Accurate Ulva prolifera regions extraction of UAV images with superpixel and CNNs for ocean environment monitoring

Wang, Shengke; Liu, Lu; Qu, Liang; Yu, Changyin; Sun, Yu; Gao, Feng; Dong, Junyu

doi:10.1016/j.neucom.2018.06.088

Cited by 35 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, Deep Learning (DL) has achieved great progress in object recognition (Tong et al, 2019; Xie et al, 2019), prediction (Yan et al, 2018; Hao et al, 2019), speech analysis (Cummins et al, 2018), noise reduction (Islam et al, 2018), monitoring (Li et al, 2018; Wang et al, 2018), medicine (Raja et al, 2015; Safdar et al, 2018), the recommendation system (Zhang and Liu, 2014), biometrics (Xing et al, 2017) and so on. Traditionally, DL consists of multiple layers of non-linear processing units to obtain the features.…”

Section: Methodsmentioning

confidence: 99%

Cerebral Micro-Bleeding Detection Based on Densely Connected Neural Network

et al. 2019

View full text Add to dashboard Cite

Cerebral micro-bleedings (CMBs) are small chronic brain hemorrhages that have many side effects. For example, CMBs can result in long-term disability, neurologic dysfunction, cognitive impairment and side effects from other medications and treatment. Therefore, it is important and essential to detect CMBs timely and in an early stage for prompt treatment. In this research, because of the limited labeled samples, it is hard to train a classifier to achieve high accuracy. Therefore, we proposed employing Densely connected neural network (DenseNet) as the basic algorithm for transfer learning to detect CMBs. To generate the subsamples for training and test, we used a sliding window to cover the whole original images from left to right and from top to bottom. Based on the central pixel of the subsamples, we could decide the target value. Considering the data imbalance, the cost matrix was also employed. Then, based on the new model, we tested the classification accuracy, and it achieved 97.71%, which provided better performance than the state of art methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Cerebral Micro-Bleeding Detection Based on Densely Connected Neural Network

et al. 2019

View full text Add to dashboard Cite

show abstract

“…For the areas with weak-connection, we list four typical regions that are construction sites in urban, disaster regions in urban, blind coverage spots in the city, and the transportation road. In these areas, some recent studies use UAVs to offer an extended network coverage and perform some specified applications such Areas with weak-connection Urban construction sites Construction project management [119]- [121] Indoor construction monitoring [122], [123] Disaster regions Disaster surveillance [80], [124], [125] Emergency networks construction [126]- [129] Urban coverage blind spots Enhanced coverage in urban area [29], [80], [130]- [133] Patrolling and surveillance [134]- [139] Transportation systems Intelligent transportation systems [140]- [143] Connection between ground vehicles [144]- [147] Areas without network deployment Farms Survey of UAV in agriculture [63], [148] Imagery analysis of crops [149]- [153] Deserts Disaster monitoring [154]- [156] Geomorphological analysis [61], [155], [157] Military detection [158] Forests Trees and plants monitoring [159]- [162] Forest growing volume prediction [163], [164] Oceans Coastal environment analysis [165]- [168] Ocean environment monitoring [169]- [171] Marine science and observation [18]...…”

Section: B Uav-enabled Ioementioning

confidence: 99%

Unmanned aerial vehicle for internet of everything: Opportunities and challenges

Liu

Dai

Wang

et al. 2020

Computer Communications

162

View full text Add to dashboard Cite

The recent advances in information and communication technology (ICT) have further extended Internet of Things (IoT) from the sole "things" aspect to the omnipotent role of "intelligent connection of things". Meanwhile, the concept of internet of everything (IoE) is presented as such an omnipotent extension of IoT. However, the IoE realization meets critical challenges including the restricted network coverage and the limited resource of existing network technologies. Recently, Unmanned Aerial Vehicles (UAVs) have attracted significant attentions attributed to their high mobility, low cost, and flexible deployment. Thus, UAVs may potentially overcome the challenges of IoE. This article presents a comprehensive survey on opportunities and challenges of UAV-enabled IoE. We first present three critical expectations of IoE: 1) scalability requiring a scalable network architecture with ubiquitous coverage, 2) intelligence requiring a global computing plane enabling intelligent things, 3) diversity requiring provisions of diverse applications. Thereafter, we review the enabling technologies to achieve these expectations and discuss four intrinsic constraints of IoE (i.e., coverage constraint, battery constraint, computing constraint, and security issues). We then present an overview of UAVs. We next discuss the opportunities brought by UAV to IoE. Additionally, we introduce a UAV-enabled IoE (Ue-IoE) solution by exploiting UAVs's mobility, in which we show that Ue-IoE can greatly enhance the scalability, intelligence and diversity of IoE. Finally, we outline the future directions in Ue-IoE.

show abstract

“…3) Minimum area bounding rectangle (MBR) of green tides The distribution of U.prolifera green tide is one of the most important significant characteristics. In previous researches, the outer contour of U.prolifera covering pixels on satellite images is chosen as the green tide distribution in many researches [2], [29], [31]. As is shown in Fig.…”

Section: ) Gravity Center Of Green Tidesmentioning

confidence: 99%

Bidirectional Spatio-Temporal Association Between the Observed Results of Ulva Prolifera Green Tides in the Yellow Sea and the Social Response in Sina Weibo

Wang

Fang

Song

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Massive green tides caused by Ulva prolifera have annually occurred in the Yellow Sea since 2007, which has attracted much attention from the government and society. There are associations between the green tides in the Yellow Sea and social response in the social media (i.e. Sina Weibo), which are bidirectional and could be captured by the bidirectional neural network. For instance, how to detect daily U.prolifera green tides by fusing remote sensing data with social media data, and how to use the observed U.prolifera green tides to infer the social response are two challenges of State-Oceanic Administration, China. This paper first illustrated that there are bidirectional associations between green tides and Sina Weibo data. Then, this paper introduced a bidirectional spatiotemporal associative memory neural network model (BSAMNN) for modeling this bidirectional association from the spatiotemporal perspective. BSAMNN first extracted six characteristics from green tides and nine characteristics from the social responses in 2016-2019. Secondly, these characteristics were split by year and the characteristics in 2016-2018 were respectively put into the bidirectional associative memory neural network (BAM) which is a two-layer artificial neural network. Based on the BAM results and the observed data, the residual network was constructed. Thirdly, BSAMNN extracted the spatiotemporal rules from the characteristics in 2016-2018 as the constraints through the mining rule algorithm and modify the results via sea surface wind and ocean surface current. Last, BSAMNN put the characteristics in 2019 into BAM and used the residual network to modify the results, which was constrained by the spatiotemporal rules.The feasibility and reliability of our approach were demonstrated by using the U.prolifera green tides in 2019. The average accuracy, false alarm rate, and missing alarm rate of BSAMNN results were 0.69, 0.25, and 0.31 respectively which was 0.11 higher, 0.10 lower, and 0.11 lower than that of the traditional bidirectional associative memory neural network. The results indicated that our method is an effective alternative of linking the U.prolifera green tides and its public sentiments on social media.

show abstract

Accurate Ulva prolifera regions extraction of UAV images with superpixel and CNNs for ocean environment monitoring

Cited by 35 publications

References 26 publications

Cerebral Micro-Bleeding Detection Based on Densely Connected Neural Network

Cerebral Micro-Bleeding Detection Based on Densely Connected Neural Network

Unmanned aerial vehicle for internet of everything: Opportunities and challenges

Bidirectional Spatio-Temporal Association Between the Observed Results of Ulva Prolifera Green Tides in the Yellow Sea and the Social Response in Sina Weibo

Contact Info

Product

Resources

About