检索结果-内蒙古大学图书馆

TCU-Net: Transformer and Convolutional Neural Network-Based Advanced U-Net for Concealed object detection

IEEE ACCESS 2022年 10卷 122347-122360页

作者： Park, Kyeong-Beom Lee, Jae Yeol Chonnam Natl Univ Dept Ind Engn Gwangju 61186 South Korea

camouflaged object detection (COD) seeks to find concealed objects hidden in natural surroundings. COD is challenging since it has to distinguish intrinsic similarities between foreground objects and background surroundings, unlike salient object detection. Convolutional neural network (CNN)-based approaches are proposed to overcome this challenge. However, they have inherent limitations in modeling and extracting global contexts. Although Transformer-based approaches are proposed to tackle this problem, which can maintain the semantic features of input images, they have limitations in learning localized spatial features in the limited receptive field. Therefore, one of the main challenges is to conduct accurate and robust COD while maintaining global contexts without sacrificing low-level contexts. This study proposes a novel concealed object detection and segmentation method using Transformer and CNN-based advanced U-Net (TCU-Net). TCU-Net can extract globalized semantic features using the Swin Transformer-based encoder and localized spatial features using the attentive Inception decoder. In particular, multi-dilated residual (MDR) blocks connecting the encoder and decoder generate refined multi-level features to improve discriminability. Finally, the attentive Inception decoder generates the final camouflaged object mask by maintaining the localized spatial information. Instead of simple up-sampling of the feature map, the attentive Inception decoder conducts cascaded deconvolution through Inception and attention modules. A weighted hybrid loss function is used for optimizing the model, consisting of the binary cross entropy (BCE) and intersection over union (IoU) losses. We comprehensively compared the proposed TCU-Net with previous studies by analyzing different metrics based on four public datasets, such as CAMO, CHAMELEON, COD10K, and NC4K. An ablation study was also conducted to evaluate network architectures and loss functions to verify advantages of the pr

关键词： Advanced U-Net camouflaged object detection attentive Inception decoder multi-dilatedresidual block Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Powered camouflaged object Recognition Model 2

Deep Learning-Powered Camouflaged Object Recognition Model

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Tomar, Riya Chauhan, Naman Chauhan, Chhavi Tomar, Yash Singh, Soumyendra Chauhan, Nishant Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India University of Petroleum and Energy Studies School of Computer Science Dehradun India Cmr University Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Mathematics Chennai India Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Noida India

ISBN: (纸本)9798350317558

This research paper delves into the intersection of advanced technology and military strategies, specifically focusing on the imperative task of camouflaged object detection within the Indian Paramilitary forces. Leveraging cutting-edge DL Frameworks, like CNNs, Faster RCNN, and YOLOv8, our methodology aims to enhance the precision and efficiency of identifying concealed weapons and camouflaged objects in real-world scenarios. The collaboration with the Indian Paramilitary has enabled the creation of a dataset tailored to the challenges faced on the ground, reflecting a commitment to addressing contemporary threats. The study explores the global positioning of India in military technology, emphasizing the nation's role as a key player in adopting sophisticated solutions for defense. Beyond technological innovation, this research underscores a noble cause the protection of lives and the fortification of national security. The fusion of advanced technology and a profound sense of duty forms the core of this work, exemplifying a commitment to the greater good. © 2024 IEEE.

关键词： camouflaged object detection Convolutional Neural Networks (CNNs) Deep Learning Defense Strategies Faster RCNN Indian Paramilitary Military Technology object Recognition Situational Awareness YOLOv8

来源：评论

学校读者我要写书评

暂无评论

camouflaged Human detection: comparative analysis using YoloV5s, Yolov5l, Yolov5m, Yolov5n, Yolov5x Model 4

Camouflaged Human Detection: comparative analysis using Yolo...

