星载海洋激光雷达最佳工作波长分析

星载激光雷达是实现海洋垂直剖面探测的有效工具,也是目前迫切需求的海洋光学遥感手段。对星载海洋激光雷达的波长参数进行评估对保证探测有效性具有重要意义。本文从探测深度和信噪比两方面分析了星载海洋激光雷达探测全球海洋的最佳波长。利用MODIS 10个波段的水体光学特性数据,估算全球海水探测深度及相应的最优波长;并根据太阳夫琅禾费暗线特性,对信号信噪比进行优化。结果表明:在探测深度方面,最优探测波长在488 nm波段的海洋占全球海洋面积的70%左右,并且全球95%以上的海域在488 nm波段的探测深度优于0.8倍的真光层深度;在信噪比方面,相对于488 nm波段,486.134 nm夫琅禾费暗线处采用0.1 nm带宽的滤光片可以将背景光强度降低70%,相应地回波信噪比整体提升了约5.0%。就全球海洋探测来说,使用486.134 nm作为探测波长可以提高探测深度,有效抑制太阳背景光,提高信噪比,因此,486.134 nm是星载海洋激光雷达的最佳工作波长。     

Double Feature Extraction Method of Ship-Radiated Noise Signal Based on Slope Entropy and Permutation Entropy

In order to accurately identify various types of ships and develop coastal defenses, a single feature extraction method based on slope entropy (SlEn) and a double feature extraction method based on SlEn combined with permutation entropy (SlEn&PE) are proposed. Firstly, SlEn is used for the feature extraction of ship-radiated noise signal (SNS) compared with permutation entropy (PE), dispersion entropy (DE), fluctuation dispersion entropy (FDE), and reverse dispersion entropy (RDE), so that the effectiveness of SlEn is verified, and SlEn has the highest recognition rate calculated by the k-Nearest Neighbor (KNN) algorithm. Secondly, SlEn is combined with PE, DE, FDE, and RDE, respectively, to extract the feature of SNS for a higher recognition rate, and SlEn&PE has the highest recognition rate after the calculation of the KNN algorithm. Lastly, the recognition rates of SlEn and SlEn&PE are compared, and the recognition rates of SlEn&PE are higher than SlEn by 4.22%. Therefore, the double feature extraction method proposed in this paper is more effective in the application of ship type recognition.     

空间雷电探测实时采集定位系统

星载雷电探测定位系统是利用光学探测器探测闪电事件的地理位置和光脉冲波形,系统采用CPLD+DSP的数字图像处理方案,利用了CPLD复杂逻辑可编程特性将系统的部分或全部功能集成在一片CPLD上,减小了系统硬件复杂程度,节省了印制版空间.利用DSP高速数字信号处理特性完成实时处理图像数据的功能.系统用CPLD完成图像信号的采集、编码和存储控制,缩小了星载设备体积,简化了电路结构;用DSP完成大量图像数据处理工作,提高了系统工作的实时性.     

Domain-Specific On-Device Object Detection Method

Object detection is a significant activity in computer vision, and various approaches have been proposed to detect varied objects using deep neural networks (DNNs). However, because DNNs are computation-intensive, it is difficult to apply them to resource-constrained devices. Here, we propose an on-device object detection method using domain-specific models. In the proposed method, we define object of interest (OOI) groups that contain objects with a high frequency of appearance in specific domains. Compared with the existing DNN model, the layers of the domain-specific models are shallower and narrower, reducing the number of trainable parameters; thus, speeding up the object detection. To ensure a lightweight network design, we combine various network structures to obtain the best-performing lightweight detection model. The experimental results reveal that the size of the proposed lightweight model is 21.7 MB, which is 91.35% and 36.98% smaller than those of YOLOv3-SPP and Tiny-YOLO, respectively. The f-measure achieved on the MS COCO 2017 dataset were 18.3%, 11.9% and 20.3% higher than those of YOLOv3-SPP, Tiny-YOLO and YOLO-Nano, respectively. The results demonstrated that the lightweight model achieved higher efficiency and better performance on non-GPU devices, such as mobile devices and embedded boards, than conventional models.     

