像金字塔,在每层上采用改进的形态学算法快速、粗糙定位小目标。然后进一步的根据目标在时空上的位置相关性,提出基于目标运动特征分析的精确检测方法。得到精确稳定的检测结果。最后实验结果表明与经典的形态学检测算法及其他算法相比,该技术能更有效地检测弱小目标,具有更高的鲁棒性。     

Application of differential evolution for cascaded multilevel VSI with harmonics elimination PWM switching

Harmonic elimination pulse width modulation (HEPWM) method has been widely applied to multilevel voltage source inverter (MVSI) to remove low frequency harmonics from its output voltage. However, the computation of the HEPWM switching angles for MVSI is very challenging due to several constraints, namely angle sequencing, very tight angular spacing and the numerous possibilities of angles distribution ratio. Realizing the potential of Differential Evolution (DE) to handle complex problems, this work proposes its application to solve the HEPWM problem for cascaded MVSI. Its emphasis is on improving the availability of HEPWM for higher output voltage by extending the maximum range of modulation index (M). It also removes the discontinuities in the switching angles and reduces the number of distribution ratio required to obtain the required solution. Compared to the most advanced (similar) work, i.e., 7-level MVSI with seventeen switching angles, DE covers a wider range of M; the maximum achievable M is 2.80. Furthermore, it exhibits very low second order distortion factor (DF₂): for the worst case, the value of DF₂ is 0.0014%. To verify the viability of the proposed algorithm, simulation is carried out and hardware prototype is constructed. Both results show very good agreement with the theoretical prediction.