Search

Hyperspectral target detection is widely used in both military and civilian fields. In practical applications, how to select a low-correlation and representative band subset to reduce redundancy is worth discussing. However, most of the existing band selection (BS) methods usually select bands according to the statistics or correlation, which neglect the spectral characteristics of the desired target and are not specially designed for target detection. Therefore, this article proposed a novel BS method, called constrained-target BS with subspace partition (CTSPBS), to select an optimal subset with low internal correlation and strong target representability for the target detection task. By using a specially designed subspace partition method based on correlation distance (CDSP), CTSPBS divides the hyperspectral bands into several unrelated subspaces. Then, according to certain constrained-target band prioritization (BP) criteria, the band with the highest priority in each subset is selected to form the optimal subset for a specific target. Correspondingly, two versions of the proposed method, minimum variance BS with CDSP (CDSP_MinV) and minimum variance BS with CDSP (CDSP_MaxV), are derived to implement CTSPBS. Extensive experiments on three public hyperspectral datasets demonstrate that the proposed method exhibit more robust and effective performance than several state-of-the-art methods. Finally, this article focuses on the difficulty of marine benthos detection in mariculture application and proves the feasibility of the proposed method.

Vehicle re-identification (re-ID) plays an important role in the automatic analysis of the increasing urban surveillance videos and has become a hot topic in recent years. Vehicle re-ID aims at identifying vehicles across different cameras. However, it suffers from the difficulties caused by various viewpoint of vehicles, diversified illuminations, and complicated environments. In this paper, a two-stage vehicle re-ID framework is proposed to address these challenges, which contains a feature extraction module for achieving discriminative features and a spatial-temporal re-ranking module to improve the accuracy of vehicle re-ID task. Firstly, a multi-task deep network that integrates identity predicting network, attribute recognition network and verification network is adopted to learn discriminate features. Secondly, a spatio-temporal model is built to re-rank the appearance information measurement results, which utilizes the spatio-temporal relationship to increase constraints of the images. Moreover, to facilitate progressive vehicle re-ID research, experiments are conducted on both the VeRi-776 dataset and VehicleID dataset. Both the proposed multi-task feature extraction module and spatio-temporal model achieve considerable improvements.

The widespread popularization of vehicles has facilitated all people’s life during the last decades. However, the emergence of a large number of vehicles poses the critical but challenging problem of vehicle re-identification (reID). Till now, for most vehicle reID algorithms, both the training and testing processes are conducted on the same annotated datasets under supervision. However, even a well-trained model will still cause fateful performance drop due to the severe domain bias between the trained dataset and the real-world scenes. To address this problem, this paper proposes a domain adaptation framework for vehicle reID (DAVR), which narrows the cross-domain bias by fully exploiting the labeled data from the source domain to adapt the target domain. DAVR develops an image-to-image translation network named Dual-branch Adversarial Network (DAN), which promotes the images from the source domain (well-labeled) to learn the style of the target domain (unlabeled). Specially, DAN doesn’t need any annotation and can preserve identity information from source domain before and after translation. Furthermore, the generated images are employed to train the vehicle reID model by a proposed attention-based feature learning network. Through the proposed framework, the well-trained reID model has better generalization ability for various scenes in real-world situations. Comprehensive experimental results have demonstrated that our proposed DAVR can achieve excellent performances on benchmark datasets VehicleID and VeRi-776.

Marine object detection is an appealing but challengeable task in computer vision. Even though recent popular object detection algorithms perform well on common classes, they cannot acquire satisfied detection performance on marine objects because underwater images are affected by color cast and blur, and scales of the target in underwater images are usually small. These phenomena aggravate the difficulty of detection. Thus, it is urgent to design a proper structure to settle marine object detection issues. To this end, this paper proposes a novel scale-aware feature pyramid architecture named SA-FPN to extract abundant robust features on underwater images and improve the performance on marine object detection. Specifically, we design a special backbone subnetwork to improve the ability of feature extraction, which could provide richer fine-grained features for small object detection. What is more, this paper proposes a multi-scale feature pyramid to enrich the semantic features for prediction. Each feature map is enhanced by the higher level layer with context information through a top-down upsampling pathway. Through obtaining ample feature maps on underwater images, our algorithm could generate multiple bounding boxes for each target. To mitigate the reduplicative boxes and avoid miss suppression, we replace the non-maximum suppression method with soft non-maximum suppression. In this paper, we evaluate our algorithm on underwater image datasets and achieve 76.27% mAP. Meanwhile, we conduct experiments on PASCAL VOC datasets and smart unmanned vending machines datasets and get 79.13% mAP and 91.81% mAP, respectively. The experimental results reveal that our approach achieves best performance not only on marine object detection, but also on common classes.

