检索结果-内蒙古大学图书馆

Moving Object Detection Method via ResNet-18 With encoder-decoder Structure in Complex Scenes

IEEE ACCESS 2019年 7卷 108152-108160页

作者： Ou, Xianfeng Yan, Pengcheng Zhang, Yiming Tu, Bing Zhang, Guoyun Wu, Jianhui Li, Wujing Hunan Inst Sci & Technol Sch Informat Sci & Engn Yueyang 414006 Peoples R China Hunan Inst Sci & Technol Machine Vis & Artificial Intelligence Res Ctr Yueyang 414006 Peoples R China

In complex scenes, dynamic background, illumination variation, and shadow are important factors, which make conventional moving object detection algorithms suffer from poor performance. To solve this problem, a moving object detection method via ResNet-18 with encoder-decoder structure is proposed to segment moving objects from complex scenes. ResNet-18 with encoder-decoder structure possesses pixel-level classification capability to divide pixels into foreground and background, and it performs well in feature extraction because of its layers are so shallow that many more low-scale features will be retained. First, the object frames and their corresponding artificial labels are input to the network. Then, feature vectors will be generated by the encoder, and they are converted into segmentation maps by the decoder through deconvolution processing. Third, a rough matching of the moving object regions will be obtained, and finally, the Euclidean distance is used to match the moving object regions accurately. The proposed method is suitable for the scenes where dynamic background, illumination variation, and shadow exist, and experimental results on the public standard CDnet2014 and I2R datasets, from both qualitative and quantitative comparison aspects, demonstrate that the proposed method outperforms state-of-the-art algorithms significantly, and its mean F-measure increased by 1.99%similar to 29.17%.

关键词： Complex scenes moving object detection ResNet-18 encoder-decoder network background subtraction

来源：评论

学校读者我要写书评

暂无评论

RGB-T salient object detection via CNN feature and result saliency map fusion

引用

APPLIED INTELLIGENCE 2022年第10期52卷 11343-11362页

作者： Xu, Chang Li, Qingwu Zhou, Mingyu Zhou, Qingkai Zhou, Yaqin Ma, Yunpeng Hohai Univ Coll Internet Things Engn Changzhou 213022 Jiangsu Peoples R China

Thermal infrared sensors have unique advantages under the conditions of insufficient illumination, complex scenarios, or occluded appearances. RGB-T salient object detection methods integrate the complementary advantages of visual and thermal modalities to capture salient objects more accurately. Considering the characteristics of visual and thermal images, we combine CNN feature and result saliency map fusion methods to achieve RGB-T salient object detection. First, a two-stream encoder-decoder network is proposed to handle the different saliency cues within RGB-T images. Specifically, the global attention module introduces the complementary saliency cues within thermal images to visual images, thereby ensuring the consistency of salient object locations. Subsequently, the two-stream decoder module gradually fuses the high-level salient object location cues with low-level detail saliency cues to obtain single-modality saliency maps. Then, saliency maps are fused and refined by the proposed result saliency map fusion method to achieve the final saliency map with high precision. In this way, the salient object is segmented with the fine boundary, and the noise inside the salient object is effectively suppressed. Experimental results demonstrate the effectiveness of each component within the CNN feature and result saliency map fusion methods. The proposed method facilitates desirable complementation for RGB-T images and performs favorably against state-of-the-art methods, especially in the challenges of low illumination, cluttered background, and low contrast.

关键词： RGB-T salient object detection CNN attention module encoder-decoder network Result fusion Bezier interpolation

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Symmetric Convolutional Neural network for Video Bit-Depth Enhancement

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2019年第9期21卷 2397-2406页

作者： Liu, Jing Liu, Pingping Su, Yuting Jing, Peiguang Yang, Xiaokang Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai 200240 Peoples R China

In contrast to the high sensitivity of human eyes and rapid development of modern display devices in terms of dynamic range, mainstream multimedia sources are generally at relatively lower hit depths (BDs). Therefore, BD enhancement (BDE), which attempts to transform low-BD multimedia sources into high-BD sources, is considered of significant research value. Current BDE algorithms are based on images rather than videos. However, for massive numbers of videos, temporal continuity among frames should be considered. Thus, in this paper, we propose a spatiotemporal symmetric BDE network for videos based on an encoder-decoder network. Consecutive frames are input into five subnets in the encoder, where the convolutional filters in the temporal symmetric subnets share the same weights to achieve lower model complexity. In addition, symmetric skip connections are introduced between the symmetric convolutionat/deconvolutional layers of the encoder/decoder to pass features and alleviate the gradient diffusion problem. The experimental results show that our model can efficiently eliminate false contours and chroma distortions. The model significantly outperforms state-of-the-art image BDE algorithms and single-frame baseline models in terms of PSNR and SSIM.

