Dongli Wang

Dr. Dongli Wang


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
27 April 2022 in Sensors
Verified
Journal Article
Open access
PDF file
YZYan ZHOU
Yan ZHOU
SWSijie Wen
Sijie Wen
DWDongli Wang
Dongli Wang
JMJiangnan Meng
Jiangnan Meng
JMjinzhen mu
jinzhen mu
RIRichard Irampaye
Richard Irampaye
Object detection is one of the key tasks in an automatic driving system. Aiming to solve the problem of object detection, which cannot meet the detection speed and detection accuracy at the same time, a real-time object detection algorithm (MobileYOLO) is proposed based on YOLOv4. Firstly, the feature extraction network is replaced by introducing the MobileNetv2 network to reduce the number of model parameters; then, part of the standard convolution is replaced by depthwise separable convolution in PAnet and the head network to further reduce the number of model parameters. Finally, by introducing an improved lightweight channel attention modul—Efficient Channel Attention (ECA)—to improve the feature expression ability during feature fusion. The Single-Stage Headless (SSH) context module is introduced to the small object detection branch to increase the receptive field. The experimental results show that the improved algorithm has an accuracy rate of 90.7% on the KITTI data set. Compared with YOLOv4, the parameters of the proposed MobileYOLO model are reduced by 52.11 M, the model size is reduced to one-fifth, and the detection speed is increased by 70%.

29 December 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
XZXiaolin Zhu
Xiaolin Zhu
YZYan ZHOU
Yan ZHOU
DWDongli Wang
Dongli Wang
WOWanli Ouyang
Wanli Ouyang
RSRui Su
Rui Su
Group activity recognition, which aims to simultaneously understand individual action and group activity in video clips, plays a fundamental role in computer vision and video analysis. In this paper, we propose a novel relational inference framework, termed MLST-Former, for individual action and group activity recognition, capturing the various degrees of spatial-temporal dynamic interactions adaptively and jointly among actors and generating reasonable group representations. Specifically, we first design a multi-level spatial-temporal Transformer to capture the miscellaneous actors’ spatial-temporal contextual information to deal with unbalanced interactions between actors. Furthermore, our proposed network is capable of fully mining long-range spatial-temporal dependencies with the virtue of the merge function and cross attention mechanism. We then propose an inter-frame gating fusion mechanism (IGFM) to selectively aggregate the temporal and structural features of the interacting actors. A new multi-task learning strategy, consisting of the classification cost of individual actions and group activities, is also developed. Moreover, we adopt the motion trajectory branch to provide complementary dynamic features for improving recognition performance. A series of ablation studies demonstrate the effectiveness and respective contributions of the different components within the proposed method. Extensive experiments on four public GAR datasets clearly show that our approach can achieve very competitive performance by comparing them with state-of-the-art methods.

8 December 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YZYan ZHOU
Yan ZHOU
SWSijie Wen
Sijie Wen
DWDongli Wang
Dongli Wang
JMjinzhen mu
jinzhen mu
IRIrampaye Richard
Irampaye Richard
Object detection is one of the key algorithms in automatic driving systems. Aiming at addressing the problem of false detection and the missed detection of both small and occluded objects in automatic driving scenarios, an improved Faster-RCNN object detection algorithm is proposed. First, deformable convolution and a spatial attention mechanism are used to improve the ResNet-50 backbone network to enhance the feature extraction of small objects; then, an improved feature pyramid structure is introduced to reduce the loss of features in the fusion process. Three cascade detectors are introduced to solve the problem of IOU (Intersection-Over-Union) threshold mismatch, and side-aware boundary localization is applied for frame regression. Finally, Soft-NMS (Soft Non-maximum Suppression) is used to remove bounding boxes to obtain the best results. The experimental results show that the improved Faster-RCNN can better detect small objects and occluded objects, and its accuracy is 7.7% and 4.1% respectively higher than that of the baseline in the eight categories selected from the COCO2017 and BDD100k data sets.

13 June 2022 in Sensors
Verified
Journal Article
Open access
PDF file
DWDongli Wang
Dongli Wang
SXShengliang Xiang
Shengliang Xiang
YZYan ZHOU
Yan ZHOU
JMJinzhen Mu
Jinzhen Mu
HZHaibin Zhou
Haibin Zhou
RIRichard Irampaye
Richard Irampaye
Contextual information and the dependencies between dimensions is vital in image semantic segmentation. In this paper, we propose a multiple-attention mechanism network (MANet) for semantic segmentation in a very effective and efficient way. Concretely, the contributions are as follows: (1) a novel dual-attention mechanism for capturing feature dependencies in spatial and channel dimensions, where the adjacent position attention captures the dependencies between pixels well; (2) a new cross-dimensional interactive attention feature fusion module, which strengthens the fusion of fine location structure information in low-level features and category semantic information in high-level features. We conduct extensive experiments on semantic segmentation benchmarks including PASCAL VOC 2012 and Cityscapes datasets. Our MANet achieves the mIoU scores of 75.5% and 72.8% on PASCAL VOC 2012 and Cityscapes datasets, respectively. The effectiveness of the network is higher than the previous popular semantic segmentation networks under the same conditions.

29 July 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XZXiaolin Zhu
Xiaolin Zhu
DWDongli Wang
Dongli Wang
JLJianxun Li
Jianxun Li
RSRui Su
Rui Su
QWQin Wan
Qin Wan
YZYan ZHOU
Yan ZHOU
Recently, group activity recognition (GAR) has drawn growing interests in video analysis and computer vision communities. The current models of GAR tasks are often impractical in that they suppose that all interactions between actors are pairwise, which only models and leverages part of the information in real entire interactions. Motivated by this, we design a distinct dynamical attention hypergraph convolutional network framework, referred to as DAHGCN, for precise GAR, modeling the entire interactions and capturing the high-order relationships among involved actors in a real-life scenario. Specifically, to learn complementary feature representations for fine-grained GAR, a multilevel feature descriptor (MLFD) module is proposed. Furthermore, for learning higher order interaction relationships, we construct a DAHGCN to accommodate complex group interactions, which can dynamically change the topology of the hypergraph and learn these key representations by virtue of the “similarity-based shared nearest-neighbor (SSNN) clustering” and “attention mechanisms” on hypergraph. Finally, a multiscale temporal convolution (MSTC) module is utilized to explore various long-range temporal dynamic correlations across different frames. In addition, comprehensive experiments on three commonly used GAR datasets clearly demonstrate that, when compared with the state-of-the-art methods, our proposed method can achieve the most optimal performance.

1 September 2015 in IET Communications
Verified
Journal Article
Open access
PDF file
DWDongli Wang
Dongli Wang
YZYan Zhou
Yan Zhou
YWYanhua Wei
Yanhua Wei
TPTingrui Pei
Tingrui Pei
Recent growing interest for location‐based services has created a demand on object localisation approaches with low cost and high accuracy. In this study, the problem of distributed multi‐object localisation using fingerprints of received signal strength (RSS) is addressed by combining average consensus and compressed sensing. First, Bayesian compressed sensing is employed at each agent to recover the sparse index vector from RSS measurements, which are corrupted by noises. It relaxes the requirement on accurate prior position knowledge of beacon nodes and is applicable in non‐line‐of‐sight conditions. Then, average consensus is adopted to compel all agents to reach an agreement on the index vector, and in turn, on the location of objects. By using only one‐hop neighbours’ information, the proposed distributed localisation method is applicable to large‐scale networks. Moreover, the final location of each object is obtainable from each individual agent, which makes the proposed method flexible to the network administration. Experimental results are included to demonstrate the effectiveness of the proposed method.