Lazy Generic Cuts

Khandelwal, Dinesh; Bhatia, Kush; Arora, Chetan; Singla, Parag

doi:10.1016/j.cviu.2015.10.016

Cited by 7 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performed large scale experiments and the acquired quite promising results demonstrate the extreme potentials of the developed method. The integration of prior knowledge regarding texture and geometric features under a higher order formulation [10], [13] is currently under consideration and a GPU implementation is among the future perspectives as well.…”

Section: Discussionmentioning

confidence: 99%

Graph-Based Registration, Change Detection, and Classification in Very High Resolution Multitemporal Remote Sensing Data

Vakalopoulou

Καράντζαλος

Komodakis

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

International audienceIn this paper we propose a modular, scalable, metric-free, single-shot change detection/registration method. The developed framework exploits the relation between the registration and change detection problems, while under a fruitful synergy the coupling energy term constrains adequately both tasks. In particular, through a decomposed interconnected graphical model the registration similarity constraints are relaxed in the presence of change detection. Moreover, the deformation space is discretized, while efficient linear programming and duality principles are used to optimize a joint solution space where local consistency is imposed on the deformation and the detection space as well. The proposed formulation is able to operate in a fully unsupervised manner addressing binary change detection problems i.e., change or no-change with respect to different similarity metrics. Furthermore, the framework has been formulated to address automatically the detection of from-to change trajectories under a supervised setting. Promising results on large scale experiments demonstrate the extreme potentials of our method

show abstract

Section: Discussionmentioning

confidence: 99%

Graph-Based Registration, Change Detection, and Classification in Very High Resolution Multitemporal Remote Sensing Data

Vakalopoulou

Καράντζαλος

Komodakis

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Through experimental simulations across three distinct scenarios, it was observed that the ACO algorithm was less suitable for grid scheduling problems, as it consumed considerably more computational time compared to other existing evolutionary models. Khandelwala et al [12] developed a lazy version of Generic Cuts (GC) by leveraging the observation in many inference problems, a substantial portion of the constraints had never been utilized during the minimization process. Experimental results indicated that the algorithm typically required less than 3% of the total constraints.…”

Section: Related Workmentioning

confidence: 99%

Condition monitoring of electric vehicle motor testing machine’s Vital components using bagged trees and quadratic SVM: a comparative study

Ravi Kumar,

Syed Wahid Ali,

Pandian

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

The future of the automotive industry lies in the utilization of electric vehicles (EVs). A crucial component of these EVs is the drive motor. The verification of critical parameters for the electrical motor is considered to be of utmost importance, and this is achieved through the use of a motor testing machine. The motor testing machine is utilized frequently to determine characteristic curve points and the electromagnetic behavior of electric motors under various conditions. However, it has been observed that the presence of a fault in the helical gear setup of the testing machine leads to frequent breakdowns and suboptimal performance, thereby affecting the efficiency of the assembly line in the production of electric vehicles. In light of these observations, the main objective of this research endeavor is to improve the motor test bench apparatus by altering essential design parameters through the utilization of vibration signal analysis and machine learning techniques. Prior to extracting statistical features, vibration signals are obtained at different gear settings. These signals are subsequently categorized using classifiers such as Bagged Trees and Quadratic SVM. Machine learning techniques are utilized to classify the gathered signals as either normal or faulty, both with and without the inclusion of a 0.25 KW load for each condition. The performance of multiple algorithms is evaluated and scrutinized. The results have demonstrated that the Bagged Trees technique outperforms the other algorithm, achieving an impressive accuracy of 95.3%. Consequently, the proposed method presents an adept solution for augmenting the motor test bench’s capability by modifying crucial design parameters.

show abstract

“…Furthermore, in [17] an efficient method to infer solutions for higher order graphical models with submodular potentials was presented while in [18] a submodular relaxation approach was proposed for pair-wise and higher order graphical models inference. More recently [19] tackled higher order inference for graphical models which can be expressed as the minimization of partially separable function of discrete variables, while in [20] the principle of active constraints adaptively learnt over multiple iterations was adopted. Further aspects on inference, and specifically on the most commonly used optimization principles in the context of graphical models, are discussed in [21].…”

Section: Inference On Graphical Modelsmentioning

confidence: 99%

(Hyper)-graphical models in biomedical image analysis

Paragios

Ferrante

Glocker

et al. 2016

Medical Image Analysis

View full text Add to dashboard Cite

Computational vision, visual computing and biomedical image analysis have made tremendous progress over the past two decades. This is mostly due the development of efficient learning and inference algorithms which allow better and richer modeling of image and visual understanding tasks. Hyper-Graph representations are among the most prominent tools to address such perception through the casting of perception as a graph optimization problem. In this paper, we briefly introduce the importance of such representations, discuss their strength and limitations, provide appropriate strategies for their inference and present their application to address a variety of problems in biomedical image analysis.

show abstract

Lazy Generic Cuts

Cited by 7 publications

References 23 publications

Graph-Based Registration, Change Detection, and Classification in Very High Resolution Multitemporal Remote Sensing Data

Graph-Based Registration, Change Detection, and Classification in Very High Resolution Multitemporal Remote Sensing Data

Condition monitoring of electric vehicle motor testing machine’s Vital components using bagged trees and quadratic SVM: a comparative study

(Hyper)-graphical models in biomedical image analysis

Contact Info

Product

Resources

About