引用

4th International Conference on Artificial Intelligence and Signal Processing

作者： Mulla, Sufiya Mandavkar, Rajlaxmi Jamadar, Simran Magdum, Sneha Gurav, Uma KITs Coll Engn Autonomous Dept CSE Data Sci Kolhapur Maharashtra India

ISBN: (纸本)9798350350661;9798350350654

This research paper discusses about, The camouflaged human or object detection using different variations of YOLOV5. Our project deep dives into the analysis of YOLO(You Only Look Once) algorithm and it's different types for performance analysis. The proposed model, trained on the dataset with different regions and angles of images, utilizes YOLOv5 for efficient camouflaged human detection, with manual annotation of images used for training the dataset and calculated different outputs for performance analysis. There can be lot of applications of the camouflaged object detection project. Even if it is Biodiversity conservation in Nature like detecting the animals or plants which gets camouflaged in the nature and are difficult to detect or detecting enemy military invasion. This algorithm can be combined with one or more other image processing algorithms also for better accuracy and easy implementation purpose. This research work is carried out on different variants of YOLOv5 algorithm. We have used the different variants like Yolov5l, Yolov5m, Yolov5n, Yolov5x enhancing accuracy and robustness. The performance analysis is carried out in terms of P curve (Precision), R curve(recall), PR curve(precision and recall) and F1 curve of each training set and also the confusion matrix for all the algorithms is calculated and it is observed that Yolov5l works better as compared to other YOLO variants.

关键词： YOLOv5 Image processing camouflaged object detection

来源：评论

学校读者我要写书评

暂无评论

FINDING camouflaged object GUIDED BY CONTOUR AND ATTENTION 30

FINDING CAMOUFLAGED OBJECT GUIDED BY CONTOUR AND ATTENTION

引用

30th IEEE International Conference on Image Processing (ICIP)

作者： Cui, Junjie Sun, Fengming Yuan, Xia Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781728198354

camouflaged object detection aims to detect objects closely blended into the background. Inspired by visual mechanism of human being, we define detection process as an end-to-end task consisted of locating and refining. To this end, we propose Contour Supervision and Initial Locating Guidance Network (CSIGNet) to effectively segment camouflaged objects from background. Specifically, our method fully explores the contribution of semantic contour to the binary segmentation task. In addition, attention mechanism is used for our final prediction. Experiments show that it has achieved excellent results on public datasets and the model can accurately segment camouflage objects. Codes will be made available at https://***/RecKono/CSIGNet.

关键词： camouflaged object detection

来源：评论

学校读者我要写书评

暂无评论

Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage

Shifting Spotlight for Co-supervision: A Simple yet Efficien...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Hu, Yang Zhang, Jinxia Zhang, Kaihua Yuan, Yin Huang, Jiale Zhan, Zechao Wang, Xin Key Laboratory of Measurement and Control of CSE School of Automation Southeast University China School of Computer Science Nanjing University of Information Science and Technology China Advanced Ocean Institute of Southeast University China Alibaba Group China

ISBN: (纸本)9798350368741

camouflaged object detection (COD) remains a challenging task in computer vision. Existing methods often resort to additional branches for edge supervision, incurring substantial computational costs. To address this, we propose the Co-Supervised Spotlight Shifting Network (CS3Net), a compact single-branch framework inspired by how shifting light source exposes camouflage. Our spotlight shifting strategy replaces multi-branch designs by generating supervisory signals that highlight boundary cues. Within CS3Net, a Projection Aware Attention (PAA) module is devised to strengthen feature extraction, while the Extended Neighbor Connection Decoder (ENCD) enhances final predictions. Extensive experiments on public datasets demonstrate that CS3Net not only achieves superior performance, but also reduces Multiply-Accumulate operations (MACs) by 32.13% compared to state-of-the-art COD methods, striking an optimal balance between efficiency and effectiveness. © 2025 IEEE.

关键词： camouflaged object detection Efficient Network Design Network Co-supervision

来源：评论

学校读者我要写书评

暂无评论

Real time confidence estimation and multi-scale camouflage object detection 6

Real time confidence estimation and multi-scale camouflage o...

引用

6th IEEE International Conference on Automation, Electronics and Electrical Engineering, AUTEEE 2023

作者： Wang, Xufei Ren, Xiaokang Northwest Normal University College of Computer Science and Engineering Lanzhou China

ISBN: (纸本)9798350305623

Due to the fact that objects with camouflage blend seamlessly into their surroundings, exhibiting a exceptional resemblance in terms of texture, color, shape, etc., and possessing boundaries that are indistinguishable from their environment, the detection of such camouflaged objects becomes significantly more challenging. In this research, we introduce a novel network called CRNet, which incorporates a detection network for identifying camouflage objects with a real-time network for estimating confidence. Unlike other networks, in the camouflage object detection network, we design MSF2M by capturing maps at different scales and using the relationship between their maps. In the real-time confidence estimation network, we use spatial adaptive normalization for the edge region to combine the semantic information from high latitude images embedded in downstream low dimensional features. The network's outstanding performance, as described in the paper, is demonstrated through tests conducted on three standard datasets. © 2023 IEEE.

