Occlusion-based depth ordering on monocular images with Binary Partition Tree

Palou, Guillem; Salembier, Philippe

doi:10.1109/icassp.2011.5946598

Cited by 17 publications

(27 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Com: uses the combined the features. The above methods share the same depth reasoning in [13] that deletes the loop in the depth order graph by the lowest local predicted belief. Global: This is our full algorithm.…”

Section: Methodsmentioning

confidence: 99%

“…Our work assumes that the scene is composed of objects in distinct depth order, and is closely related to the works from Dimiccoli et al [4] and Palou et al [13], which infer the depth ordering from an elaborate set of rules on Tjunctions. Our work differs and improves upon previous works in the following aspects: a) in these works, the rules of inferences are designed without any learning process.…”

Section: Related Workmentioning

confidence: 99%

“…JA: We re-implement the algorithm proposed in [13] that orders the depth mainly by angles within a junction. pBF: uses the proposed boundary features.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A learning-based framework for depth ordering

Jia

Gallagher²,

Chang

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Depth ordering is instrumental for understanding the 3D geometry of an image. We as humans are surprisingly good at depth ordering even with abstract 2D line drawings. In this paper we propose a learning based framework for discrete depth ordering inference.Boundary and junction characteristics are important clues for this task, and we have developed new features based on these attributes. Although each feature individually can produce reasonable depth ordering results, they still have limitations, and we can achieve better performance by combining them. In practice, local depth ordering inferences can be contradictory. Therefore, we propose a Markov Random Field model with terms that are more global than previous work, and use graph optimization to encourage a globally consistent ordering. In addition, to produce better object segmentation for the task of depth ordering, we propose to explicitly enforce closed loops and long edges for the occlusion boundary detection.We collect a new depth-order dataset for this problem, including more than a thousand human-labeled images with different daily objects in various configurations. The proposed algorithm gives promising performance over conventional methods on both synthetic and real scenes.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A learning-based framework for depth ordering

Jia

Gallagher²,

Chang

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Seeking for the global minimum of this criterion starting from the initial partition alone has proven to be difficult, as C(D) is extremely non-convex, with many local minima. The work in [29] attempts to find a global minimum by searching for the optimal solution with a RANSAC-style algorithm. For images with few T-junctions, the solution found can be near the optimal.…”

Section: Minimization Processmentioning

confidence: 99%

“…For the first class of cues, each point of the image is assigned a confidence value, indicating the probability to be indeed a true T-junction. The confidence computation is performed, as in [29], during the BPT construction so as to introduce depth information into the region similarity measure (2).…”

Section: Occlusion Depth Cues Estimationmentioning

confidence: 99%

Monocular Depth Ordering Using T-Junctions and Convexity Occlusion Cues

Palou

Salembier

2013

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-This paper proposes a system that relates objects in an image using occlusion cues and arranges them according to depth. The system does not rely on a priori knowledge of the scene structure and focuses on detecting special points, such as T-junctions and highly convex contours, to infer the depth relationships between objects in the scene. The system makes extensive use of the binary partition tree as hierarchical region-based image representation jointly with a new approach for candidate T-junction estimation. Since some regions may not involve T-junctions, occlusion is also detected by examining convex shapes on region boundaries. Combining T-junctions and convexity leads to a system which only relies on low level depth cues and does not rely on semantic information. However, it shows a similar or better performance with the state-of-the-art while not assuming any type of scene.As an extension of the automatic depth ordering system, a semi-automatic approach is also proposed. If the user provides the depth order for a subset of regions in the image, the system is able to easily integrate this user information to the final depth order for the complete image. For some applications, user interaction can naturally be integrated, improving the quality of the automatically generated depth map.

show abstract

From Occlusion to Global Depth Order, a Monocular Approach

Rezaeirowshan

Ballester

Haro

2017

Communications in Computer and Information Science

View full text Add to dashboard Cite

Estimating 3D structure of the scene from a single image remains a challenging problem in computer vision. This paper proposes a novel approach to obtain a global depth order of objects by incorporating monocular perceptual cues such as T-junctions and object boundary convexity, which are local indicators of occlusions, together with physical cues, namely ground contact points. The proposed combination of these local cues complement each other and creates a more thorough partial depth order relationship. The different partial orders are then robustly aggregated using a Markov random chain approximation to obtain the most plausible global depth order. Experiments show that the proposed method excels in comparison to state of the art methods.

show abstract

Occlusion-based depth ordering on monocular images with Binary Partition Tree

Cited by 17 publications

References 4 publications

A learning-based framework for depth ordering

A learning-based framework for depth ordering

Monocular Depth Ordering Using T-Junctions and Convexity Occlusion Cues

From Occlusion to Global Depth Order, a Monocular Approach

Contact Info

Product

Resources

About