关键词： Video bit-depth enhancement encoder-decoder network spatiotemporal symmetry convolutional neural networks feature fusion

来源：评论

学校读者我要写书评

暂无评论

Zero-reference single underwater image enhancement

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第30期82卷 46423-46438页

作者： Yang, Aiping Wang, Chaochen Wang, Jinbin Wang, Qian Zhang, Tengfei Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Shanghai Artificial Intelligence Lab Shanghai Peoples R China

Underwater images play an essential role in acquiring and analyzing underwater information. Autonomous Underwater Vehicles (AUVs) highly rely on the quality of the captured underwater images, in order to carry out several activities. Due to the poor lighting conditions and the limited capacity of the optical imaging device, captured underwater images usually contain severe color distortions and contrast reduction. To this end, most existing deep learning-based underwater image enhancement methods synthesize the pseudo ground-truth, or employ the in-air clear images as references to train the models. However, the synthesized or selected reference images are generally unsatisfying due to the lack of diversity and applicability. This paper presents a novel underwater image enhancement approach based on training an end-to-end underwater image enhancement network, without using any reference image. A novel encoder-decoder network structure and a set of non-reference loss functions are designed to measure the enhancement quality. The subjective and objective evaluations show that the proposed algorithm outperforms the state-of-the-art approaches.

关键词： Underwater image enhancement Zero reference encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Leveraging Bounding Box Annotations for Fish Segmentation in Underwater Images

引用

IEEE ACCESS 2023年 11卷 125984-125994页

作者： Sanchez, Josep S. Lisani, Jose-Luis Catalan, Ignacio A. Alvarez-Ellacuria, Amaya Univ Illes Balears Ciencies Matematiques & Informat Palma De Mallorca 07122 Spain UIB CSIC IMEDEA Esporles 07190 Spain

The use of Deep learning techniques in the field of Marine Science has become popular in recent years. For instance, many works propose the application of instance segmentation neural networks (in particular, Mask R-CNN) for detection and classification of fish in underwater images. The performance of these learning-based approaches depends heavily on the volume of data used for training, which, in the case of instance segmentation models for fish detection, implies that human experts must label and mark the shapes of all the fish appearing in a vast amount of underwater images. This is an enormously time-consuming task that we seek to alleviate in this paper. We propose a training strategy that combines manual and semi-automatic annotations. The latter are obtained in a weakly-supervised manner: the bounding box that contains the fish is manually selected, but its shape is automatically obtained thanks to a pretrained encoder-decoder segmentation network. Several popular architectures for this encoder-decoder network are examined. This strategy permits to reduce drastically the annotation cost for instance segmentation, at the expense of a small drop in performance with respect to the use of fully manual annotations. We show that a balance can be achieved between the segmentation performance and the time used to collect the training data by using the proposed strategy.

关键词： Deep learning fish analysis instance segmentation bounding box weakly-supervised learning encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Feature transfer based adversarial domain adaptation method for cross-domain road extraction

引用

GEOCARTO INTERNATIONAL 2022年第2期37卷 445-455页

作者： Wang, Shuyang Mu, Xiaodong He, Hao Yang, Dongfang Zhao, Peng Xian Hitech Res Inst Dept Informat Engn Xian Peoples R China Xian Hitech Res Inst Dept Control Engn Xian Peoples R China

In order to improve the cross-domain applicability of road segmentation, a feature transfer based adversarial domain adaptation method is presented for cross-domain road extraction. The presented method consists of two main parts, a feature transfer network and an adversarial domain adaption network. The feature transfer network transforms the images of the source domain into the feature space of the target domain. The adversarial domain adaption network learns to distinguish whether the results come from source domain or target domain, to promote the backbone network of road extraction to learn the common features of the road. The experimental results showed that the proposed method improved the generalization ability of the road extraction network and could extract the road target from cross-domain images accurately and effectively. The proposed method can realize the road extraction across domain without any annotation of target domain, so it has good application value.