Objectives This study sought to define electrographic characteristics of the fossa ovalis (FO) and use these findings in developing a 3-dimensional (3D) transseptal puncture (TSP) technique that does not rely on fluoroscopy or echocardiography. Background Traditional TSP method based on fluoroscopy or echocardiography is basically a 2-dimensional (2D) technique. A valid 3D method of TSP has not been sufficiently clarified. Methods The shape of the FO and its center were “electrographically” defined by comparing their potential characteristics to those of the surrounding limbus. After validation by intracardiac echocardiography, this FO mapping was incorporated into 3D electroanatomical reconstruction of the right atrium. Using a new catheter connection, the transseptal needle could be visualized nonfluoroscopically and directed to the precise localization of the FO on the electroanatomic map. Results A total of 276 patients who underwent atrial fibrillation ablation were included. The central FO was identified in all cases with atrial electrogram voltage at 0.33 ± 0.21 mV. The amplitude of atrial potential at the FO annulus was 1.70 ± 0.72 mV (p Conclusions Electrographic characteristics of the FO center are distinct from those of the surrounding regions. This information can be leveraged to define the FO on 3D electroanatomic mappings, thereby facilitating safe TSP without the need of ancillary imaging with fluoroscopy or echocardiography.

Band selection (BS) is considered as an effective method for dimensionality reduction of hyperspectral data. As an important application for hyperspectral remote sensing, target detection is widely concerned. Therefore, how to select more representational band subset for specific target to improve performance of detection is worth discussing. This letter proposed a BS method for specific target detection, called constrained target band selection under adaptive subspace partitioning (CTASPBS). Firstly, all bands are partitioned into multiple weakly correlated subsets via adaptive subspace partition strategy (ASPS). Then, according to a target-constrained band prioritization (BP) criterion, the band with the highest priority in each subset is selected to form the optimal band subset. Due to the application of different BP criterion, two BS methods ASPS_MinV and ASPS_MaxV are proposed. Finally, experimental results on real hyperspectral data show that CTASPBS is an effective BS method for specific target detection.

BACKGROUND To find out the real-world investigation on discontinuation of oral anticoagulation after paroxysmal atrial fibrillation (AF) catheter ablation China. METHODS We enrolled in our study 1,508 consecutive paroxysmal AF patients who underwent catheter ablation from five centers. Patients' clinical data and follow-up data were collected. Clinical data included on-admission characteristics such as gender, age, type and duration of AF, type of ablation, ablation sessions, history of diseases, CHA2DS2-VASc score, echocardiographic variables, medication, and blood test variables. Follow-up data included duration of follow-up, the status of oral anticoagulant (OAC) therapy, adverse events, and recurrence of AF. RESULTS A total of 1,491 patients were included in the final analysis, while the other 17 patients lost contact. The follow-up duration was 12 to 74 months (27.8±14.6 months). Of 1,491 patients, 989 (66.3%) patients stopped OAC therapy 3 to 14 months after successful ablation during follow-up. Stroke or transient ischemic attack (TIA) occurred in 37 (2.5%) patients. Major bleeding occurred in 24 (1.6%) patients. Six (0.4%) patients died at follow-up. Patients who stopped OAC had lower CHA2DS2-VASc score (1.5±1.4 vs. 2.4±1.7, P

