Publications
-
A Pavement Crack Segmentation Method Based on Deformable Convolution and Enhance Perceive Net [read]
Multimedia Tools and Applications · Jun 1, 2024
Cracks in pavement roads serve as significant signals of the structural and operational state. Identifying and addressing these cracks promptly can enhance the lifespan of infrastructure, decrease fuel consumption by vehicles, and advance safety and ride comfort. Conventionally, inspections for infrastructure distress have been manually conducted by visually examining the pavement, which is time-consuming. Previous methods take too much effort into global information rather than detail and can not handle the crack and background area imbalance, thus the segmentation result is not accurate. This paper proposes a pavement crack segmentation method based on deformable convolution (DCN) and enhance perceive net(EPerNet). On one hand, we combine DCN with layer normalization and feed forwarding layer to generate high-level and low-level feature maps. On the other hand, considering crack segmentation mainly focus on detail, we developed a network called EPerNet, which can better perceive crack information. At last, since the crack area always occupies a relatively small partition of an image, we adopted the online hard example mining strategy during training. Experiment result has shown that our proposed network exhibits excellent performance and offers a practical method for effectively segmenting pavement cracks
-
Single Human Parsing Based on Visual Attention and Feature Enhancement [read]
Journal of Advanced Computational Intelligence and Intelligent Informatics · Mar 6, 2023
Human parsing is one of the basic tasks in the field of computer vision. It aims at assigning pixel-level semantic labels to each human body part. Single human parsing requires further associating semantic parts with each instance. Aiming at the problem that it is difficult to distinguish the body parts with similar local features, this paper proposes a single human parsing method based on the visual attention mechanism. The proposed algorithm integrates advanced semantic features, global context information, and edge information to obtain accurate results of single human parsing resolution. The proposed algorithm is validated on standard look into part (LIP) dataset, and the results prove the effectiveness of the proposed algorithm.
-
Reduced Reference Quality Assessment for Image Retargeting by Earth Mover’s Distance [read]
Applied Sciences · Oct 19, 2021
A reduced reference quality assessment algorithm for image retargeting by earth mover’s distance is proposed in this paper. In the reference image, all the feature points are extracted using scale invariant feature transform. Let the histograms of image patch around each feature point be local information, and the histograms of saliency feature as global information. Those feature information is extracted at the sender side and transmitted to the receiver side. After that, the same feature information extraction process is performed for the retargeted image at the receiver side. Finally, all feature information of the reference and retargeted images is used collectively to compute the quality of the retargeted image. An overall quality score is calculated from the local and global similarity measure using earth mover’s distance between reference and retargeted images. The key step in our algorithm is to provide an earth mover’s distance metric in a manner that indicates how the local and global information in the reference image is preserved in corresponding retargeted image. Experimental results show that the proposed algorithm can improve the image quality scores on four common criteria in the retargeted image quality assessment community.
Patents
-
A twin network single-target tracking method and device
CN 202310897743.2 · Filed Jul 20, 2023
-
Real-time semantic segmentation method, device, electronic device and storage medium for night image
CN 202310856554.0 · Filed Jul 12, 2023
-
Two non-reference image quality evaluation methods based on graph convolution and multi-scale features
CN 2023108015262 · Filed Jun 30, 2023
-
A method and system for estimating human posture based on shape similarity
CN 202210752411.0 · Filed Jun 30, 2022