检索结果-内蒙古大学图书馆

IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS)

作者： Wang, Yong Li, Ling Yang, Xin Wang, Xinxin Liu, Hui Army Engn Univ PLA Field Engn Coll Nanjing Peoples R China Army Engn Univ PLA Grad Sch Nanjing Peoples R China

ISBN: (纸本)9781728165905

camouflaged object detection is a hard assignment due to their textures are similar to the background. The main intention of this paper is probe into a problem about the camouflaged object detection, that is, detecting its camouflaged object for a given image. This problem has not been well studied in spite of a large area of potential applications such as camouflage military targets detection and wildlife protection. To address this problem, a camouflage object detection method based on deep learning is proposed. The suggested method can detect camouflaged object which can extract deep features automatically. It can also provide detection probability which reflect camouflage efficiency. Experimental results show that the deep learning measure can effectively detect different scene, representing the camouflage level of low, medium and high respectively.

关键词： camouflaged object detection features extraction Deep Learning

来源：评论

学校读者我要写书评

暂无评论

CoNet: A Consistency-Oriented Network for camouflaged object Segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第1期35卷 287-299页

作者： Wu, Fei Yin, Jun Li, Xiaochuan Wu, Jianfeng Jin, Da Yang, Jiamin Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310058 Peoples R China Zhejiang Univ Polytech Inst Zhejiang Hangzhou 310058 Peoples R China Dahua Technol Co Ltd Hangzhou 310053 Peoples R China Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310058 Peoples R China

camouflaged object segmentation (COS) is a recently emerging task due to its broad application prospect. The coloration and texture similarities between the objects and their surroundings makes it a challenging task. Motivated by this, we propose a consistency-oriented network (CoNet) to address these challenges by looking into the visual consistencies between object and background. Specifically, we design a primary detection module (PDM) to firstly locate the object by fusing the backbone features. A filter is introduced to better focus on the object's foreground feature based on its primary location. To obtain the visual consistency between the object and background, the foreground feature is then fed into the consistency evaluation module (CEM) to interact with the global feature. Both features are simultaneously processed by a shared discriminator and then fused together to attain the consistency attention map. The final feature refinement is conducted in the detail refinement module (DRM) by merging the consistency attention map with the global features via hierarchical feature fusion. Extensive experiments on benchmark COS datasets show that the proposed CoNet outperforms the state-of-the-art (SOTA) models in most cases. Ablation experiments verify the effectiveness of different backbones, designed modules and upsampling methods. Furthermore, extra studies on the labelling techniques and interdisciplinary applications demonstrate the great potential of the proposed CoNet.

关键词： Feature extraction Visualization object segmentation object detection Estimation object recognition Image resolution camouflaged object detection camouflaged object segmentation consistency-oriented global-foreground consistency

来源：评论

学校读者我要写书评

暂无评论

Research on camouflaged object Segmentation Based on Feature Fusion and Attention Mechanism

引用

IET IMAGE PROCESSING 2025年第1期19卷

作者： Wang, Yixuan Yan, Jingke City Univ Civil Engn Hong Kong Peoples R China Southwest Jiaotong Univ State Key Lab Rail Transit Vehicle Syst Chengdu Si Chuan Peoples R China

camouflaged object detection (COD) aims to detect objects that 'blend in' with their surroundings and the lack of a clear boundary between the target object and the background in COD tasks makes accurate detection of targets difficult. Although many innovative algorithms and methods have been developed to improve the results of camouflaged object detection, the problem of poor detection accuracy in complex scenes still exists. To improve the accuracy of camouflage target segmentation, a camouflaged object detection algorithm using contextual feature enhancement and an attention mechanism called amplify and predict network (APNet) is proposed. In this paper, context feature enhancement module (CFEM) and reverse attention prediction module (RAPM) are *** can accept multi-level features extracted from the backbone network, and convey the features with enhancement processing to achieve the fusion of multi-level *** focuses on the edge feature information through the reverse attention mechanism to mine deeper camouflaged target information to achieve and further refine the predicted results. The proposed algorithm achieves weighted F-measure and mean absolute error (MAE) of 0.708 and 0.033 on the COD10K dataset, respectively, and the experimental results on other publicly available datasets are also significantly better than the other 14 state-of-the-art models, and achieves the optimal performance on the four objective evaluation metrics, and the proposed algorithm obtains sharper edge details on COD tasks and improves the prediction performance.