With the development of smart cities, urban surveillance video analysis will play a further significant role in intelligent transportation systems. Identifying the same target vehicle in large datasets from non-overlapping cameras should be highlighted, which has grown into a hot topic in promoting intelligent transportation systems. However, vehicle re-identification (re-ID) technology is a challenging task since vehicles of the same design or manufacturer show similar appearance. To fill these gaps, we tackle this challenge by proposing Triplet Center Loss based Part-aware Model (TCPM) that leverages the discriminative features in part details of vehicles to refine the accuracy of vehicle re-identification. TCPM base on part discovery is that partitions the vehicle from horizontal and vertical directions to strengthen the details of the vehicle and reinforce the internal consistency of the parts. In addition, to eliminate intra-class differences in local regions of the vehicle, we propose external memory modules to emphasize the consistency of each part to learn the discriminating features, which forms a global dictionary over all categories in dataset. In TCPM, triplet-center loss is introduced to ensure each part of vehicle features extracted has intra-class consistency and inter-class separability. Experimental results show that our proposed TCPM has an enormous preference over the existing state-of-the-art methods on benchmark datasets VehicleID and VeRi-776.

This study sought to define electrographic characteristics of the fossa ovalis (FO) and use these findings in developing a 3-dimensional (3D) transseptal puncture (TSP) technique that does not rely on fluoroscopy or echocardiography.Traditional TSP method based on fluoroscopy or echocardiography is basically a 2-dimensional (2D) technique. A valid 3D method of TSP has not been sufficiently clarified.The shape of the FO and its center were "electrographically" defined by comparing their potential characteristics to those of the surrounding limbus. After validation by intracardiac echocardiography, this FO mapping was incorporated into 3D electroanatomical reconstruction of the right atrium. Using a new catheter connection, the transseptal needle could be visualized nonfluoroscopically and directed to the precise localization of the FO on the electroanatomic map.A total of 276 patients who underwent atrial fibrillation ablation were included. The central FO was identified in all cases with atrial electrogram voltage at 0.33 ± 0.21 mV. The amplitude of atrial potential at the FO annulus was 1.70 ± 0.72 mV (p 0.001). By incorporating the electrographically defined FO into the 3D electroanatomic mapping and using the transseptal needle visualization approach, TSP was successful in all patients, with 91% of the cases at the first attempt. Atrial fibrillation ablation was completed in all patients with no major complication.Electrographic characteristics of the FO center are distinct from those of the surrounding regions. This information can be leveraged to define the FO on 3D electroanatomic mappings, thereby facilitating safe TSP without the need of ancillary imaging with fluoroscopy or echocardiography.

Background To study the effectiveness and safety of atrial fibrillation (AF) catheter ablation after pericardiectomy. Methods Data of 24 consecutive AF patients after pericardiectomy underwent catheter ablation from five centers were collected and analyzed retrospectively. All patients were followed up at 1, 3, and 12 months after catheter ablation. Results of a repeated blood test, electrocardiogram, and echocardiography during follow-up were also collected. Adverse events such as recurrence of AF, heart failure, stroke/transient ischemic attack (TIA) and minor, and major bleeding were recorded. All patients underwent brain magnetic resonance imaging (MRI) at the end of 12 months follow-up. Results Patients were young (20-73 years old, 48.1±11.0). Fifteen (62.5%) patients were male. CHA2DS2-VASc score (0-3, 0.21±0.41) was low in these 24 patients. Among these patients, 11 (45.8%) were paroxysmal AF, 8 (33.3%) were persistent AF, and 5 (20.8%) were long-lasting persistent AF. Left atrium diameter over 45 mm was detected in 17 (70.8%) patients. All patients underwent catheter ablation successfully. No peri-ablation procedure-related complication happened. Oral anticoagulant therapy was stopped 3 months after the final ablation. Anti-arrhythmia drugs were continued for all patients after ablation. For 12 months follow-up, AF recurred in 10 (41.7%) patients 3-7 months after the first ablation. MRI detected silent cerebral infarction (SCI) in 2 (8.3%) patients. No other adverse events occurred during follow-up. Conclusions It is safe for AF patients to undergo catheter ablation after pericardiectomy, but the rate of recurrence of AF is high.

