作者：
Hu, BoChen, SibaoAnhui Univ
Sch Comp Sci & Technol Anhui Prov Key Lab Informat Mat & Intelligent Sen Hefei 230601 Anhui Peoples R China
camouflaged object detection (COD), with the aim of detecting camouflagedobjects from similar backgrounds, is a rewarding but challenging task. A major challenge is that intrinsic similarity between foreground object...
详细信息
ISBN:
(纸本)9798400718212
camouflaged object detection (COD), with the aim of detecting camouflagedobjects from similar backgrounds, is a rewarding but challenging task. A major challenge is that intrinsic similarity between foreground object and background surroundings makes existing methods based on CNNs difficult to accurately identify objects. For that purpose, we propose a novel edge-guided contextual attention fusion network (ECAFNet) in this paper. Specifically, instead of using traditional CNN encoder, we adopt an effective transformer encoder, which can learn more robust and precise representations for the image features. Besides, we introduce three novel modules including edge generation module (EGM) to get object edges for more accurate segmentation of objects, edge-guided receptive field module (ERFM) to enlarge receptive field to capture more robust features, and contextual attention fusion module (CAFM) to closely fuse multiscale features. Extensive experiments on three challenging benchmark datasets indicate that the proposed ECAFNet is an efficient COD method and significantly surpasses the state-of-the-art models.
camouflaged object detection (COD) aims to identify objects that blend in with their surroundings and have numerous practical applications. However, COD is a challenging task due to the high similarity between camoufl...
详细信息
ISBN:
(纸本)9789819985548;9789819985555
camouflaged object detection (COD) aims to identify objects that blend in with their surroundings and have numerous practical applications. However, COD is a challenging task due to the high similarity between camouflagedobjects and their surroundings. To address the problem of identifying camouflagedobjects, we investigated how humans observe such objects. We found that humans typically first scan the entire image to obtain an approximate location of the target object. They then observe the differences between the boundary of the target object and its surrounding environment to refine their perception of the object. This continuous refinement process helps humans eventually identify the camouflagedobject. Based on this observation, we propose a novel COD method that emphasizes boundary positioning and leverages multi-scale feature fusion. Our model includes two important modules: the Enhanced Feature Module (EFM) and the Boundary and Positioning joint-guided Feature Fusion Module (BPFM). The EFM provides multi-scale information and obtains aggregated feature representations, resulting in more robust feature representations for the initial positioning of the camouflagedobject. In BPFM, we mimic human observation of camouflagedobjects by injecting boundary and positioning information into each level of the backbone features, working together to refine the target object in blurred regions progressively. We validated the effectiveness of our model on three benchmark datasets (COD10K, CAMO, CHAMELEON), and the results showed that our proposed method significantly outperforms existing COD models.
Due to the inherent visual similarity between the camouflagedobject and background, camouflaged object detection (COD) is widely recognized as a challenging task in the field of computer vision, and traditional objec...
详细信息
ISBN:
(纸本)9798350349405;9798350349399
Due to the inherent visual similarity between the camouflagedobject and background, camouflaged object detection (COD) is widely recognized as a challenging task in the field of computer vision, and traditional objectdetection networks often struggle to extract features and accurately identify camouflagedobjects. In this paper, we propose an edge-guided pixel level connected component assisted network for COD. Specifically, the edge prior is used to guide object feature extraction and the pixel level connected component obtained from the extracted feature is used to refine the bounding box of the object. We selectively employ a gray-polarization COD dataset to showcase the ability of feature extraction from backgrounds where camouflagedobjects may blend in or be occluded. Numerous experiments demonstrate the superiority of our method compared to state-of-the-arts in the case of limited information.
camouflaged object detection (COD), which aims to segment objects that are highly similar to their background, is a valuable yet challenging task. Due to the interference of clutter and noise in the background, existi...
详细信息
camouflaged object detection focuses on the challenge of segmenting objects that visually blend into their background. The effectiveness of camouflage strategies hinges on how well objects interact with their backgrou...
详细信息
camouflagedobjects share very similar colors but have different semantics with the surroundings. Cognitive scientists observe that both the global contour (i.e., boundary) and the local pattern (i.e., texture) of cam...
详细信息
camouflagedobjects share very similar colors but have different semantics with the surroundings. Cognitive scientists observe that both the global contour (i.e., boundary) and the local pattern (i.e., texture) of camouflagedobjects are key cues to help humans find them successfully. Inspired by the cognitive scientist's observation, we propose a novel boundary-and-texture enhancement network (FindNet) for camouflaged object detection (COD) from single images. Different from most of existing COD methods, FindNet embeds both the boundary-and-texture information into the camouflagedobject features. The boundary enhancement (BE) module is leveraged to focus on the global contour of the camouflagedobject, and the texture enhancement (TE) module is utilized to focus on the local pattern. The enhanced features from BE and TE, which complement each other, are combined to obtain the final prediction. FindNet performs competently on various conditions of COD, including slightly clear boundaries but very similar textures, fuzzy boundaries but slightly differentiated textures, and simultaneous fuzzy boundaries and textures. Experimental results exhibit clear improvements of FindNet over fifteen state-of-the-art methods on four benchmark datasets, in terms of detection accuracy and boundary clearness. The code will be publicly released.
camouflaged object detection (COD) is an emerging visual detection task, which aims to locate and distinguish the disguised target in complex backgrounds by imitating the human visual detection system. Recently, COD h...
