shi furong

Dr. shi furong


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
6 August 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
SFshi furong
shi furong
TZTong Zhang
Tong Zhang
TZTao Zhang
Tao Zhang
Vehicle detection in aerial images is an important and challenging task in the field of remote sensing. Recently, deep learning technologies have yielded superior performance for object detection in remote sensing images. However, the detection results of the existing methods are horizontal bounding boxes that ignore vehicle orientations, thereby having limited applicability in scenes with dense vehicles or clutter backgrounds. In this article, we propose a one-stage, anchor-free detection approach to detect arbitrarily oriented vehicles in high-resolution aerial images. The vehicle detection task is transformed into a multitask learning problem by directly predicting high-level vehicle features via a fully convolutional network. That is, a classification subtask is created to look for vehicle central points and three regression subtasks are created to predict vehicle orientations, scales, and offsets of vehicle central points. First, coarse and fine feature maps outputted from different stages of a residual network are concatenated together by a feature pyramid fusion strategy. Upon the concatenated features, four convolutional layers are attached in parallel to predict high-level vehicle features. During training, task uncertainty learned from the training data is used to weight loss function in the multitask learning setting. For inferencing, oriented bounding boxes are generated using the predicted vehicle features, and oriented nonmaximum suppression (NMS) postprocessing is used to reduce redundant results. Experiments on two public aerial image data sets have shown the effectiveness of the proposed approach.

6 July 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SFshi furong
shi furong
TZTong Zhang
Tong Zhang
Deep-learning technologies, especially convolutional neural networks (CNNs), have achieved great success in building extraction from areal images. However, shape details are often lost during the down-sampling process, which results in discontinuous segmentation or inaccurate segmentation boundary. In order to compensate for the loss of shape information, two shape-related auxiliary tasks (i.e., boundary prediction and distance estimation) were jointly learned with building segmentation task in our proposed network. Meanwhile, two consistency constraint losses were designed based on the multi-task network to exploit the duality between the mask prediction and two shape-related information predictions. Specifically, an atrous spatial pyramid pooling (ASPP) module was appended to the top of the encoder of a U-shaped network to obtain multi-scale features. Based on the multi-scale features, one regression loss and two classification losses were used for predicting the distance-transform map, segmentation, and boundary. Two inter-task consistency-loss functions were constructed to ensure the consistency between distance maps and masks, and the consistency between masks and boundary maps. Experimental results on three public aerial image data sets showed that our method achieved superior performance over the recent state-of-the-art models.

5 September 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
SFshi furong
shi furong
TZTong Zhang
Tong Zhang
The mainstream instance segmentation in remote sensing images takes the way of “Detect then Segment.” Anchor-free detectors get rid of the predefined anchors and can be used for proposal generation. However, in the existing methods based on anchor-free detectors, incompact proposals are directly used for segmentation, which may result in incomplete mask segmentation. In addition, the commonly used mask segmentation module is based on the trimmed features, which is not sufficient for accurate mask segmentation due to the loss of spatial details. In this letter, an anchor-free network is proposed, for instance, segmentation in remote sensing images. In order to obtain more compact proposals, a box refinement module, which predicts the distance offsets of a pixel to four sides of a proposal, is designed for initial proposals generated by an anchor-free detector. Based on the refined proposals, a saliency supplement module is designed to obtain accurate instance-wise masks by embedding the saliency map into the coarse masks. Compared with other methods, the proposed method conducted on two remote sensing datasets achieves the optimal performance, with an average precision (AP) of 0.652 and 0.678.

1 October 2024 in Journal of Applied Remote Sensing
Verified
Journal Article
Closed access
PDF file
WLWentao Li
Wentao Li
HXHaixia Xu
Haixia Xu
SFshi furong
shi furong
LYLiming Yuan
Liming Yuan
SYSheng-Zhi Yang
Sheng-Zhi Yang
Synthetic aperture radar (SAR), which is an active microwave imaging sensor, is widely used in change detection, object detection, and for the monitoring of disasters. As electronic technology develops, many high-resolution and different bands of spaceborne SAR have been launched into space. Due to its all-day and all-weather imaging and its penetration characteristics, SAR has been widely used in ship detection characteristics.1,2

3 November 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
SFshi furong
shi furong
TZTao Zhang
Tao Zhang
ZGZan Gao
Zan Gao
FZFeifei Zhang
Feifei Zhang
XWXianbin Wen
Xianbin Wen
Vehicle detection in satellite videos is crucial for large-scale traffic monitoring and urban management, yet remains challenging due to the extremely small object size and limited appearance features. Existing methods generally focus on extracting spatiotemporal information at the local pixel level while neglecting the long-range dependencies between vehicle instances. This insufficient spatiotemporal feature aggregation limits the accuracy of detection. To address this issue, we propose a coarse-to-fine multi-level spatiotemporal attention network (MLSTA-Net) for detecting tiny vehicles in satellite videos. Specifically, a pixel-level spatiotemporal attention (PiSTA) module is introduced, which leverages motion priors to guide the aggregation of spatiotemporal features at the pixel level, thereby enhancing the fine-grained representation of targets and generating coarse vehicle detection results. Subsequently, an instance-level spatiotemporal attention (InSTA) module is developed to refine initial detections by modeling the spatial relationships of instances within a single frame and the temporal consistency of instances across multiple frames. Experiments on VISO and SAT-MTB datasets demonstrate that the MLSTA-Net method achieves superior performance over state-of-the-art object detection approaches.

1 January 2024 in Journal of Applied Remote Sensing
Verified
Journal Article
Closed access
PDF file
XLXiaoning Liu
Xiaoning Liu
SFshi furong
shi furong
HXHaixia Xu
Haixia Xu
LYLiming Yuan
Liming Yuan
SYSheng-Zhi Yang
Sheng-Zhi Yang
In recent years, methods based on convolutional neural networks (CNNs) have achieved significant results in the problem of target classification of synthetic aperture radar (SAR) images. However, the challenges of SAR image data labeling and the characteristics of CNNs relying on a large amount of labeled data for training have seriously limited the further development of this field. In this work, we propose an approach based on attention mechanism and feature complementary fusion (AFCF-CNN) to address these challenges. First, we design and construct a feature complementary module for extracting and fusing multi-layer features, making full use of limited data and utilizing contextual information between different layers to capture more robust feature representations. Then, the attention mechanism reduces the interference of redundant background information, while it highlights the weight information of key targets in the image to further enhance the key local feature representations. Finally, experiments conducted on the moving and stationary target acquisition and recognition dataset show that our model significantly outperforms other state-of-the-art methods despite severe shortages of training data.