Where Is My Mirror?

Yang, Xin; Mei, Haiyang; Xu, Ke; Wei, Xiaopeng; Yin, Baocai; Lau, Rynson W. H.

doi:10.1109/iccv.2019.00890

Cited by 82 publications

(97 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the previous step of instance segmentation, semantic segmentation finds the area of the person image reflected by the mirror. [14] improved semantic segmentation approach more precisely. They designed a semantic segmentation network with stacking multi-scale feature extraction modules.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Reflected Images From Object Detector in Indoor Environment Utilizing Depth Information

Park

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

We observed that mirror reflection severely degrades person detection performance in an indoor environment, which is an essential task for service robots. To address this problem, we propose a new real-time method to identify reflected virtual images in an indoor environment utilizing 3D depth information. Images reflected by the mirror are similar to real objects, so it is a non-trivial task to differentiate them. Conventional object detectors, which do not deal with this problem, obviously recognize reflected images as real objects. The proposed method compares the geometric relationship between the 3D spatial information of the detected object and its surrounding environment where the object locates. It analyzes the layout of surrounding indoor space utilizing semantic segmentation and plane detection method. With the estimated layout of indoor space, detected object candidates are examined whether they are real or reflected images utilizing 3D depth information. To verify the proposed method, a large indoor dataset was newly acquired and examined in a dedicated Living-lab environment. The performance of the algorithm is verified by comparing conventional detectors with the proposed method in the acquired Living-lab dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Edge detection and fusion module are additionally utilized in [15] to segment mirror region. They extracted mirror maps from contextual-contrasted features following [14] and refined it with mirror boundary map from edge information. However, the above methods need an appropriate annotation to train the segmentation network.…”

Section: Related Workmentioning

confidence: 99%

Identifying Reflected Images From Object Detector in Indoor Environment Utilizing Depth Information

Park

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Specific Region Segmentation (SRS) we defined here refers to segmenting the specific region such as shadow [20,25,72,70], mirror [59,36], glass [38,57] and water [16] region in the scene. Such regions are special and has a critical impact on the vision systems.…”

Section: Related Workmentioning

confidence: 99%

“…Specifically, multi-scale contexts are developed in [3,65,37] and multilevel contexts are extracted in [60,62]. Large-field contextual features are captured in [42,38], direction-aware contexts are explored in [20], and contextual contrasted features are leveraged in [8,59]. However, exploring contextual features indiscriminately may not contribute much to COS as the contexts would often be dominated by features of conspicuous objects.…”

Section: Related Workmentioning

confidence: 99%

Camouflaged Object Segmentation with Distraction Mining

Mei¹,

Ji²,

Wei³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Camouflaged object segmentation (COS) aims to identify objects that are "perfectly" assimilate into their surroundings, which has a wide range of valuable applications.The key challenge of COS is that there exist high intrinsic similarities between the candidate objects and noise background. In this paper, we strive to embrace challenges towards effective and efficient COS. To this end, we develop a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature. Specifically, our PFNet contains two key modules, i.e., the positioning module (PM) and the focus module (FM). The PM is designed to mimic the detection process in predation for positioning the potential target objects from a global perspective and the FM is then used to perform the identification process in predation for progressively refining the coarse prediction via focusing on the ambiguous regions. Notably, in the FM, we develop a novel distraction mining strategy for the distraction discovery and removal, to benefit the performance of estimation. Extensive experiments demonstrate that our PFNet runs in real-time (72 FPS) and significantly outperforms 18 cutting-edge models on three challenging datasets under four standard metrics.

show abstract

“…Especially, our method shows a large improvement on the DUTS-test dataset, which includes many challenge cases, demonstrating the strong capability of our PSCNet. In the future, we will explore the potential of our PSC module design for other layer separation tasks, such as mirror detection [79], lane marking detection [80], shadow detection [81]- [83] and removal [84], [85], reflection removal [86], [87], rain removal [88], haze removal [89], [90], etc.…”

Section: Comparison With the State-of-the-artsmentioning

confidence: 99%

Pyramid Spatial Context Features for Salient Object Detection

2020

IEEE Access

View full text Add to dashboard Cite

Salient object detection aims to obtain the most attractive objects from the input images, which severs as a pre-processing step for many image processing tasks. This paper presents a novel deep neural network design for salient object detection by formulating a pyramid spatial context module, PSC module for short, to capture the spatial context information at multiple scales. To achieve this, we first adopt convolutional operations with different dilated rates to generate the feature maps with different respective fields, and then use the two-round recurrent translations to explore multiple types of spatial context features on these feature maps. By further inserting this module in a deep network, namely PSCNet, we are able to optimize the network in an end-to-end manner for salient object detection. We evaluate the proposed method on six public benchmark datasets by comparing it with 25 salient object detection methods. The experimental results demonstrate that our PSCNet performs favorably against all the other methods. INDEX TERMS Salient object detection, spatial context, pyramid features, deep neural network.

show abstract

Where Is My Mirror?

Cited by 82 publications

References 48 publications

Identifying Reflected Images From Object Detector in Indoor Environment Utilizing Depth Information

Identifying Reflected Images From Object Detector in Indoor Environment Utilizing Depth Information

Camouflaged Object Segmentation with Distraction Mining

Pyramid Spatial Context Features for Salient Object Detection

Contact Info

Product

Resources

About