关键词： camouflaged object detection confidence estimation feature fusion image segmentation

来源：评论

学校读者我要写书评

暂无评论

CEMINet: Context exploration and multi-level interaction network for salient object detection

引用

DIGITAL SIGNAL PROCESSING 2024年 147卷

作者： Xia, Chenxing Chen, Xinyu Sun, Yanguang Ge, Bin Fang, Xianjin Gao, Xiuju Li, Kuan-Ching Zhang, Hanling Zhang, Yan Anhui Univ Sci & Technol Coll Comp Sci & Engn Huainan 232001 Peoples R China Anhui Purvar Bigdata Technol Co Ltd Huainan 232001 Anhui Peoples R China Hefei Comprehens Natl Sci Ctr Inst Energy Hefei 230051 Anhui Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei 230051 Anhui Peoples R China Anhui Univ Sci & Technol Coll Elect & Informat Engn Huainan 232001 Anhui Peoples R China Providence Univ Dept Comp Sci & Informat Engn Taichung 43301 Taiwan Hunan Univ Sch Design Changsha 410082 Peoples R China Anhui Univ Sch Elect & Informat Engn Hefei 230039 Anhui Peoples R China

Precise salient object detection (SOD) in realistic scenarios heavily relies on multi -scale context. Although existing SOD methods have made significant advancements by incorporating contextual information, they often overlook the correlation of contexts at different scales during feature extraction, leading to challenges in producing precise saliency maps. Our proposed solution to mitigate the above challenges associated with SOD is the Context Exploration and Multi -level Interaction Network (CEMINet). Specifically, we first develop a progressive multi -scale context extraction (PMCE) module, which enables the gradual capture of strongly correlated multi -scale context with the aid of multi -receptive -field convolution operations. Additionally, we design a hierarchical feature hybrid interaction (HFHI) module to effectively aggregate multi -level features by exploiting a hybrid interaction strategy following a top -down approach. And then, a well -designed stereoscopic attention enhancement (SAE) module is presented to refine multi -level features from HFHI through two parallel attention branches combined in a stereoscopic structure for generating precise predictions. Comprehensive experiments show our CEMINet achieves superior performance, without requiring any post -processing, compared to 16 state-of-the-art SOD models across five popular datasets. To substantiate the effectiveness and generality of our model, we also implement it to the camouflaged object detection (COD), outperforming the corresponding state-of-the-art models.

关键词： camouflaged object detection Deep learning Multi-scale context Multi-level feature Salient object detection

来源：评论

学校读者我要写书评

暂无评论

PreyNet: Preying on camouflaged objects 22

PreyNet: Preying on Camouflaged Objects

引用

30th ACM International Conference on Multimedia (MM)

作者： Zhang, Miao Xu, Shuang Piao, Yongri Shi, Dongxiang Lin, Shusen Lu, Huchuan Dalian Univ Technol Dalian Peoples R China Key Lab Ubiquitous Network & Serv Software Liaoni Dalian Peoples R China Pengcheng Lab Dalian Peoples R China

ISBN: (纸本)9781450392037

Species often adopt various camouflage strategies to be seamlessly blended into the surroundings for self-protection. To figure out the concealment, predators have evolved excellent hunting skills. Exploring the intrinsic mechanisms of the predation behavior can offer more insightful glimpse into the task of camouflaged object detection (COD). In this work, we strive to seek answers for accurate COD and propose a PreyNet, which mimics the two processes of predation, namely, initial detection (sensory mechanism) and predator learning (cognitive mechanism). To exploit the sensory process, a bidirectional bridging interaction module (BBIM) is designed for selecting and aggregating initial features in an attentive manner. The predator learning process is formulated as a policy- and-calibration paradigm, with the goal of deciding on uncertain regions and encouraging targeted feature calibration. Besides, we obtain adaptive weight for multi-layer supervision during training via computing on the uncertainty estimation. Extensive experiments demonstrate that our model produces state-of-the-art results on several benchmarks. We further verify the scalability of the predator learning paradigm through applications on top-ranking salient object detection models. Our code is publicly available at https://***/OIPLab-DUT/PreyNet.

