Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection

Lü, Rui; Zhou, Menghan; Ming, Anlong; Zhou, Yu

doi:10.1109/icme.2019.00263

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, for the edge path (see Sec.3.1), a structure similar to [15] is employed to extract consistent and accurate occlusion edge, which is fundamental for occlusion reasoning. For the orientation path (see Sec.3.2), to learn more sufficient cues near the boundary for occlusion reasoning, the high-level bilateral feature is obtained, and a Multi-rate Context Learner (MCL) is proposed to extract the feature (see Sec.3.2.1).…”

Section: Ofnetmentioning

confidence: 99%

“…We adopt the module proposed in [15], which has a high capability to capture accurate location cue and sensitive perception of the entire object. In [15], the low-level cue from the first three side-outputs preserves the original size of the input image and encodes abundant spatial information. Without losing resolution, the large receptive field is achieved via dilated convolution [35] after res50 [9].…”

Section: Edge Pathmentioning

confidence: 99%

“…The Bilateral Response Fusion (BRF) shown in Fig.3 is presented to compensate the precise position for high-level features and suppress the clutter of non-occluded pixels for low-level features. Different from [15], we employ an additional convolution block to refine the contour, and integrate specific task features provided by diverse channels. Besides, this well-designed convolution block eliminates the gridding artifacts [36] caused by the dilated convolution in high-level layers.…”

Section: Edge Pathmentioning

confidence: 99%

See 2 more Smart Citations

Occlusion-Shared and Feature-Separated Network for Occlusion Relationship Reasoning

Lü

Feng

Zhou

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

Occlusion relationship reasoning demands closed contour to express the object, and orientation of each contour pixel to describe the order relationship between objects. Current CNN-based methods neglect two critical issues of the task: (1) simultaneous existence of the relevance and distinction for the two elements, i.e, occlusion edge and occlusion orientation; and (2) inadequate exploration to the orientation features. For the reasons above, we propose the Occlusion-shared and Feature-separated Network (OFNet). On one hand, considering the relevance between edge and orientation, two sub-networks are designed to share the occlusion cue. On the other hand, the whole network is split into two paths to learn the high-level semantic features separately. Moreover, a contextual feature for orientation prediction is extracted, which represents the bilateral cue of the foreground and background areas. The bilateral cue is then fused with the occlusion cue to precisely locate the object regions. Finally, a stripe convolution is designed to further aggregate features from surrounding scenes of the occlusion edge. The proposed OFNet remarkably advances the state-of-the-art approaches on PIOD and BSDS ownership dataset. The source code is available at https://github.com/buptlr/OFNet.

show abstract

Section: Ofnetmentioning

confidence: 99%

Section: Edge Pathmentioning

confidence: 99%

Section: Edge Pathmentioning

confidence: 99%

See 1 more Smart Citation

Occlusion-Shared and Feature-Separated Network for Occlusion Relationship Reasoning

Lü

Feng

Zhou

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our network, as shown in Fig. 2, we use ResNet [6] as a base feature extraction model as in previous works [18,11,10]. According to the size of the feature maps, this model is divided into five stages (see Fig.…”

Section: Dual-path Decoder Networkmentioning

confidence: 99%

DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning

Feng¹,

Kang²,

Ye³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Occlusion relationship reasoning based on convolution neural networks consists of two subtasks: occlusion boundary extraction and occlusion orientation inference. Due to the essential differences between the two subtasks in the feature expression at the higher and lower stages, it is challenging to carry on them simultaneously in one network. To address this issue, we propose a novel Dual-path Decoder Network, which uniformly extracts occlusion information at higher stages and separates into two paths to recover boundary and occlusion orientation respectively in lower stages. Besides, considering the restriction of occlusion orientation presentation to occlusion orientation learning, we design a new orthogonal representation for occlusion orientation and proposed the Orthogonal Orientation Regression loss which can get rid of the unfitness between occlusion representation and learning and further prompt the occlusion orientation learning. Finally, we apply a multi-scale loss together with our proposed orientation regression loss to guide the boundary and orientation path learning respectively. Experiments demonstrate that our proposed method achieves state-of-the-art results on PIOD and BSDS ownership datasets.

show abstract

Multi-class Human Body Parsing with Edge-Enhancement Network

Huang

et al. 2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Context-Constrained Accurate Contour Extraction for Occlusion Edge Detection

Cited by 7 publications

References 16 publications

Occlusion-Shared and Feature-Separated Network for Occlusion Relationship Reasoning

Occlusion-Shared and Feature-Separated Network for Occlusion Relationship Reasoning

DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning

Multi-class Human Body Parsing with Edge-Enhancement Network

Contact Info

Product

Resources

About