A 3D measurement method for specular surfaces based on polarization image sequences and machine learning

Abstract Background The Taylor Spatial Frame (TSF) has been widely used on tibia fractures. However, traditional radiograph measurement method is complicated and the reduction accuracy is not high enough for correcting residual deformities. We proposed the marker-3D measurement method to solve these problems. This study aimed to compare the reduction accuracy of the traditional radiograph measurement method and the marker-3D measurement method in tibia fracture treated with TSF. Methods From January 2016 to June 2019, A retrospective analysis was performed based on the patients with tibia fracture treated with TSF in Tianjin Hospital. Forty-one patients were qualified for this study, including 21 patients in the marker-3D measurement group (experimental group) and 20 patients in the traditional radiograph measurement group (control group). In the experimental group, CT scan was performed for 3D reconstruction with 6 markers installed on the TSF, to determine the adjusting plan; in the control group, the Anteroposterior (AP) and Lateral radiographs were performed for the deformity parameters. All fractures were corrected after TSF adjusting, and then X-rays were taken to measure the residual deformities. Results All patients reached functional reduction. The residual displacement deformity (RDD) in AP radiograph was 0.5 (0, 1.72) mm in experimental group and 1.74 (0.43, 3.67) mm in control group; the residual angle deformity (RAD) in AP radiograph was 0 (0, 1.25) ° in experimental group and 1.25 (0.62, 1.95) °in control group. As to the Lateral radiograph, the RDD was 0 (0, 1.22) mm in experimental group and 2.02 (0, 3.74) mm in control group; the RAD was 0 (0, 0) ° in experimental group and 1.42 (0, 1.93) ° in control group. Significant differences in all above comparisons were found between the groups (AP radiograph RDD: P = 0.024, RAD: P = 0.020; Lateral radiograph RDD: P = 0.016, RAD: P = 0.004). Conclusion Both groups achieved satisfactory fracture reduction. However, the residual deformities in the experimental group were significantly smaller. This study proved that the marker-3D measurement method could further improve the accuracy of the reduction.

Download Full-text

Multi-stage deep learning based single-frame fringe projection 3D measurement method

Infrared and Laser Engineering ◽

10.3788/irla20200023 ◽

2020 ◽

Vol 49 (6) ◽

pp. 20200023

Author(s):

张钊 Zhao Zhang ◽

韩博文 Bowen Han ◽

于浩天 Haotian Yu ◽

张毅 Yi Zhang ◽

郑东亮 Dongliang Zheng ◽

...

Keyword(s):

Deep Learning ◽

Measurement Method ◽

Fringe Projection ◽

3D Measurement ◽

Single Frame ◽

Multi Stage

Download Full-text

Measurement Method for Evaluating the Lockdown Policies during the COVID-19 Pandemic

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17155574 ◽

2020 ◽

Vol 17 (15) ◽

pp. 5574 ◽

Cited By ~ 2

Author(s):

Mohammed Al Zobbi ◽

Belal Alsinglawi ◽

Omar Mubin ◽

Fady Alnajjar

Keyword(s):

Machine Learning ◽

Infection Rate ◽

Global Economy ◽

Data Analytics ◽

Measurement Method ◽

Mean Absolute Error ◽

Absolute Error ◽

Decision Makers ◽

Machine Learning Classification ◽

Data Analyses

Coronavirus Disease 2019 (COVID-19) has affected day to day life and slowed down the global economy. Most countries are enforcing strict quarantine to control the havoc of this highly contagious disease. Since the outbreak of COVID-19, many data analyses have been done to provide close support to decision-makers. We propose a method comprising data analytics and machine learning classification for evaluating the effectiveness of lockdown regulations. Lockdown regulations should be reviewed on a regular basis by governments, to enable reasonable control over the outbreak. The model aims to measure the efficiency of lockdown procedures for various countries. The model shows a direct correlation between lockdown procedures and the infection rate. Lockdown efficiency is measured by finding a correlation coefficient between lockdown attributes and the infection rate. The lockdown attributes include retail and recreation, grocery and pharmacy, parks, transit stations, workplaces, residential, and schools. Our results show that combining all the independent attributes in our study resulted in a higher correlation (0.68) to the dependent value Interquartile 3 (Q3). Mean Absolute Error (MAE) was found to be the least value when combining all attributes.

Download Full-text