关键词： camouflaged object detection sensory mechanism predator learning

来源：评论

学校读者我要写书评

暂无评论

Bilateral Reference for High-Resolution Dichotomous Image Segmentation

引用

CAAI Artificial Intelligence Research 2024年第1期3卷 82-93页

作者： Peng Zheng Dehong Gao Deng-Ping Fan Li Liu Jorma Laaksonen Wanli Ouyang Nicu Sebe College of Computer Science Nankai UniversityTianjin 300350China Shanghai AI Laboratory Shanghai 200232China School of Cybersecurity Northwestern Polytechnical UniversityXi’an 710072China College of Electronic Science and Technology National University of Defense TechnologyChangsha 410073China Department of Computer Science Aalto UniversityEspoo FI-02150Finland Department of Information Engineering and Computer Science University of TrentoTrento I-38122Italy

We introduce a novel bilateral reference framework(BiRefNet)for high-resolution dichotomous image segmentation(DIS).It comprises two essential components:the localization module(LM)and the reconstruction module(RM)with our proposed bilateral reference(BiRef).LM aids in object localization using global semantic *** the RM,we utilize BiRef for the reconstruction process,where hierarchical patches of images provide the source reference,and gradient maps serve as the target *** components collaborate to generate the final predicted *** also introduce auxiliary gradient supervision to enhance the focus on regions with finer *** addition,we outline practical training strategies tailored for DIS to improve map quality and the training *** validate the general applicability of our approach,we conduct extensive experiments on four tasks to evince that BiRefNet exhibits remarkable performance,outperforming task-specific cutting-edge methods across all *** codes are publicly available at https://***/ZhengPeng7/BiRefNet.

关键词： dichotomous image segmentation camouflaged object detection salient object detection bilateral reference highresolution segmentation

来源：评论

学校读者我要写书评

暂无评论

Camouflage detection: Optimization-based computer vision for Alligator sinensis with low detectability in complex wild environments

引用

ECOLOGICAL INFORMATICS 2024年 83卷

作者： Liu, Yantong Che, Sai Ai, Liwei Song, Chuanxiang Zhang, Zheyu Zhou, Yongkang Yang, Xiao Xian, Chen Kunsan Natl Univ Dept Comp Informat Engn Gunsan 54150 South Korea Kunsan Natl Univ Dept Mech Engn Gunsan 54150 South Korea Jiangsu Univ Sci & Technol Dept Mech Engn Zhenjiang 212000 Peoples R China Sichuan Univ Coll Water Resource & Hydropower State Key Lab Hydraul & Mt River Engn Chengdu 610065 Peoples R China Alligator Sinensis Res Ctr Anhui Prov Xuanzhou 242000 Peoples R China Univ Georgia Dept Poultry Sci Athens GA 30605 USA

Alligator sinensis is an extremely rare species that possesses excellent camouflage, allowing it to fit perfectly into its natural environment. The use of camouflage makes detection difficult for both humans and automated systems, highlighting the importance of modern technologies for animal monitoring. To address this issue, we present YOLO v8-SIM, an innovative detection technique specifically developed to significantly enhance the identification precision. YOLO v8-SIM utilizes a sophisticated dual-layer attention mechanism, an optimized loss function called inner intersection-over-union (IoU), and a technique called slim-neck cross-layer hopping. The results of our study demonstrate that the model achieves an accuracy rate of 91 %, a recall rate of 89.9 %, and a mean average precision (mAP) of 92.3 % and an IoU threshold of 0.5. In addition, the model operates at a frame rate of 72.21 frames per second (FPS) and excels at accurately recognizing objects that are partially visible or smaller in size. To further improve our initiatives, we suggest creating an open-source collection of data that showcases A. sinensis in its native environment while using camouflage techniques. These developments collectively enhance the ability to detect disguised animals, thereby promoting the monitoring and protection of biodiversity, and supporting ecosystem sustainability.

关键词： Alligator sinensis YOLO v8 optimization Wildlife conservation technology Camouflage pattern recognition camouflaged object detection Ecological monitoring algorithms

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：