关键词： attention mechanism camouflaged object detection feature fusion reverse attention

来源：评论

学校读者我要写书评

暂无评论

EDCAANet: A lightweight COD network based on edge detection and coordinate attention assistance

引用

IMAGE AND VISION COMPUTING 2025年 154卷

作者： Pan, Qing Feng, Xiayuan Tian, Nili Guangdong Univ Technol Sch Informat Engn Guangzhou Peoples R China

In order to obtain the higher efficiency and the more accuracy in camouflaged object detection (COD), a lightweight COD network based on edge detection and coordinate attention assistance (EDCAANet) is presented in this paper. Firstly, an Integrated Edge and Global Context Information Module (IEGC) is proposed, which uses edge detection as an auxiliary means to collaborate with the atrous spatial convolution pooling pyramid (ASPP) for obtaining global context information to achieve the preliminary positioning of the camouflaged object. Then, the Receptive Field Module based on Coordinate Attention (RFMC) is put forward, in which the Coordinate Attention (CA) mechanism is employed as another aid means to expand receptive ffeld features and then achieve global comprehensive of the image. In the final stage of feature fusion, the proposed lightweight Adjacent and Global Context Focusing module (AGCF) is employed to aggregate the multi-scale semantic features output by RFMC at adjacent levels and the global context features output by IEGC. These aggregated features are mainly refined by the proposed Multi Scale Convolutional Aggregation (MSDA) blocks in the module, allowing features to interact and combine at various scales to ultimately produce prediction results. The experiments include performance comparison experiment, testing in complex background, generalization experiment, as well as ablation experiment and complexity analysis. Four public datasets are adopted for experiments, four recognized COD metrics are employed for performance evaluation, 3 backbone networks and 18 methods are used for comparison. The experimental results show that the proposed method can obtain both the more excellent detection performance and the higher efficiency.

关键词： camouflaged object detection Deep learning Attention mechanism Edge detection Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Depth-Guided Texture Diffusion for Image Semantic Segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第2期35卷 1287-1302页

作者： Sun, Wei Li, Yuan Ye, Qixiang Jiao, Jianbin Zhou, Yanzhao Univ Chinese Acad Sci UCAS Sch Elect Elect & Commun Engn Beijing 101408 Peoples R China Univ Chinese Acad Sci UCAS Sch Emergency Management Sci & Engn Beijing 101408 Peoples R China

Depth information provides valuable insights into the 3D structure, especially the outline of objects, which can be utilized to enhance semantic segmentation. However, a naive fusion of depth information can disrupt features and compromise accuracy due to the gap between depth and RGB modalities. In this work, we introduce a depth-guided texture diffusion approach that effectively tackles the outlined challenge. Our method extracts low-level features from edges and textures to create a texture image. This image is then selectively diffused across the depth map, enhancing structural information vital for precisely extracting object outlines. By integrating this enhanced depth map with the original RGB image into a joint feature embedding, our method effectively bridges the disparity between depth and RGB modalities, enabling more accurate semantic segmentation. We conduct comprehensive experiments on diverse, widely-used datasets covering various semantic segmentation tasks, including camouflaged object detection (COD), Salient object detection (SOD), and indoor semantic segmentation. With source-free estimated depth or depth captured by depth cameras, our method consistently outperforms existing baselines and achieves new state-of-the-art results, demonstrating the effectiveness of our depth-guided texture diffusion for image semantic segmentation. The source code and datasets are publicly available at https://***/Wistzz/***.

关键词： Feature extraction object detection Semantic segmentation Semantics Accuracy Visualization Data mining Circuits and systems Three-dimensional displays Image color analysis RGB-D SOD indoor semantic segmentation camouflaged object detection texture learning

来源：评论

学校读者我要写书评

暂无评论

Hunt camouflaged objects via Revealing Mutation Regions

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 1836-1851页

作者： Zhang, Xinyue Zhou, Jiahuan Yan, Luxin Zhong, Sheng Zou, Xu Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Natl Key Lab Multispectral Informat Intelligent Pr Wuhan 430072 Peoples R China Peking Univ Wangxuan Inst Comp Technol Beijing 100871 Peoples R China