Detection and counting small objects using under-water robot draw an appealing attention because of its urgent demands in marine aquaculture. Because this challenge problem must be solved before the underwater robot can be used to catch seafood in practice instead of diver. This paper proposed a novel method using Faster R-CNN and kernelized correlation filter (KCF) tracking algorithm to detect seafood objects, such as sea cucumber, sea urchin, and scallop and so on in real time. Firstly, we trained an accurate and stable Faster R-CNN detector with VGG model using underwater image database, which is built by ourselves. Next, we recognized and tracked the seafood objects in order to fetch them using underwater robot vision in naturalistic ocean environment. The experimental results show the proposed method can recognized and catch seafood in real time using our integrated underwater robot.

In this paper, scanning electron microscopy (SEM), microscopy and laser diffracting measurements experiments were adopted for investigating the shape and size of the linked polymer microspheres. Besides, nuclear-pore film filtration and sand packed tube displacement experiments were also adopted to investigate the matching relationship between the microspheres size and pores size. The results demonstrated that the original shape of the microspheres was typically spherical with a size range of 200 nanometers to 20 micrometers. When the microspheres were dispersed in water, their size increased due to swelling but spherical conformation remained. And the polydispersed microsphere system appeared. There was a certain matching relationship between the microsphere size and the membranes pores size, and the best plugging property could only occur when they were well-matched. A matching relationship also existed in the sand packed tube displacement experiment, and plugging could occur effectively only if sand packed tubes with low permeability were used.

In this article, the morphology, particle size, and plugging properties of crosslinked polyacrylamide (CPAM) microspheres were investigated through optical microscopy, scanning electron microscopy (SEM), nuclear-pore membrane filtration experiments, a micro-visual model, sandpack experiments, parallel twin-tube plugging, and oil displacement experiments. The results revealed that the primary particle sizes of the CPAM microspheres ranged from several hundreds of nanometers to 5 μm; however, after the microspheres were fully swelled in water, their sizes increased by approximately five times of their original sizes. As a CPAM microsphere dispersion system had good dispersibility and deformation capabilities, a 1.2 μm nuclear-pore membrane as well as the deep part of a sandpack tube could be effectively plugged. Consequently, the flow diversion effect was achieved in the vertical and planar directions. When the CPAM microspheres migrated in porous media, they could displace residual oil on the pole wall and water flow channel to realize the synchronization of profile control and coordination and improve recovery efficiency. © 2016 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2016, 133, 43666.

Coronary heart disease (CHD) is the most common type of heart disease and cause of heart attacks. This study investigated the epidemiological characteristics of CHD and its risk factors in Jiaozhou, Shandong province, to ultimately find a way of reducing the prevalence of cardiovascular disease, and to provide a theoretical basis for establishing a cardiovascular disease management path under the regional medical collaborative mechanism.A questionnaire survey was performed including 1 952 people aged 35 years or older who were questioned by means of stratified, cluster, proportional sampling to investigate the prevalence of CHD and its risk factors. The data were inputted into SPSS11.0 statistical software for processing and analysis. We advised the local medical institutions to establish health files for the residents with CHD and risk factors. They were followed up regularly. Their risk factors and life-style were monitored, and advice was given as to proper medications. Green channels were established, and the patients were transmitted in a timely manner to superior hospitals for better treatment if the necessary treatments were not available in the local hospitals. The control of risk factors was observed after the follow-up for half a year.In Jiaozhou, the rates of coronary artery disease, hypertension, diabetes, hyperlipidemia and overweight were 8.15%, 28.54%, 11.43%, 35.46%, and 18.70% respectively. The rates of hypertension, diabetes, hyperlipidemia and overweight were higher than the data published in "The report of Chinese cardiovascular disease 2012"; which are 24%, 9.7%, 18.6%, and 9.7%, respectively. The control of risk factors improved significantly after the guidance of the residents lifestyle and medication for six months.The high prevalence of coronary artery disease in Jiaozhou is closely related to age, gender, diet structure, family history of cardiovascular disease, hypertension, diabetes, hyperlipidemia, overweight, and unhealthy lifestyle. Under the regional medical coordination mechanism, the collaborative management of cardiovascular disease can provide new management concepts for the areas short of medical resources, so as to reduce the prevalence of cardiovascular disease.