检索结果-内蒙古大学图书馆

Feature Aggregation and Propagation Network for camouflaged object detection

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 7036-7047页

作者： Zhou, Tao Zhou, Yi Gong, Chen Yang, Jian Zhang, Yu Nanjing Univ Sci & Technol Key Lab Intelligent Percept & Syst High Dimens In PCA Lab Minist Educ Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Social Nanjing 210094 Peoples R China Minist Educ Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing 211189 Peoples R China Lehigh Univ Dept Bioengn Bethlehem 18015 PA USA

camouflaged object detection (COD) aims to detect/segment camouflaged objects embedded in the environment, which has attracted increasing attention over the past decades. Although several COD methods have been developed, they still suffer from unsatisfactory performance due to the intrinsic similarities between the foreground objects and background surroundings. In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection. Specifically, we propose a Boundary Guidance Module (BGM) to explicitly model the boundary characteristic, which can provide boundary-enhanced features to boost the COD performance. To capture the scale variations of the camouflaged objects, we propose a Multi-scale Feature Aggregation Module (MFAM) to characterize the multi-scale information from each layer and obtain the aggregated feature representations. Furthermore, we propose a Cross-level Fusion and Propagation Module (CFPM). In the CFPM, the feature fusion part can effectively integrate the features from adjacent layers to exploit the cross-level correlations, and the feature propagation part can transmit valuable context information from the encoder to the decoder network via a gate unit. Finally, we formulate a unified and end-to-end trainable framework where cross-level features can be effectively fused and propagated for capturing rich context information. Extensive experiments on three benchmark camouflaged datasets demonstrate that our FAP-Net outperforms other state-of-the-art COD models. Moreover, our model can be extended to the polyp segmentation task, and the comparison results further validate the effectiveness of the proposed model in segmenting polyps. The source code and results will be released at https://***/taozh2017/FAPNet.

关键词： camouflaged object detection boundary guidance module multi-scale feature aggregation cross-level fusion feature propagation

来源：评论

学校读者我要写书评

暂无评论

CFANet: A Cross-layer Feature Aggregation Network for camouflaged object detection

CFANet: A Cross-layer Feature Aggregation Network for Camouf...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhang, Qing Yan, Weiqi Shanghai Inst Technol Sch Comp Sci & Informat Engn Shanghai Peoples R China

ISBN: (纸本)9781665468916

Deep learning-based camouflaged object detection approaches have achieved great progress in recent years. However, it is still challenging to accurately identify the camouflaged objects from the highly similar backgrounds. In this paper, we design a novel cross-layer feature aggregation network (CFANet) for camouflaged object detection to explore how to effectively aggregate multi-level and multi-scale features generated from the backbone network by excavating the similarities and differences of features at different levels. Firstly, we design a cross-layer feature fusion (CLFF) module to generate discriminative features by fusing and refining the multi-level side-output features with similar characteristics in the same feature group. Secondly, we design a uniqueness enhancement (UE) strategy to respectively emphasize the superiority of deep features and shallow features in locating the camouflaged objects and sharpening the structure details. Extensive experiments on four benchmarks are conducted to demonstrate that the proposed CFANet network performs favorably against 11 state-of-the-art camouflaged object detection methods, demonstrating the effectiveness and superiority of our method. The code and results can be found from the link of https://***/ZhangQing0329/CFANet

关键词： camouflaged object detection multi-scale feature fusion attention deep learning

来源：评论

学校读者我要写书评

暂无评论

camouflaged object detection via Neighbor Connection and Hierarchical Information Transfer