详细信息
camouflaged object detection (COD) is an emerging visual detection task, which aims to locate and distinguish the disguised target in complex backgrounds by imitating the human visual detection system. Recently, COD has attracted increasing attention in computer vision, and a few models of camouflaged object detection have been successfully explored. However, most existing works primarily focus on modeling camouflaged object detection over in-depth analyzing existing COD structures. To the best of our knowledge, a systematic review for COD has not been publicly reported, especially for recently proposed deep learning-based COD models. To make up this vacancy, we firstly proposed a comprehensive review on both COD models and public benchmark datasets and provide potential directions for future COD studies. Specifically, we conduct a comprehensive summary of 39 existing COD models from 1998 to 2021. And then, to facilitate subsequent research on COD, we classify the existing structures into two categories, 27 traditional handcrafted feature-based structures and 12 structures based on deep learning. In addition, we further group traditional handcrafted feature-based structures into six sub-classes based on the detection mechanism: texture, color, motion, intensity, optical flow, and multi-modal fusion. Furthermore, we take an in-depth analysis of the deep learning-based structure based on both detection motivation and detection performance and evaluate the performance of each structure. Moreover, we sum up four widely used COD datasets and describe the details of each one. Finally, we also discuss the limitations of COD and the corresponding solutions to improve detection accuracy. We still mention the relevant applications of camouflaged object detection and its future research directions to promote the development of camouflaged object detection.
camouflaged object detection (COD) aims to accurately detect objects hidden in the surrounding environment. However, the existing COD methods mainly locate camouflagedobjects in the RGB domain, their performance has ...
详细信息
ISBN:
(纸本)9798400701085
camouflaged object detection (COD) aims to accurately detect objects hidden in the surrounding environment. However, the existing COD methods mainly locate camouflagedobjects in the RGB domain, their performance has not been fully exploited in many challenging scenarios. Considering that the features of the camouflagedobject and the background are more discriminative in the frequency domain, we propose a novel learnable and separable frequency perception mechanism driven by the semantic hierarchy in the frequency domain. Our entire network adopts a two-stage model, including a frequency-guided coarse localization stage and a detail-preserving fine localization stage. With the multi-level features extracted by the backbone, we design a flexible frequency perception module based on octave convolution for coarse positioning. Then, we design the correction fusion module to step-by-step integrate the high-level features through the prior-guided correction and cross-layer feature channel association, and finally combine them with the shallow features to achieve the detailed correction of the camouflagedobjects. Compared with the currently existing models, our proposed method achieves competitive performance in three popular benchmark datasets both qualitatively and quantitatively. The code will be released at https://***/rmcong/FPNet_ACMMM23.
camouflagedobject usually have a similar appearance or color to their surrounding environment, so it's difficult to be detected, especially in heavily obscured situations. To deal with this challenge, in this pap...
详细信息
ISBN:
(纸本)9781665468916
camouflagedobject usually have a similar appearance or color to their surrounding environment, so it's difficult to be detected, especially in heavily obscured situations. To deal with this challenge, in this paper, we propose a novel occlusion aware transformer network (OAFormer) to accurately identify the occluded camouflagedobject. In OAFormer, a hierarchical location guidance module (HLGM) is designed to locate the potential locations of camouflagedobjects. Then, in order to perceive the structural consistency of the occluded object, we design a neighborhood searching module (NSM) to focus on local pixel details of concealed objects. Besides, for each NSM, we take advantages of transformer blocks to capture long-distance dependencies. So our model can easily capture the complete camouflagedobject. In the end, we utilize the auxiliary supervision strategy to promote the learning ability of our model. Compared with other state-of-the-art methods, the proposed OAFormer achieves higher accuracy on four challenging datasets. Code and models are available at: https://***/xinyang920/OAFormer.
Recent camouflaged object detection (COD) approaches have been proposed to accurately segment objects blended into surroundings. The most challenging and critical issue in COD is to find out the lines of demarcation b...
详细信息
ISBN:
(纸本)9798400701085
Recent camouflaged object detection (COD) approaches have been proposed to accurately segment objects blended into surroundings. The most challenging and critical issue in COD is to find out the lines of demarcation between objects and background in the camouflage environment. Because of the similarity between the target object and the background, these lines are difficult to be found accurately. However, these are easy to be observed in different frequency components of the image. To this end, in this paper we rethink COD from the perspective of frequency components and propose a Frequency Representation Integration Network to mine informative cues from them. Specifically, we obtain high-frequency components from the original image by Laplacian pyramid-like decomposition, and then respectively send the image to a transformer-based encoder and frequency components to a tailored CNN-based Residual Frequency Array Encoder. Besides, we utilize the multi-head self-attention in transformer encoder to capture low-frequency signals, which can effectively parse the overall contextual information of camouflage scenes. We also design a Frequency Representation Reasoning Module, which progressively eliminates discrepancies between differentiated frequency representations and integrates them by modeling their point-wise relations. Moreover, to further bridge different frequency representations, we introduce the image reconstruction task to implicitly guide their integration. Sufficient experiments on three widely-used COD benchmark datasets demonstrate that our method surpasses existing state-of-the-art methods by a large margin.
暂无评论