Due to the high similarity between hidden objects and the surrounding background, camouflaged object detection (COD) remains a challenge. While many recently proposed methods have shown remarkable performance, most of them begin object perception by indiscriminately considering every pixel of the image. However, these early-stage region-insensitive perception methods still struggle to resist background interference, potentially missing subtle pixel changes by not prioritizing potential camouflaged areas initially. Fortunately, we reveal that the availability of an accurate mutation map can significantly enhance camouflaged discrimination ability. To this end, we propose MRNet (Mutation Region Network). MRNet initially generates a mutation map that identifies potential mutation regions exhibiting subtle pixel changes. The generation method involves amplifying and differing pixel changes based on the position and corresponding values of pixels. Subsequently, the selective expansion search operation utilizes the mutation map to extract the mapped graph, effectively reducing interference from background pixels that are distant from the mutation regions. Finally, decoding the mapped graph generates precise masks. Furthermore, we have created the largest test dataset with known categories to advance community research. Extensive experiments conducted on three widely used datasets and our proposed dataset show that MRNet surpasses other methods with superior performance.

关键词： Feature extraction Image edge detection Transformers Search problems Interference Image segmentation Data mining Convolution Training object recognition camouflaged object detection mutation map selective expansion search operation

来源：评论

学校读者我要写书评

暂无评论

Exploration, fusion, and refinement: a multivariate features interaction network for visual camouflaged detection

引用

VISUAL COMPUTER 2025年第6期41卷 4253-4267页

作者： Huang, Zhen Zhu, Yongjian Zhang, Qiao Zang, Hongyan Lei, Tengfei Qilu Inst Technol Sch Comp & Informat Engn Jinan 250200 Peoples R China Shenzhen Technol Univ Sch Engn Phys Shenzhen 518118 Peoples R China China Univ Petr East China Sch Comp Sci & Technol Qingdao 266580 Peoples R China

camouflaged object detection (COD) aims to find objects hidden in the surrounding environment. camouflaged objects are usually fused with the background and have high intrinsic similarity, and the sizes and appearances of camouflaged objects vary, causing most previous single-stage methods to fail. To this end, we propose a multivariate feature interaction network (MFINet) based on a multistage design. Specifically, the MFINet consists of three stages: a feature exploration stage, a feature fusion stage, and a feature refinement stage. In the feature exploration phase, we design three key components: a global information exploration unit (GIEU), a spatial information exploration unit (SIEU), and a multi-scale exploration unit (MEU). The GIEU locates the position of the camouflaged object by integrating the global contextual information. The SIEU aggregates effective spatial information. The MEU explores the rich multi-scale information. In the feature fusion stage, we design a multielement feature fusion module to integrate the consistency and complementarity of multi-scale features to fully explore the valuable clues in the context by exploiting the global semantics and spatial details. In the feature refinement phase, we design a cross-layer consistency refinement module to facilitate information transfer between neighboring layers and refine camouflage features by mutual guidance of low-level and high-level features. The proposed MFINet is evaluated on four challenging COD benchmark datasets (i.e., CAMO, CHAMELEON, COD10K, and NC4K) using four widely used metrics. These evaluations demonstrate that our proposed method is superior to other existing cutting-edge methods for camouflaged object detection. The code will be released at https://***/ZYJ9224/MFINet.

关键词： Deep learning camouflaged object detection Multivariate Exploration Fusion Refinement

来源：评论

学校读者我要写书评

暂无评论

IdeNet: Making Neural Network Identify camouflaged objects Like Creatures

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 4824-4839页

作者： Guan, Juwei Fang, Xiaolin Zhu, Tongxin Cai, Zhipeng Ling, Zhen Yang, Ming Luo, Junzhou Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 211189 Peoples R China Georgia State Univ Dept Comp Sci Atlanta GA 30303 USA

camouflaged objects often blend in with their surroundings, making the perception of a camouflaged object a more complex procedure. However, most neural-network-based methods that simulate the visual information processing pathway of creatures only roughly define the general process, which deficiently reproduces the process of identifying camouflaged objects. How to make modeled neural networks perceive camouflaged objects as effectively as creatures is a significant topic that deserves further consideration. After meticulous analysis of biological visual information processing, we propose an end-to-end prudent and comprehensive neural network, termed IdeNet, to model the critical information processing. Specifically, IdeNet divides the entire perception process into five stages: information collection, information augmentation, information filtering, information localization, and information correction and object identification. In addition, we design tailored visual information processing mechanisms for each stage, including the information augmentation module (IAM), the information filtering module (IFM), the information localization module (ILM), and the information correction module (ICM), to model the critical visual information processing and establish the inextricable association of biological behavior and visual information processing. The extensive experiments show that IdeNet outperforms state-of-the-art methods in all benchmarks, demonstrating the effectiveness of the five-stage partitioning of visual information processing pathway and the tailored visual information processing mechanisms for camouflaged object detection. Our code is publicly available at: https://***/whyandbecause/IdeNet.