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2022年 221卷

作者： Zhang, Cong Wang, Kang Bi, Hongbo Liu, Ziqi Yang, Lina Northeast Petr Univ Dept Elect Informat Engn Daqing 163318 Peoples R China

camouflaged object detection (COD) aims to detect objects with high similarity to the background. Unlike general object detection, COD is a more challenging task because the target boundaries are vague and the location is difficult to determine. In this paper, we propose a novel COD framework, which consists of two main components, namely, Neighbor Connection Mode (NCM) and Hierarchical Information Transfer (HIT). NCM aggregates the features from the neighboring layers of the encoder network to enhance the complementation of various level information. Our NCM not only reduces the burden of dense connection that consumes a lot of computing memory and redundant features but also weakens the phenomenon of the long-term transmission of context. We also propose a HIT module to transfer the features of different dilated rates inside each level hierarchically, which expands the receptive field of each branch and enhances the relationship between different features. Our method accurately detects camouflaged objects by considering full level information and a large receptive field. The experiments on three COD datasets show that our model achieves state-of-the-art performance.

关键词： Deep learning camouflaged object detection Salient object detection

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer-based Real-Time camouflaged object detection System at Edge 9

Vision Transformer-based Real-Time Camouflaged Object Detect...

引用

IEEE International Conference on Smart Computing (SMARTCOMP)

作者： Putatunda, Rohan Khan, Md Azim Gangopadhyay, Aryya Wang, Jianwu Busart, Carl Erbacher, Robert F. Univ Maryland Baltimore Cty Dept Informat Syst Baltimore MD 21228 USA DEVCOM Army Res Lab Adelphi MD USA

ISBN: (纸本)9798350322811

camouflaged object detection is a challenging task in computer vision that involves identifying objects that are intentionally or unintentionally hidden in their surrounding environment. Vision Transformer mechanisms play a critical role in improving the performance of deep learning models by focusing on the most relevant features that help object detection under camouflaged conditions. In this paper, we utilized a vision transformer (VT) in two phases, a) By integrating VT with a deep learning architecture for efficient monocular depth map generation for camouflaged objects and b) By embedding VT multiclass object detection model with multimodal feature input (RGB with RGB-D) that increases the visual cues and provides more representational information to the model for performance enhancement. Additionally, we performed an ablation study to understand the role of the vision transformer in camouflaged object detection and incorporated GRAD-CAM on top of the model to visualize the performance improvement achieved by embedding the VT in the model architecture. We deployed the model on resource-constrained edge devices for real-time object detection to realistically test the performance of the trained model.

关键词： camouflaged object detection Multi-Modality Vision Transformer GRAD-CAM

来源：评论

学校读者我要写书评

暂无评论

Depth-aided camouflaged object detection 23

Depth-aided Camouflaged Object Detection

引用

31st ACM International Conference on Multimedia (MM)

作者： Wang, Qingwei Yang, Jinyu Yu, Xiaosheng Wang, Fangyi Chen, Peng Zheng, Feng China Three Gorges Univ Yichang Peoples R China Southern Univ Sci & Technol Shenzhen Peoples R China Univ Birmingham Birmingham W Midlands England

ISBN: (纸本)9798400701085

camouflaged object detection (COD) aims to identify and segment objects that blend into their surroundings. Since the color and texture of the camouflaged objects are extremely similar to the surrounding environment, it is super challenging for vision models to precisely detect them. Inspired by research on biology and evolution, we introduce depth information as an additional cue to help break camouflage, which can provide spatial information and texture-free separation for foreground and background. To dig clues of camouflaged objects in both RGB and depth modalities, we innovatively propose Depth-aided camouflaged object detection (DaCOD), which involves two key components. We firstly propose the Multi-modal Collaborative Learning (MCL) module, which aims to collaboratively learning deep features from both RGB and depth channels via a hybrid backbone. Then, we propose a novel Cross-modal Asymmetric Fusion (CAF) strategy, which asymmetrically fuse RGB and depth information for complementary depth feature enhancement to produce accurate predictions. We conducted numerous experiments of the proposed DaCOD on three widely-used challenging COD benchmark datasets, in which DaCOD outperforms the current state-of-the-arts by a large margin. All resources are available at https://***/qingwei-wang/DaCOD.

