Approach to reduce light field sampling redundancy for flame temperature reconstruction.

Flame temperature measurement through a light field camera shows an attractive research interest due to its capabilities of obtaining spatial and angular rays' information by a single exposure. However, the sampling information collected by the light field camera is vast and most of them are redundant. The reconstruction process occupies a larger computing memory and time-consuming. We propose a novel approach i.e., feature rays under-sampling (FRUS) to reduce the light field sampling redundancy and thus improve the reconstruction efficiency. The proposed approach is evaluated through numerical and experimental studies. Effects of under-sampling methods, flame dividing voxels, noise levels and light field camera parameters are investigated. It has been observed that the proposed approach provides better anti-noise ability and reconstruction efficiency. It can be valuable not only for the flame temperature reconstruction but also for other applications such as particle image velocimetry and light field microscope.

A crowdsourcing semi-automatic image segmentation platform for cell biology.

State-of-the-art computer-vision algorithms rely on big and accurately annotated data, which are expensive, laborious and time-consuming to generate. This task is even more challenging when it comes to microbiological images, because they require specialized expertise for accurate annotation. Previous studies show that crowdsourcing and assistive-annotation tools are two potential solutions to address this challenge. In this work, we have developed a web-based platform to enable crowdsourcing annotation of image data; the platform is powered by a semi-automated assistive tool to support non-expert annotators to improve the annotation efficiency. The behavior of annotators with and without the assistive tool is analyzed, using biological images of different complexity. More specifically, non-experts have been asked to use the platform to annotate microbiological images of gut parasites, which are compared with annotations by experts. A quantitative evaluation is carried out on the results, confirming that the assistive tools can noticeably decrease the non-expert annotation's cost (time, click, interaction, etc.) while preserving or even improving the annotation's quality. The annotation quality of non-experts has been investigated using IoU (intersection over union), precision and recall; based on this analysis we propose some ideas on how to better design similar crowdsourcing and assistive platforms.

Automatic Annotation of Subsea Pipelines using Deep Learning.

Regulatory requirements for sub-sea oil and gas operators mandates the frequent inspection of pipeline assets to ensure that their degradation and damage are maintained at acceptable levels. The inspection process is usually sub-contracted to surveyors who utilize sub-sea Remotely Operated Vehicles (ROVs), launched from a surface vessel and piloted over the pipeline. ROVs capture data from various sensors/instruments which are subsequently reviewed and interpreted by human operators, creating a log of event annotations; a slow, labor-intensive and costly process. The paper presents an automatic image annotation framework that identifies/classifies key events of interest in the video footage viz. exposure, burial, field joints, anodes, and free spans. The reported methodology utilizes transfer learning with a Deep Convolutional Neural Network (ResNet-50), fine-tuned on real-life, representative data from challenging sub-sea environments with low lighting conditions, sand agitation, sea-life and vegetation. The network outputs are configured to perform multi-label image classifications for critical events. The annotation performance varies between 95.1% and 99.7% in terms of accuracy and 90.4% and 99.4% in terms of F1-Score depending on event type. The performance results are on a per-frame basis and corroborate the potential of the algorithm to be the foundation for an intelligent decision support framework that automates the annotation process. The solution can execute annotations in real-time and is significantly more cost-effective than human-only approaches.

Three-dimensional temperature field measurement of flame using a single light field camera.

Compared with conventional camera, the light field camera takes the advantage of being capable of recording the direction and intensity information of each ray projected onto the CCD (charge couple device) sensor simultaneously. In this paper, a novel method is proposed for reconstructing three-dimensional (3-D) temperature field of a flame based on a single light field camera. A radiative imaging of a single light field camera is also modeled for the flame. In this model, the principal ray represents the beam projected onto the pixel of the CCD sensor. The radiation direction of the ray from the flame outside the camera is obtained according to thin lens equation based on geometrical optics. The intensities of the principal rays recorded by the pixels on the CCD sensor are mathematically modeled based on radiative transfer equation. The temperature distribution of the flame is then reconstructed by solving the mathematical model through the use of least square QR-factorization algorithm (LSQR). The numerical simulations and experiments are carried out to investigate the validity of the proposed method. The results presented in this study show that the proposed method is capable of reconstructing the 3-D temperature field of a flame.