关键词： Visualization Information processing Feature extraction Location awareness Biological information theory object detection Convolution camouflaged object detection information augmentation information filtering information localization information correction

来源：评论

学校读者我要写书评

暂无评论

Boundary-Sensitive Segmentation of Small Liver Lesions

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第5期28卷 2991-3002页

作者： Wei, Tao Wang, Yiqi Zhang, Yuqiang Wang, Yunfu Zhao, Liang Guangxi Univ Sch Comp & Elect Informat Nanning Peoples R China Hubei Univ Med Taihe Hospita l Shiyan 442000 Peoples R China Hubei Univ Med Taihe Hosp Hubei Key Lab Embryon Stem Cell Res Shiyan 442000 Peoples R China Hubei Univ Med Taihe Hosp Hubei Prov Clin Res Ctr Precise Diag & Treatment L Hubei Key Lab Embryon Stem Cell Res Shiyan 442000 Peoples R China Guangxi Univ Sch Comp & Elect Informat Nanning 530004 Peoples R China

Early diagnosis plays a pivotal role in handling the global health challenge posed by liver diseases. However, early-stage lesions are typically quite small, presenting significant difficulties due to insufficient regions for developing effective features, indistinguishable boundaries of small lesions, and a lack of tiny liver lesion masks. To address these issues, we approach the solution in two-fold: an efficient model and a high-quality dataset. The model is built upon the advantages of path signature and camouflaged object detection. The path signature narrows down the ambiguous boundaries between lesions and other tissues while the camouflaged object detection achieves high accuracy in detecting inconspicuous lesions. The two are seamlessly integrated to ensure high accuracy and fidelity. For the dataset, we collect more than ten thousand liver images with over four thousand lesions, approximately half of which are small. Experiments on both an established dataset and our newly constructed one show that the proposed model outperforms state-of-the-art semantic segmentation and camouflaged object detection models, particularly in detecting small lesions. Moreover, the decisive and faithful salience maps generated by the model at the boundary regions demonstrate its strong robustness.

关键词： Liver lesion segmentation path signature camouflaged object detection

来源：评论

学校读者我要写书评

暂无评论

Detecting camouflaged objects via Multi-Stage Coarse-to-Fine Refinement

引用

IEEE ACCESS 2024年 12卷 44055-44068页

作者： Wang, Yuye Chen, Tianyou Hu, Xiaoguang Shi, Jiaqi Jia, Zichong Minnan Normal Univ Coll Phys & Informat Engn Zhangzhou 363000 Fujian Peoples R China Cent China Normal Univ Fac Artificial Intelligence Educ Wuhan 430079 Hubei Peoples R China Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China

camouflaged objects are typically assimilated into their surroundings. Consequently, in contrast to generic object detection/segmentation, camouflaged object detection proves to be considerably more intricate due to the indistinct boundaries and heightened intrinsic similarities between foreground targets and the surrounding environment. Despite the proposition of numerous algorithms that have demonstrated commendable performance across various scenarios, these approaches may still grapple with blurred boundaries, leading to the inadvertent omission of camouflaged targets in challenging scenes. In this paper, we introduce a multi-stage framework tailored for segmenting camouflaged objects through a process of coarse-to-fine refinement. Specifically, our network encompasses three distinct decoders, each fulfilling a unique role in the model. In the initial decoder, we introduce the Bi-directional Locating Module to excavate foreground and background cues, enhancing target localization. The second decoder focuses on leveraging boundary information to augment overall performance, incorporating the Multi-level Feature Fusion Module to generate prediction maps with finer boundaries. Subsequently, the third decoder introduces the Mask-guided Fusion Module, designed to process high-resolution features under the guidance of the second decoder's results. This approach enables the preservation of structural details and the generation of fine-grained prediction maps. Through the integration of the three decoders, our model effectively identifies and segments camouflaged targets. Extensive experiments are conducted on three commonly used benchmark datasets. The results of these experiments demonstrate that, even without the application of pre-processing or post-processing techniques, our model outperforms 14 state-of-the-art algorithms.

关键词： Decoding Feature extraction object detection object recognition Semantics Benchmark testing Background noise Convolutional neural networks Image analysis camouflaged object detection coarse-to-fine refinement convolutional neural network multi-stage detection

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

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

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：