scholarly journals Data-Driven Object Pose Estimation in a Practical Bin-Picking Application

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6093
Author(s):  
Viktor Kozák ◽  
Roman Sushkov ◽  
Miroslav Kulich ◽  
Libor Přeučil
Keyword(s):  
Pose Estimation ◽  
Data Gathering ◽  
Data Driven ◽  
Fixed Position ◽  
Automatic Data ◽  
Direct Light ◽  
Data Driven Approach ◽  
Bin Picking ◽  
Object Pose Estimation ◽  
Metallic Parts

This paper addresses the problem of pose estimation from 2D images for textureless industrial metallic parts for a semistructured bin-picking task. The appearance of metallic reflective parts is highly dependent on the camera viewing direction, as well as the distribution of light on the object, making conventional vision-based methods unsuitable for the task. We propose a solution using direct light at a fixed position to the camera, mounted directly on the robot’s gripper, that allows us to take advantage of the reflective properties of the manipulated object. We propose a data-driven approach based on convolutional neural networks (CNN), without the need for a hard-coded geometry of the manipulated object. The solution was modified for an industrial application and extensively tested in a real factory. Our solution uses a cheap 2D camera and allows for a semi-automatic data-gathering process on-site.

Contour clustering: A field-data-driven approach for documenting and analysing prototypical f0 contours

2021 ◽  
pp. 1-30
Author(s):  
Constantijn Kaland
Keyword(s):  
Cluster Analysis ◽  
User Interfaces ◽  
Data Driven ◽  
Language Documentation ◽  
Cluster Number ◽  
Automatic Data ◽  
Speaker Variability ◽  
The Core ◽  
Data Driven Approach ◽  
Confirmatory Analysis

ABSTRACT This paper reports an automatic data-driven analysis for describing prototypical intonation patterns, particularly suitable for initial stages of prosodic research and language description. The approach has several advantages over traditional ways to investigate intonation, such as the applicability to spontaneous speech, language- and domain-independency, and the potential of revealing meaningful functions of intonation. These features make the approach particularly useful for language documentation, where the description of prosody is often lacking. The core of this approach is a cluster analysis on a time-series of f0 measurements and consists of two scripts (Praat and R, available from https://constantijnkaland.github.io/contourclustering/). Graphical user interfaces can be used to perform the analyses on collected data ranging from spontaneous to highly controlled speech. There is limited need for manual annotation prior to analysis and speaker variability can be accounted for. After cluster analysis, Praat textgrids can be generated with the cluster number annotated for each individual contour. Although further confirmatory analysis is still required, the outcomes provide useful and unbiased directions for any investigation of prototypical f0 contours based on their acoustic form.

scholarly journals Fast Object Pose Estimation Using Adaptive Threshold for Bin-Picking

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 63055-63064 ◽  
Author(s):  
Wu Yan ◽  
Zhihao Xu ◽  
Xuefeng Zhou ◽  
Qianxing Su ◽  
Shuai Li ◽  
...  
Keyword(s):  
Pose Estimation ◽  
Adaptive Threshold ◽  
Bin Picking ◽  
Object Pose Estimation

scholarly journals Object Pose Estimation for Robot Loading in Accommodation Space Using Alpha-Shape Algorithm

2021 ◽  
Author(s):  
Qingda Guo ◽  
Lulu Tang ◽  
Jianchi Zhang
Keyword(s):  
Pose Estimation ◽  
Fruit Fly ◽  
Fruit Fly Optimization Algorithm ◽  
Fruit Fly Optimization ◽  
Alpha Shape ◽  
Accommodation Space ◽  
Bin Picking ◽  
Object Pose Estimation ◽  
The Common ◽  
Setting Parameters

Abstract Robots with visual sensors have been used in various goods logistics, such as bin picking or uploading. However, there are more and more demands for the automatic blanking and loading, it is necessary to solve the problem of object pose estimation in changing accommodation space. This paper proposes a method for pose estimation in the accommodation space using alpha-shape algorithm and improved Fruit fly Optimization Algorithm (FOA). The alpha-shape volume variety of object and measured space is set to the objective function and the pose variety of object is set to six variables of improved FOA. The experiments were performed by setting parameters of improved FOA and considering the four space types represented the common accommodation shapes. Compared with previous work using convex hull, the new study using alpha-shape algorithm not only keeps the object in the accommodation space, but also maintains the object pose is at the bottom of the space and can meet the practical requirement of object placement by robot arms.

scholarly journals The French domestic "sanitary pass" did not solve Covid-19 vaccination inequities in France

2022 ◽  
Author(s):  
Florence Débarre ◽  
Emmanuel Lecoeur ◽  
Lucie Guimier ◽  
Marie Jauffret-Roustide ◽  
Anne-Sophie Jannot
Keyword(s):  
Data Gathering ◽  
Data Driven ◽  
Geographic Factors ◽  
Vaccination Rates ◽  
Before And After ◽  
Data Driven Approach ◽  
Deprived Areas

The French sanitary pass led to an increase in vaccination rates in France, but local heterogeneities in vaccination rates remain. To identify potential determinants of these heterogeneities and how the French sanitary pass influenced them, we used a data-driven approach on exhaustive nationwide data, gathering 181 socio-economic and geographic factors. Our analysis reveals that, both before and after the introduction of the French sanitary pass, factors with the largest impact are related to poverty, with the most deprived areas having greater than 10 times the odds of being among the districts with lower vaccination rates.

scholarly journals Restructuring ENT out-patient services during the coronavirus disease 2019 pandemic – an iterative approach

2020 ◽  
Vol 134 (8) ◽  
pp. 670-679 ◽  
Author(s):  
M Halliwell-Ewen ◽  
B Atkin ◽  
C T Huins ◽  
C L Dalton
Keyword(s):  
National Health Service ◽  
Data Gathering ◽  
Significant Rise ◽  
Data Driven ◽  
Iterative Approach ◽  
End Points ◽  
Patient Capacity ◽  
Data Driven Approach ◽  
Patient Work ◽  
Procedure Duration

AbstractBackgroundCoronavirus disease 2019 has demanded enormous adjustments to National Health Service provisions. Non-urgent out-patient work was initially postponed or performed virtually, but is now being re-established. In ENT surgery, aerosol-generating procedures pose a particular challenge in out-patient settings.ObjectiveA rapid restructuring of ENT out-patient services is required, to safely accommodate aerosol-generating procedures and increase in-person attendances, whilst coronavirus disease 2019 persists.MethodsData were collected prospectively over four consecutive cycles. Two surveys were conducted. Results were analysed and disseminated, with recommendations for service restructuring implemented at cycle end-points.ResultsOut-patient activity increased four-fold, associated with a significant rise in aerosol-generating procedures during the study period. Mean aerosol-generating procedure duration dropped weekly, implying a learning curve. Service restructuring occurred at cycle end-points.ConclusionIterative data gathering, results analysis and outcome dissemination enabled a swift, data-driven approach to the restructuring of ENT out-patient services. Patient and staff safety was ensured, whilst out-patient capacity was optimised.

Sign in / Sign up

Export Citation Format

Share Document