Deep Hierarchical Ensemble Model for Suicide Detection on Imbalanced Social Media Data

As a serious worldwide problem, suicide often causes huge and irreversible losses to families and society. Therefore, it is necessary to detect and help individuals with suicidal ideation in time. In recent years, the prosperous development of social media has provided new perspectives on suicide detection, but related research still faces some difficulties, such as data imbalance and expression implicitness. In this paper, we propose a Deep Hierarchical Ensemble model for Suicide Detection (DHE-SD) based on a hierarchical ensemble strategy, and construct a dataset based on Sina Weibo, which contains more than 550 thousand posts from 4521 users. To verify the effectiveness of the model, we also conduct experiments on a public Weibo dataset containing 7329 users’ posts. The proposed model achieves the best performance on both the constructed dataset and the public dataset. In addition, in order to make the model applicable to a wider population, we use the proposed sentence-level mask mechanism to delete user posts with strong suicidal ideation. Experiments show that the proposed model can still effectively identify social media users with suicidal ideation even when the performance of the baseline models decrease significantly.     

HMD-Net: A Vehicle Hazmat Marker Detection Benchmark

Vehicles carrying hazardous material (hazmat) are severe threats to the safety of highway transportation, and a model that can automatically recognize hazmat markers installed or attached on vehicles is essential for intelligent management systems. However, there is still no public dataset for benchmarking the task of hazmat marker detection. To this end, this paper releases a large-scale vehicle hazmat marker dataset named VisInt-VHM, which includes 10,000 images with a total of 20,023 hazmat markers captured under different environmental conditions from a real-world highway. Meanwhile, we provide an compact hazmat marker detection network named HMD-Net, which utilizes a revised lightweight backbone and is further compressed by channel pruning. As a consequence, the trained-model can be efficiently deployed on a resource-restricted edge device. Experimental results demonstrate that compared with some established methods such as YOLOv3, YOLOv4, their lightweight versions and popular lightweight models, HMD-Net can achieve a better trade-off between the detection accuracy and the inference speed.     

Learning Visible Thermal Person Re-Identification via Spatial Dependence and Dual-Constraint Loss

Visible thermal person re-identification (VT Re-ID) is the task of matching pedestrian images collected by thermal and visible light cameras. The two main challenges presented by VT Re-ID are the intra-class variation between pedestrian images and the cross-modality difference between visible and thermal images. Existing works have principally focused on local representation through cross-modality feature distribution, but ignore the internal connection of the local features of pedestrian body parts. Therefore, this paper proposes a dual-path attention network model to establish the spatial dependency relationship between the local features of the pedestrian feature map and to effectively enhance the feature extraction. Meanwhile, we propose cross-modality dual-constraint loss, which adds the center and boundary constraints for each class distribution in the embedding space to promote compactness within the class and enhance the separability between classes. Our experimental results show that our proposed approach has advantages over the state-of-the-art methods on the two public datasets SYSU-MM01 and RegDB. The result for the SYSU-MM01 is Rank-1/mAP 57.74%/54.35%, and the result for the RegDB is Rank-1/mAP 76.07%/69.43%.     

A new liquid-phase microextraction method based on solidification of floating organic drop

In the present study, a new and versatile liquid-phase microextraction method is described. This method requires very simple and cheap apparatus and also a small amount of organic solvent. Eight microliters of 1-undecanol was delivered to the surface of solution containing analytes and solution was stirred for a desired time. Then sample vial was cooled by inserting it into an ice bath for 5 min. The solidified 1-undecanol was transferred into a suitable vial and immediately melted; then, 2 μL of it was injected into a gas chromatograph for analysis.Some polycyclic aromatic hydrocarbons (PAHs) were used as model compounds for developing and evaluating of the method performance. Analysis was carried out by gas chromatography/flame ionization detection (GC/FID).Several factors influencing the microextraction efficiency, such as the nature and volume of organic solvent, the temperature and volume of sample solution, stirring rate and extraction time were investigated and optimized. The applicability of the technique was evaluated by determination of trace amounts of PAHs in environmental samples. Under the optimized conditions, the detection limits (LOD) of the method were in the range of 0.07-1.67 μg L⁻¹ and relative standard deviations (R.S.D.) for 10 μg L⁻¹ PAHs were <7%. A good linearity (r² > 0.995) in a calibration range of 0.25-300.00 μg L⁻¹ was obtained. After 30 min extraction duration, enrichment factors were in the range of 594-1940. Finally, the proposed method was applied to the determination of trace amounts of PAHs in several real water samples, and satisfactory results were resulted. Since very simple devices were used, this new technique is affordable, efficient, and convenient for extraction and determination of low concentrations of PAHs in water samples.