关键词： camouflaged object detection RGB-D Fusion Cross-modal Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced camouflaged object detection for Agricultural Pest Management: Insights from Unified Benchmark Dataset Analysis 21

Enhanced Camouflaged Object Detection for Agricultural Pest ...

引用

21st International Bhurban Conference on Applied Sciences and Technology, IBCAST 2024

作者： Hussain, Syed Muhammad Zaidi, Samiya Ali Hyder, Afsah Ali Rizvi, Syed Muhammad Farhan, Muhammad School of Science and Engineering Habib University Karachi Pakistan

ISBN: (纸本)9798331516680

In recent decades, the severity of climate change has led to a rise in the frequency of agricultural pest attacks on farms causing significant economic damage and food shortages. Effective management of pests, specifically camouflaged pests, poses significant challenges in agriculture, requiring accurate automated detection and segmentation. In this study, we leverage state-of-the-art object detection and segmentation models, specifically the single-stage YOLOv8 model, fine-tuned on a large-scale Unified Benchmark camouflaged object detection Dataset (UBCODD) consisting of 52,447 images. Furthermore, we extend our analysis to benchmark agricultural pest datasets such as IP-102 and the Locust-Mini Dataset, showcasing competitive performance metrics. This integrated approach allows us to capture agricultural camouflaged pests with greater detail and accuracy. Our findings lay the groundwork for the advancement of single-stage object detectors and segmentation models in the field of agriculture. Moreover, we contribute to open-source initiatives in agricultural technology by generating bounding box annotations for the entire IP-102 and binary masks for the Agricultural Pests Image Dataset. This research signifies a significant advancement in agricultural pest recognition and segmentation using cutting-edge computer vision technologies. © 2024 IEEE.

关键词： camouflaged object detection camouflaged Pests camouflaged Segmentation Pest detection UBCODD

来源：评论

学校读者我要写书评

暂无评论

A MULTICHANNEL LOCALIZATION METHOD FOR camouflaged object detection 30

A MULTICHANNEL LOCALIZATION METHOD FOR CAMOUFLAGED OBJECT DE...

引用

30th IEEE International Conference on Image Processing (ICIP)

作者： Rahman, Md. Rakibur Chowdhury, Md. Mafri Sarkar, Md. Shohanur Rahaman Karim, Md. Shahriar North South Univ Elect & Comp Engn Dhaka Bangladesh

ISBN: (纸本)9781728198354

This paper proposes a multichannel method for discriminative region localization in camouflaged object detection (COD) tasks. In one channel, processing the phase and amplitude of 2-D Fourier spectra generate a modified form of the original image, used later for a pixel-wise optimal local entropy analysis. The other channel implements a class activation map (CAM) and Global Average Pooling (GAP) for object localization. We combine the channels linearly to form the final localized version of the COD images. Experimentation in multiple COD datasets demonstrates that the proposed method successfully localizes regions containing more than 80% of the camouflaged objects. Our proposed method does not require memoryintensive devices or prior training on particular image features, making it easily integrable into a resource-constrained environment. The proposed approach is also applicable to non-COD images.

关键词： camouflaged object detection Local Entropy Class Activation Map

来源：评论

学校读者我要写书评

暂无评论

TINYCOD: Tiny and Effective Model for camouflaged object detection 48

TINYCOD: Tiny and Effective Model for Camouflaged Object Det...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Xing, Haozhe Gao, Shuyong Tang, Hao Mok, Tsui Qin Kang, Yanlan Zhang, Wenqiang Information Technology and Electrical Engineering Eth Zurich Zurich Switzerland Fudan University Academy for Engineering & Technology Shanghai China Fudan University School of Computer Science Shanghai China

ISBN: (纸本)9781728163277

关键词： camouflaged object detection edge features feature fusion image segmentation lightweight model

