Multi Scale Shape Index for 3D Object Recognition

Bonde, Ujwal; Badrinarayanan, Vijay; Cipolla, Roberto

doi:10.1007/978-3-642-38267-3_26

Cited by 10 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Multi-scale Shape Index (MSSI) [45] is an extension of Koenderink's Shape Index (SI) [46]. The MSSI evaluates shapes at the optimal scale.…”

Section: The Morphology Of the Land Surface Temperaturementioning

confidence: 99%

“…As the smoothing shifts the original point, the characteristic scale can be found in terms of the kernel size that produces the maximum normalized distance d traveled by a point in the scale space [45]. Since the distance traveled is along the kernel magnitude, the shifted distance caused by the kernel smoothing on an image surface is simply the difference between the original and the smoothed pixel values.…”

Section: The Morphology Of the Land Surface Temperaturementioning

confidence: 99%

“…However, the MSSI alone does not capture complete information on the latent morphology [46]. Objects with the same shape yet different sizes cannot be distinguished only by using the MSSI, thus the use of curvedness is also recommended [45]. The curvedness is calculated at the optimal scale θ* based upon the principle curvatures through …”

Section: The Morphology Of the Land Surface Temperaturementioning

confidence: 99%

See 2 more Smart Citations

The Morphology, Dynamics and Potential Hotspots of Land Surface Temperature at a Local Scale in Urban Areas

2015

View full text Add to dashboard Cite

Current characterization of the Urban Heat Island (UHI) remains insufficient to support the effective mitigation and adaptation of increasing temperatures in urban areas. Planning and design strategies are restricted to the investigation of temperature anomalies at a city scale. By focusing on Land Surface Temperature of Wuhan, China, this research examines the temperature variations locally where mitigation and adaptation would be more feasible. It shows how local temperature anomalies can be identified morphologically. Technically, the MODerate-resolution Imaging Spectroradiometer satellite image products are used. They are first considered as noisy observations of the latent temperature patterns. The continuous latent patterns of the temperature are then recovered from these discrete observations by using the non-parametric Multi-Task Gaussian Process Modeling. The Multi-Scale Shape Index is then applied in the area of focus to extract the local morphological features. A triplet of shape, curvedness and temperature is formed as the criteria to extract local heat islands. The behavior of the local heat islands can thus be quantified morphologically. The places with critical deformations are identified as hotpots. The hotspots with certain yearly behavior are further associated with land surface composition to determine effective mitigation and adaptation strategies. This research can assist in the temperature and planning field on two levels: (1) the local land surface temperature patterns are characterized by decomposing the variations into fundamental deformation modes to allow a process-based understanding of the dynamics; and (2) the characterization at local scale conforms to planning and design conventions where mitigation and adaptation strategies are supposed to be more practical. The weaknesses and limitations of the study are addressed in the closing section.

show abstract

“…The Multi-scale Shape Index (MSSI) [45] is an extension of Koenderink's Shape Index (SI) [46]. The MSSI evaluates shapes at the optimal scale.…”

Section: The Morphology Of the Land Surface Temperaturementioning

confidence: 99%

Section: The Morphology Of the Land Surface Temperaturementioning

confidence: 99%

Section: The Morphology Of the Land Surface Temperaturementioning

confidence: 99%

See 1 more Smart Citation

The Morphology, Dynamics and Potential Hotspots of Land Surface Temperature at a Local Scale in Urban Areas

2015

View full text Add to dashboard Cite

show abstract

“…Using the multi-scale method of Bonde et al [3] we calculate the two principal curvatures λ 1 , λ 2 for every point on the point cloud. We only consider the magnitude of the principal curvatures.…”

Section: Edgelet Detectionmentioning

confidence: 99%

Robust Instance Recognition in Presence of Occlusion and Clutter

Bonde

Badrinarayanan

Cipolla

2014

Computer Vision – ECCV 2014

Self Cite

View full text Add to dashboard Cite

Abstract. We present a robust learning based instance recognition framework from single view point clouds. Our framework is able to handle real-world instance recognition challenges, i.e, clutter, similar looking distractors and occlusion. Recent algorithms have separately tried to address the problem of clutter [9] and occlusion [16] but fail when these challenges are combined. In comparison we handle all challenges within a single framework. Our framework uses a soft label Random Forest [5] to learn discriminative shape features of an object and use them to classify both its location and pose. We propose a novel iterative training scheme for forests which maximizes the margin between classes to improve recognition accuracy, as compared to a conventional training procedure. The learnt forest outperforms template matching, DPM [7] in presence of similar looking distractors. Using occlusion information, computed from the depth data, the forest learns to emphasize the shape features from the visible regions thus making it robust to occlusion. We benchmark our system with the state-of-the-art recognition systems [9,7] in challenging scenes drawn from the largest publicly available dataset. To complement the lack of occlusion tests in this dataset, we introduce our Desk3D dataset and demonstrate that our algorithm outperforms other methods in all settings.

show abstract

“…The Multi-Scale Shape Index (MSSI) (Bonde et al, 2013) is an extension of Koenderink's Shape Index (SI) (Koenderink and van Doorn, 1992) that evaluates shapes at the optimal scale. It thus contains 2 steps: 1) scale selection, and 2) the SI evaluation.…”

Section: The Morphological Indicatorsmentioning

confidence: 99%

Identifying the Local Surface Urban Heat Island Through the Morphology of the Land Surface Temperature

Wang

Zhan

Xiao

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Current characterization of the Land Surface Temperature (LST) at city scale insufficiently supports efficient mitigations and adaptations of the Surface Urban Heat Island (SUHI) at local scale. This research intends to delineate the LST variation at local scale where mitigations and adaptations are more feasible. At the local scale, the research helps to identify the local SUHI (LSUHI) at different levels. The concept complies with the planning and design conventions that urban problems are treated with respect to hierarchies or priorities. Technically, the MODerate-resolution Imaging Spectroradiometer satellite image products are used. The continuous and smooth latent LST is first recovered from the raw images. The Multi-Scale Shape Index (MSSI) is then applied to the latent LST to extract morphological indicators. The local scale variation of the LST is quantified by the indicators such that the LSUHI can be identified morphologically. The results are promising. It can potentially be extended to investigate the temporal dynamics of the LST and LSUHI. This research serves to the application of remote sensing, pattern analysis, urban microclimate study, and urban planning at least at 2 levels: (1) it extends the understanding of the SUHI to the local scale, and (2) the characterization at local scale facilitates problem identification and support mitigations and adaptations more efficiently.

show abstract

Multi Scale Shape Index for 3D Object Recognition

Cited by 10 publications

References 23 publications

The Morphology, Dynamics and Potential Hotspots of Land Surface Temperature at a Local Scale in Urban Areas

The Morphology, Dynamics and Potential Hotspots of Land Surface Temperature at a Local Scale in Urban Areas

Robust Instance Recognition in Presence of Occlusion and Clutter

Identifying the Local Surface Urban Heat Island Through the Morphology of the Land Surface Temperature

Contact Info

Product

Resources

About