A5054067779- Water Quality Monitoring Technologies
- Identification and Quantification in Food
- Marine and fisheries research
- Maritime Navigation and Safety
- Building Energy and Comfort Optimization
- Phase Change Materials Research
- Maritime and Coastal Archaeology
- Adsorption and Cooling Systems
- Smart Agriculture and AI
- Ichthyology and Marine Biology
- Advanced Technologies in Various Fields
Shanghai Ocean University
2021-2024
Chinese Academy of Fishery Sciences
2022-2023
Ministry of Agriculture and Rural Affairs
2022-2023
The refined monitoring and identification of fishing operations by vessels is great significance value to vessels. In order solve the problem inaccurate statistics current Engraulis japonicus quota classification, this paper proposes an improved algorithm based on YOLOv5. This method introduces SENet attention mechanism into YOLOv5 backbone network structure, integrates target information in different periods operations, reduces interference complex backgrounds, improves precision model...
Marine fishery resources are linked to global food security and the livelihoods of millions people, but their sustainability is seriously affected by overexpansion fishing activities. The regulation activities vessels has been based on ineffective data sources. Fortunately, rapid developments in nighttime light remote sensing have provided effective for formulation marine fisheries regulations. We conducted a series experiments explore application Luojia1-01 (LJ-01) images extraction...
Present study used the position data of BeiDou Vessel Monitoring System (VMS) in 2018, with respect to motorised fishingvessels East China Sea and Yellow construct a fishing vessel operating status classification model based onthreshold, deep neural network DBSCAN density clustering algorithm. The geographic grid was divided into cells of0.1°×0.1° average time per square km (h km-2) each calculated obtain spatial distributionof intensity region 2018. results showed that threshold method...
Abstract This essay will introduce an increasingly popular topic: Green building. We list 3 important fields of green building technology, which are materials, structure design and energy. In each part we some advanced technologies evaluate them with principles.
In order to solve the statistical problem of some targets when fishing vessels are operating, based on deep learning technology, this paper uses improved YOLOv5s and SORT algorithms achieve target statistics. First, is fused with CBAM SE attention mechanism modules, respectively, reduce interference complex backgrounds improve model detection accuracy simultaneously. Comparing three models, a better effect selected. Secondly, through threshold method, algorithm combined line DeepSORT count...
The type of fishing vessel operation is an important parameter for the and management fishery resources. offshore motor vessels in East China Sea Yellow were taken as object research, BeiDou Vessel Monitoring System (VMS) position data from 2018 these objects used. filtered extracted according to operating characteristics canvas stow net vessel, trajectory map drawn. On this basis, a classification method based on migration learning proposed. This uses VGG16 basic network, parameters that...
The fish target detection algorithm lacks a good quality data set, and the achieves real-time with lower power consumption on embedded devices, it is difficult to balance calculation speed identification ability. To this end, paper collected annotated set of 84 fishes containing 10042 images, based proposed multi-scale input fast network (BTP-yoloV3) its optimization method. experiment uses Depthwise convolution redesign backbone yoloV4 network, which reduces amount by 94.1%, test accuracy...