Jinling Li

Jinling Li

Auto-generated profile, based on publicly available information

Jinling Li

University of South China,Computer School,Hengyang,China,421001

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2021 in Photogrammetric Engineering & Remote Sensing
Verified
Journal Article
Open access
QCQimin Cheng
Qimin Cheng
YXYuan Xu
Yuan Xu
PFPeng Fu
Peng Fu
JLJinling Li
Jinling Li
WWWei Wang
Wei Wang
YRYingchao Ren
Yingchao Ren
Deep learning techniques, especially convolutional neural networks, have boosted performance in analyzing and understanding remotely sensed images to a great extent. However, existing scene-classification methods generally neglect local and spatial information that is vital to scene classification of remotely sensed images. In this study, a method of scene classification for remotely sensed images based on pretrained densely connected convolutional neural networks combined with an ensemble classifier is proposed to tackle the under-utilization of local and spatial information for image classification. Specifically, we first exploit the pretrained DenseNet and fine-tuned it to release its potential in remote-sensing image feature representation. Second, a spatial-pyramid structure and an improved Fisher-vector coding strategy are leveraged to further strengthen representation capability and the robustness of the feature map captured from convolutional layers. Then we integrate an ensemble classifier in our network architecture considering that lower attention to feature descriptors. Extensive experiments are conducted, and the proposed method achieves superior performance on UC Merced, AID, and NWPU-RESISC45 data sets.

28 August 2020 in Complexity
Verified
Journal Article
Open access
PDF file
JLJinling Li
Jinling Li
QHQingshan Hou
Qingshan Hou
JXJinsheng Xing
Jinsheng Xing
Multiobject detection tasks in complex scenes have become an important research topic, which is the basis of other computer vision tasks. Considering the defects of the traditional single shot multibox detector (SSD) algorithm, such as poor small object detection effect, reliance on manual setting for default box generation, and insufficient semantic information of the low detection layer, the detection effect in complex scenes was not ideal. Aiming at the shortcomings of the SSD algorithm, an improved algorithm based on the adaptive default box mechanism (ADB) is proposed. The algorithm introduces the adaptive default box mechanism, which can improve the imbalance of positive and negative samples and avoid manually set default box super parameters. Experimental results show that, compared with the traditional SSD algorithm, the improved algorithm has a better detection effect and higher accuracy in complex scenes.

1 March 2021
Verified
Conference Paper
Closed access
JLJinling Li
Jinling Li
In order to solve the problems of the long existence of traditional visualization methods of educational resources and low user satisfaction, this paper studies a visualization method of educational resources based on intelligent classroom. The framework of intelligent classroom data analysis is designed, the data mining model of intelligent classroom education resources is constructed, and the mined resource data is integrated and processed. Based on the integration results of intelligent classroom education resource data, the data set is processed hierarchically according to the length of data encoding, and the visualization of education resource is realized by combining the time dimension of parallel coordinate system. The experimental results show that the maximum visualization time of educational resources in this method is only 3.56s, and the average user satisfaction score is 9.6. The visualization efficiency and user satisfaction of educational resources are both high.