Dataset Information

Estimating Dining Plate Size From an Egocentric Image Sequence Without a Fiducial Marker.

ABSTRACT: Despite the extreme importance of food intake in human health, it is currently difficult to conduct an objective dietary assessment without individuals' self-report. In recent years, a passive method utilizing a wearable electronic device has emerged. This device acquires food images automatically during the eating process. These images are then analyzed to estimate intakes of calories and nutrients, assisted by advanced computational algorithms. Although this passive method is highly desirable, it has been thwarted by the requirement of a fiducial marker which must be present in the image for a scale reference. The importance of this scale reference is analogous to the importance of the scale bar in a map which determines distances or areas in any geological region covered by the map. Likewise, the sizes or volumes of arbitrary foods on a dining table covered by an image cannot be determined without the scale reference. Currently, the fiducial marker (often a checkerboard card) serves as the scale reference which must be present on the table before taking pictures, requiring human efforts to carry, place and retrieve the fiducial marker manually. In this work, we demonstrate that the fiducial marker can be eliminated if an individual's dining location is fixed and a one-time calibration using a circular plate of known size is performed. When the individual uses another circular plate of an unknown size, our algorithm estimates its radius using the range of pre-calibrated distances between the camera and the plate from which the desired scale reference is determined automatically. Our comparative experiment indicates that the mean absolute percentage error of the proposed estimation method is ~10.73%. Although this error is larger than that of the manual method of 6.68% using a fiducial marker on the table, the new method has a distinctive advantage of eliminating the manual procedure and automatically generating the scale reference.

SUBMITTER: Jia W

PROVIDER: S-EPMC7840562 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimating Dining Plate Size From an Egocentric Image Sequence Without a Fiducial Marker.

Jia Wenyan W Wu Zekun Z Ren Yiqiu Y Cao Shunxin S Mao Zhi-Hong ZH Sun Mingui M

Frontiers in nutrition 20210114

Despite the extreme importance of food intake in human health, it is currently difficult to conduct an objective dietary assessment without individuals' self-report. In recent years, a passive method utilizing a wearable electronic device has emerged. This device acquires food images automatically during the eating process. These images are then analyzed to estimate intakes of calories and nutrients, assisted by advanced computational algorithms. Although this passive method is highly desirable, ...[more]

PMID: 33521029

Similar Datasets

Project description:The true extent of a tumor is difficult to visualize, during radiotherapy, using current modalities. In the present study, the safety and feasibility of a mixture of N-butyl cyanoacrylate and lipiodol (NBCA/Lip) was evaluated in order to investigate the optimal combination for application as a fiducial marker for radiotherapy. Four combinations of NBCA/Lip injection (1:1-0.1, 1:1-0.15, 1:3-0.1 and 1:3-0.15 ml) were injected into the subcutaneous tissue of BALB/c mice. The changes in gross histopathology, body weight, skin score, marker volume, neutrophil and macrophage counts were observed to analyze the effects of the different mixing ratios and injection volumes, in order to identify the best combination. Evaluation according to the International Organization for Standardization criteria was further conducted in order to test the biocompatibility of the mixture, including an acute systematic assay with mice, cytotoxicity with L929 fibroblasts and delayed-type hypersensitivity tests with guinea pigs and an intradermal test with rabbits. The results revealed that at the seventh week, 42 markers (42/48; 87.5%) were still visible using computed tomography (CT) imaging. No serious adverse effects were observed throughout the study period; however, the combination of 1:1-0.1 ml had the lowest body weight and worst skin score. A review of the histopathological reaction to NBCA/Lip revealed a combination of acute inflammation, chronic inflammation, granulation tissue, foreign-body reaction and fibrous capsule formation. The 1:1 NBCA combination ratio resulted in the most intense tissue repair reaction and a slower degradation rate of markers. In general, the combination of 1:3-0.15 ml had a better fusion with local tissue, maintained a stable imaging nodule on CT images for 7 weeks and the final biocompatibility test demonstrated its safety. Overall, the findings of the present study demonstrated NBCA/Lip as a safe and feasible fiducial marker, when using the 1:3-0.15 ml combination.

Dataset Information

Estimating Dining Plate Size From an Egocentric Image Sequence Without a Fiducial Marker.

Publications

Estimating Dining Plate Size From an Egocentric Image Sequence Without a Fiducial Marker.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets