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.     

Looking ahead: Joint small group detection and tracking in crowd scenes

Small group detection and tracking in crowd scenes are basis for high level crowd analysis tasks. However, it suffers from the ambiguities in generating proper groups and in handling dynamic changes of group configurations. In this paper, we propose a novel delay decision-making based method for addressing the above problems, motivated by the idea that these ambiguities can be solved using rich temporal context. Specifically, given individual detections, small group hypotheses are generated. Then candidate group hypotheses across consecutive frames and their potential associations are built in a tree. By seeking for the best non-conflicting subset from the hypothesis tree, small groups are determined and simultaneously their trajectories are got. So this framework is called joint detection and tracking. This joint framework reduces the ambiguities in small group decision and tracking by looking ahead for several frames. However, it results in the unmanageable solution space because the number of track hypotheses grows exponentially over time. To solve this problem, effective pruning strategies are developed, which can keep the solution space manageable and also improve the credibility of small groups. Experiments on public datasets demonstrate the effectiveness of our method. The method achieves the state-of-the-art performance even in noisy crowd scenes.     

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。     

Utilizing sensor data to model students’ creativity in a digital environment

While creativity is essential for developing students’ broad expertise in Science, Technology, Engineering, and Math (STEM) fields, many students struggle with various aspects of being creative. Digital technologies have the unique opportunity to support the creative process by (1) recognizing elements of students’ creativity, such as when creativity is lacking (modeling step), and (2) providing tailored scaffolding based on that information (intervention step). However, to date little work exists on either of these aspects. Here, we focus on the modeling step. Specifically, we explore the utility of various sensing devices, including an eye tracker, a skin conductance bracelet, and an EEG sensor, for modeling creativity during an educational activity, namely geometry proof generation. We found reliable differences in sensor features characterizing low vs. high creativity students. We then applied machine learning to build classifiers that achieved good accuracy in distinguishing these two student groups, providing evidence that sensor features are valuable for modeling creativity.     

Studying local liquid velocity in liquid–solid packed bed using the newly developed X-ray DIR technique

Combination of X-ray Digital Industrial Radiography (DIR) and Particle Tracking Velocimetry (PTV) techniques for local liquid velocity measurement (V_LL) has been newly developed and successfully applied for trickle bed reactor (TBR). The technique was validated against newly developed fiber optical probe technique. This work attempts to highlight the applicability of this newly developed technique on a liquid–solid packed bed reactor. In this work, liquid was represented by water and solids were represented by EPS beads. The EPS beads were chosen because of its low density property. Three superficial liquid velocities (V_SL) were applied to the system. The experiment was replicated four times. The digital industrial radiography (DIR) consists of a complementary metal oxide semiconductor (CMOS) digital detector and X-ray source. Results of this work suggest that the technique has been successfully applied and comparable with previous work that has been done in the literature. It also suggests that there will be a maximum measurable interstitial liquid velocity when it travel inside the packed bed. The measured V_LL can have a maximum range that is between 4 and 4.7 times that of its V_SL. For V_SL=0.42±±2%, the V_LL-Max is in between 1.7 cm/s and 1.9 cm/s, V_SL=0.84±±2%, the V_LL-Max is in between 3.6 cm/s and 4.0 cm/s, and for V_SL=1.11±±2%, the V_LL-Max is in between 4.3 cm/s and 4.8 cm/s.     

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.     

小型机载激光通信系统设计与验证

针对空空宽带高速通信的需求，设计了小型化机载激光通信系统。仿真分析了300 km、2.5 Gb/s无线激光链路性能，并通过运动仿真台模拟机动环境测试了系统的跟踪与通信性能，其中粗跟踪误差为533.2 μrad(1σ)，精跟踪误差为3.6 μrad(1σ)，测试数据传输240 s，通信误码率为2.82×10-9。仿真与实验验证了该系统用于远距离空空无线激光通信的可行性。