Underwater image super-resolution using multi-stage information distillation networks

Recently, single image super-resolution (SISR) has been widely applied in the fields of underwater robot vision and obtained remarkable performance. However, most current methods generally suffered from the problem of a heavy burden on computational resources with large model sizes, which limited their real-world underwater robotic applications. In this paper, we introduce and tackle the super resolution (SR) problem for underwater robot vision and provide an efficient solution for near real-time applications. We present a novel lightweight multi-stage information distillation network, named MSIDN, for better balancing performance against applicability, which aggregates the local distilled features from different stages for more powerful feature representation. Moreover, a novel recursive residual feature distillation (RRFD) module is constructed to progressively extract useful features with a modest number of parameters in each stage. We also propose a channel interaction & distillation (CI&D) module that employs channel split operation on the preceding features to produce two-part features and utilizes the inter channel-wise interaction information between them to generate the distilled features, which can effectively extract the useful information of current stage without extra parameters. Besides, we present USR-2K dataset, a collection of over 1.6K samples for large-scale underwater image SR training, and a testset with an additional 400 samples for benchmark evaluation. Extensive experiments on several standard benchmark datasets show that the proposed MSIDN can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.     

Split Enzyme-Based Biosensors for Structural Characterization of Soluble and Insoluble β-Glucans

β-Glucan is widely distributed in various plants and microorganisms and is composed of β-1,3-linked d-glucose units. It may have a branched short or long side chain of glucose units with β-1,6- or β-1,4-linkage. Numerous studies have investigated different β-glucans and revealed their bioactivities. To understand the structure-function relationship of β-glucan, we constructed a split-luciferase complementation assay for the structural analysis of long-chain β-1,6-branched β-1,3-glucan. The N- and C-terminal fragments of luciferase from deep-sea shrimp were fused to insect-derived β-1,3-glucan recognition protein and fungal endo-β-1,6-glucanase (Neg1)-derived β-1,6-glucan recognition protein, respectively. In this approach, two β-glucan recognition proteins bound to β-glucan molecules come into close proximity, resulting in the assembly of the full-length reporter enzyme and induction of transient luciferase activity, indicative of the structure of β-glucan. To test the applicability of this assay, β-glucan and two β-glucan recognition proteins were mixed, resulting in an increase in the luminescence intensity in a β-1,3-glucan with a long polymer of β-1,6-glucan in a dose-dependent manner. This simple test also allows the monitoring of real-time changes in the side chain structure and serves as a convenient method to distinguish between β-1,3-glucan and long-chain β-1,6-branched β-1,3-glucan in various soluble and insoluble β-glucans.     

基于光刀图像的机器人示教纠偏方法

为了解决机器人辅助在线检测系统示教过程中效率低、人为干预多的问题,针对孔类特征,提出一种通过处理光刀图像获取机器人位姿纠正参数的方法。在该方法中,纠偏过程按照将图像光刀线调整为水平方向、将被测特征调整至图像中央、根据不同特征调整最优扫描方向3个步骤进行。根据光刀图像可以求出测量坐标系与被测特征的位姿关系,并得到该位姿与理想测量位姿的偏差。经过坐标变换即可得到在机器人基坐标系下的调整参数。另外,可利用电脑控制机器人运动,从而实现了纠偏过程的自动化。实验结果表明,该方法可将初始的示教位姿修正为理想位姿,且比传统方式效率更高。     

基于层次分析法的叶用甜菜种质资源观赏性评价

根据叶用甜菜品种的观赏特性,运用层次分析法初步建立叶用甜菜品种观赏价值的评价模型,包含叶梗、叶片和整体感3个方面共11个评价因子。结果表明:叶梗是评价叶用甜菜观赏价值的核心要素;叶梗色、叶梗厚、叶丛型是重要因子,分别以红、粉红、粉白叶梗,叶梗厚度厚和直立型叶丛为优良性状。利用该评价模型对8个甜菜品种进行观赏价值综合评价,筛选出‘Clnx-blush2018'、'Clnx-fen2018’和‘荷兰必久'3个观赏价值高、适于市场推广叶品种。     

Sub-band coding of hexagonal images

According to the circle-packing theorem, the packing efficiency of a hexagonal lattice is higher than an equivalent square tessellation. Consequently, in several contexts, hexagonally sampled images compared to their Cartesian counterparts are better at preserving information content. In this paper, novel mapping techniques alongside the wavelet compression scheme are presented for hexagonal images. Specifically, we introduce two tree-based coding schemes, referred to as SBHex (spirally-mapped branch-coding for hexagonal images) and BBHex (breadth-first block-coding for hexagonal images). Both of these coding schemes respect the geometry of the hexagonal lattice and yield better compression results. Our empirical results show that the proposed algorithms for hexagonal images produce better reconstruction quality at low bits per pixel representations compared to the tree-based coding counterparts for the Cartesian grid.     

基于音频特征的工程车辆工况识别研究

高效率地使用工程车辆是工程项目管理中节约成本的有效方法，无人监管环境下工程车辆的工况识别，是实现工程车辆高效率使用的有效手段。目前以GPS等技术为核心的车辆智能管理系统未对工程车辆进行工况识别，提出一种基于GRU循环神经网络的工程车辆工况识别方法，通过对工程车辆在不同工况下产生的音频信号进行分析，从中提取Mel倒谱系数作为主要特征，构建GRU循环神经网络模型进行训练和识别。实验结果表明，该方法可以实现对工程车辆工况的有效识别。     

空间曲线的特征识别与高质量非均匀采样

为避免传统均匀采样方法因忽视曲线重要特征而生成不理想的采样结果,获得给定数量且由特征点和辅助点组成的采样点序列,提出基于特征识别的高质量空间曲线非均匀采样方法.首先使用抛物线插值法得到曲线上所有曲率极大值点和挠率极大值点的近似位置,经筛选后产生特征点,以更好地抓住空间曲线的轮廓特征.然后定义基于弧长、曲率和挠率加权组合的特征函数,并以此自适应地选取曲线上的辅助点.与3种主流采样方法比较的实验结果表明,该方法能够获得更高质量的采样结果且具有更好的实用性,从而进一步改善空间曲线的B样条拟合效果.     

基于表情识别技术的用户研究方法

目的为了以更加客观的方式评估用户体验,拓展用户研究的途径,引入表情识别技术对已有用户研究方法进行优化与探索。方法以阅读APP为研究载体,以表情识别与卷积神经网络算法为技术手段,通过设计人机交互实验将其应用于用户研究过程中,建立用户面部表情与用户主观满意度的映射关系。结果针对阅读APP"X",开展了基于表情识别技术和传统问卷访谈的双向设计研究,并采用对比验证的方法得出了基于表情识别技术的用户满意度客观度量方法的有效性和可行性,进而挖掘了基于表情识别方法的用户研究优势。结论基于表情识别技术的用户研究方法在产品交互设计中具有一定的通用性。通过识别分析用户与产品进行人机交互时的面部表情动态变化,可以使用户体验评估更加客观并容易解读,准确定位产品交互体验问题,为设计领域中的用户研究和认识提供了新思路,同时也为表情识别技术与产品设计的交叉融合提供了理论和实践意义的参考。