来源：评论

学校读者我要写书评

暂无评论

Depth alignment interaction network for camouflaged object detection

引用

MULTIMEDIA SYSTEMS 2024年第1期30卷 51-51页

作者： Bi, Hongbo Tong, Yuyu Zhang, Jiayuan Zhang, Cong Tong, Jinghui Jin, Wei Northeast Petr Univ Sanya Offshore Oil & Gas Res Inst Daqing 163319 Peoples R China Natl Univ Def Technol Coll Elect Countermeasures Hefei 230037 Peoples R China Northeast Petr Univ Sch Elect Informat Engn Daqing 163319 Peoples R China Guizhou Univ State Key Lab Publ Big Data Guiyang 550025 Peoples R China

Many animals actively change their own characteristics, such as color and texture, through camouflage, a natural defense mechanism, making them difficult to be detected in the natural environment, which makes the task of camouflaged object detection extremely challenging. Biological research shows that the eyes of animals have three-dimensional perception ability, and the obtained depth information can provide useful object positioning clues for finding camouflaged objects. However, almost all the current studies for camouflaged object detection do not combine depth maps with RGB images. Therefore, combining depth maps with traditional unimodal RGB images is of great research significance to improve the accuracy of camouflaged object detection. In this paper, we propose a depth alignment interaction network for camouflaged object detection in which the depth maps used are generated from existing monocular depth estimation networks. To address the problem that the quality of the generated depth maps varies, we propose a depth alignment index method to evaluate the quality of the depth maps. The method dynamically assigns the proportion of depth maps in the fusion process to depth maps of different quality according to their alignment with RGB images. Then, to fully extract the fused artifact features, we design an expanded pyramid interaction module, which first expands the receptive field of the features in each layer. Then, the features at the higher levels interacted with the features at the lower levels by connecting them step-by-step to further refine the predicted camouflaged area. Extensive experiments on 4 camouflaged object detection datasets demonstrate the effectiveness of our solution for camouflaged object detection.

关键词： camouflaged object detection Depth alignment index Expanded pyramid interaction Deep learning

来源：评论

学校读者我要写书评

暂无评论

Reverse cross-refinement network for camouflaged object detection

引用

IMAGE AND VISION COMPUTING 2024年 150卷

作者： Ye, Qian Zhou, Yaqin Huo, Guanying Liu, Yan Zhou, Yan Li, Qingwu Hohai Univ Coll Informat Sci & Engn Changzhou 213200 Peoples R China Hohai Univ Jiangsu Key Lab Power Transmiss & Distribut Equipm Changzhou 213200 Peoples R China

Due to the high intrinsic similarity between camouflaged objects and the background, camouflaged objects often exhibit blurred boundaries, making it challenging to distinguish the boundaries of objects. Existing methods still focus on the overall regional accuracy but not on the boundary quality and are not competent to identify camouflaged objects from the background in complex scenarios. Thus, we propose a novel reverse cross-refinement network called RCR-Net. Specifically, we design a diverse feature enhancement module that simulates the correspondingly expanded receptive fields of the human visual system by using convolutional kernels with different dilation rates in parallel. Also, the boundary attention module is used to reduce the noise of the bottom features. Moreover, a multi-scale feature aggregation module is proposed to transmit the diverse features from pixel-level camouflaged edges to the entire camouflaged object region in a coarse-to-fine manner, which consists of reverse guidance, group guidance, and position guidance. Reverse guidance mines complementary regions and details by erasing already estimated object regions. Group guidance and position guidance integrate different features through simple and effective splitting and connecting operations. Extensive experiments show that RCR-Net outperforms the existing 18 state-of-the-art methods on four widely-used COD datasets. Especially, compared with the existing top-1 model HitNet, RCR-Net significantly improves the performance by similar to 16.4% (Mean Absolute Error) on the CAMO dataset, showing that RCR-Net could accurately detect camouflaged objects.

关键词： camouflaged object detection Cross refinement Reverse guidance Receptive field

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：