Quantized Residual Preference Based Linkage Clustering for Model Selection and Inlier Segmentation in Geometric Multi-Model Fitting

Zhao, Qing; Zhang, Yun; Qin, Qianqing; Luo, Bin

doi:10.3390/s20133806

Cited by 9 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other techniques follow a preference-based approach and focus on clustering as a basis to perform model estimation. Examples of methods in this category include Residual Histogram Analysis (RHA) (Zhang and Kosecká 2006), J-Linkage (Toldo and Fusiello 2008), Kernel Optimization (Chin et al 2010), T-linkage (Magri and Fusiello 2014), Random Cluster Model (RCM) (Pham et al 2014), Robust Preference Analysis (RPA) (Magri and Fusiello 2015) and Quantized Residual Preference (Zhao et al 2020). The problem of fitting multiple models can be also formulated as an energy minimization problem (Delong et al 2012a, b), as in PEARL (Propose Expand and Reestimate Labels) (Isack and Boykov 2012) and Multi-X (Barath and Matas 2018).…”

Section: Multi-model Fittingmentioning

confidence: 99%

Multi-frame Motion Segmentation by Combining Two-Frame Results

2022

View full text Add to dashboard Cite

In this paper we consider the motion segmentation problem on sparse and unstructured datasets involving rigid motions, motivated by multibody structure from motion. In particular, we assume only two-frame correspondences as input without prior knowledge about trajectories. Inspired by the success of synchronization methods, we address this problem by introducing a two-stage approach: first, motion segmentation is addressed on image pairs independently; then, two-frame results are combined in a robust way to compute the final multi-frame segmentation. Our synthetic and real experiments demonstrate that the proposed approach is very effective in reducing the errors among two-frame results and it can cope with a large amount of mismatches. Moreover, our method can be profitably used to build a multibody structure from motion pipeline.

show abstract

Section: Multi-model Fittingmentioning

confidence: 99%

Multi-frame Motion Segmentation by Combining Two-Frame Results

2022

View full text Add to dashboard Cite

show abstract

“…The traditional multi-motion segmentation method [21], [22], [23], [24] using powerful geometric constraints cluster points of the scene into objects with different motion models. This type of method is at the feature point level instead of instance-level, limited by the model number of the segmentation and has a high computational burden.…”

Section: Related Work a Moving Object Segmentationmentioning

confidence: 99%

RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions

Wang¹,

Li²,

Luo³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Segmenting each moving object instance in a scene is essential for many applications. But like many other computer vision tasks, this task performs well in optimal weather, but then adverse weather tends to fail. To be robust in weather conditions, the usual way is to train network in data of given weather pattern or to fuse multiple sensors. We focus on a new possibility, that is, to improve its resilience to weather interference through the network's structural design. First, we propose a novel FPN structure called RiWFPN with a progressive topdown interaction and attention refinement module. RiWFPN can directly replace other FPN structures to improve the robustness of the network in non-optimal weather conditions. Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet. Finally, in order to verify the effect of moving instance segmentation in different weather disturbances, we propose a VKTTI-moving dataset which is a moving instance segmentation dataset based on the VKTTI dataset, taking into account different weather scenes such as rain, fog, sunset, morning as well as overcast. The experiment proves how RiWFPN improves the network's resilience to adverse weather effects compared to other FPN structures. We compare RiWNet to several other state-of-theart methods in some challenging datasets, and RiWNet shows better performance especially under adverse weather conditions.

show abstract

“…The multi-motion segmentation method [12,13,[46][47][48] based on geometric methods involves clustering points of the same motion into a motion model parameter instance to segment the multiple motion models of the scene, which can be utilized to discover new objects based on their motion. This kind of method obtains the results at the feature point level, instead of pixel by pixel, and the application conditions and scenarios are limited.…”

Section: Motion Segmentationmentioning

confidence: 99%

U2-ONet: A Two-Level Nested Octave U-Structure Network with a Multi-Scale Attention Mechanism for Moving Object Segmentation

Wang

et al. 2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Most scenes in practical applications are dynamic scenes containing moving objects, so accurately segmenting moving objects is crucial for many computer vision applications. In order to efficiently segment all the moving objects in the scene, regardless of whether the object has a predefined semantic label, we propose a two-level nested octave U-structure network with a multi-scale attention mechanism, called U2-ONet. U2-ONet takes two RGB frames, the optical flow between these frames, and the instance segmentation of the frames as inputs. Each stage of U2-ONet is filled with the newly designed octave residual U-block (ORSU block) to enhance the ability to obtain more contextual information at different scales while reducing the spatial redundancy of the feature maps. In order to efficiently train the multi-scale deep network, we introduce a hierarchical training supervision strategy that calculates the loss at each level while adding knowledge-matching loss to keep the optimization consistent. The experimental results show that the proposed U2-ONet method can achieve a state-of-the-art performance in several general moving object segmentation datasets.

show abstract

Quantized Residual Preference Based Linkage Clustering for Model Selection and Inlier Segmentation in Geometric Multi-Model Fitting

Cited by 9 publications

References 33 publications

Multi-frame Motion Segmentation by Combining Two-Frame Results

Multi-frame Motion Segmentation by Combining Two-Frame Results

RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions

U2-ONet: A Two-Level Nested Octave U-Structure Network with a Multi-Scale Attention Mechanism for Moving Object Segmentation

Contact Info

Product

Resources

About