关键词： Road extraction transfer learning domain adaption generative adversarial network encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Research on Efficient Asymmetric Attention Module for Real-Time Semantic Segmentation networks in Urban Scenes

引用

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS 2024年第3期28卷 562-572页

作者： Su, Xu Li, Lihong Xiao, Jiejie Wang, Pengtao Hebei Univ Engn Sch Informat & Elect Engn 19 Taiji Rd Handan 056038 Hebei Peoples R China Hebei Key Lab Secur & Protect Informat Sensing & P 19 Taiji Rd Handan 056038 Hebei Peoples R China

Currently, numerous high-precision models have been proposed for semantic segmentation, but the model parameters are large and the segmentation speed is slow. Real-time semantic segmentation for urban scenes necessitates a balance between accuracy, inference speed, and model size. In this paper, we present an efficient solution to this challenge, efficient asymmetric attention module net (EAAMNet) for the semantic segmentation of urban scenes, which adopts an asymmetric encoder-decoder structure. The encoder part of the network utilizes an efficient asymmetric attention module to form the network backbone. In the decoding part, we propose a lightweight multi-feature fusion decoder that can maintain good segmentation accuracy with a small number of parameters. Our extensive evaluations demonstrate that EAAMNet achieves a favorable equilibrium between segmentation efficiency, model parameters, and segmentation accuracy, rendering it highly suitable for real-time semantic segmen69.32% mIoU at 141 fps on CamVid without any prealso enhances accuracy and increases speed.

关键词： semantic segmentation real-time convolutional neural network encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention 17

Improving Attention-Based Handwritten Mathematical Expressio...

引用

17th International Conference on Frontiers in Handwriting Recognition (ICFHR)

作者： Li, Zhe Jin, Lianwen Lai, Songxuan Zhu, Yecheng South China Univ Technol Sch Elect & Informat Engn Guangzhou Peoples R China

ISBN: (纸本)9781728199665

Handwritten mathematical expression recognition (HMER) is an important research direction in handwriting recognition. The performance of HMER suffers from the two-dimensional structure of mathematical expressions (MEs). To address this issue, in this paper, we propose a high-performance HMER model with scale augmentation and drop attention. Specifically, tackling ME with unstable scale in both horizontal and vertical directions, scale augmentation improves the performance of the model on MEs of various scales. An attention-based encoder-decoder network is used for extracting features and generating predictions. In addition, drop attention is proposed to further improve performance when the attention distribution of the decoder is not precise. Compared with previous methods, our method achieves state-of-the-art performance on two public datasets of CROHME 2014 and CROHME 2016.

关键词： handwritten mathematical expression recognition data augmentation encoder-decoder network attention mechanism

来源：评论

学校读者我要写书评

暂无评论

INTERFERENCE SUPPRESSION FOR SAR IMAGE BASED ON JOINT SUPERVISION EN-decoder network

INTERFERENCE SUPPRESSION FOR SAR IMAGE BASED ON JOINT SUPERV...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Zhang, Hao Wei, Shunjun Zhou, Zichen Shi, Jun Zhang, Xiaoling Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

SAR is usually subject to strong electromagnetic interference (EMI) during electronic reconnaissance missions, which will seriously weaken its ability of surveying and mapping. This paper presents a novel method for SAR image interference suppression based on the encoder-decoder network (named as ISEDnet). ISEDnet mainly consists of consecutive feature extraction net (FEN), the additional encoder-decoder network, and the image supervision mechanism. FEN is used to extract the features of interfered SAR images, and the encoder-decoder network (EDN) is used to suppress interference of SAR images. The image supervision mechanism is proposed to recover the target features. The network trained with simulation and real measurement data, the effectiveness of ISEDnet are verified by both simulation and the Sentinel-1 satellite SAR images. Compared to the traditional notch filtering method, ISEDnet can successfully suppress different types of SAR interference and improve interference suppression performance.

关键词： Synthetic aperture radar interference suppression encoder-decoder network Sentinel-1 satellite

来源：评论

学校读者我要写书评

暂无评论

Generating Adversarial Examples with Image-To-Perturbation network 39

Generating Adversarial Examples with Image-To-Perturbation N...

引用

39th Chinese Control Conference (CCC)

作者： Wang, Desheng Jin, Weidong Wu, Yunpu Southwest Jiaotong Univ Sch Elect Engn Chengdu 611756 Peoples R China

ISBN: (纸本)9789881563903

Deep neural networks have been found to be easily misled by adversarial examples that are maliciously crafted by adding small perturbations. A variety of methods have been proposed to generate adversarial examples, but more efforts are needed to generate them with high perceptual quality and low computation costs. In this paper, we propose an adversarial attack method that uses a conditional encoder-decoder network named Image-To-Perturbation to generate adversarial perturbations in residual learning fashion. Image-To-Perturbation network can learn the mapping from clean images to according adversarial perturbations, once it is trained, it can generate perturbations for any examples efficiently. We test the proposed method on different target models using MNIST and CIFAR-10 datasets. The experimental results show that our model is easy to train and the generated adversarial examples are perceptually realistic and achieve high attack success rate.

关键词： Deep Neural networks Adversarial Examples encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：