In this study, an estimation method for human height is proposed using color and depth information. Color images are used for deep learning by mask R-CNN to detect a human body and a human head separately. If color images are not available for extracting the human body region due to low light environment, then the human body region is extracted by comparing between current frame in depth video and a pre-stored background depth image. The topmost point of the human head region is extracted as the top of the head and the bottommost point of the human body region as the bottom of the foot. The depth value of the head top-point is corrected to a pixel value that has high similarity to a neighboring pixel. The position of the body bottom-point is corrected by calculating a depth gradient between vertically adjacent pixels. Two head-top and foot-bottom points are converted into 3D real-world coordinates using depth information. Two real-world coordinates estimate human height by measuring a Euclidean distance. Estimation errors for human height are corrected as the average of accumulated heights. In experiment results, we achieve that the estimated errors of human height with a standing state are 0.7% and 2.2% when the human body region is extracted by mask R-CNN and the background depth image, respectively.

This paper proposes a method to classify food types and to estimate meal intake amounts in pre- and post-meal images through a deep learning object detection network. The food types and the food regions are detected through Mask R-CNN. In order to make both pre- and post-meal images to a same capturing environment, the post-meal image is corrected through a homography transformation based on the meal plate regions in both images. The 3D shape of the food is determined as one of a spherical cap, a cone, and a cuboid depending on the food type. The meal intake amount is estimated as food volume differences between the pre-meal and post-meal images. As results of the simulation, the food classification accuracy and the food region detection accuracy are up to 97.57% and 93.6%, respectively.

In this paper, we propose an amount estimation method for food intake based on both color and depth images. Two pairs of color and depth images are captured pre- and post-meals. The pre- and post-meal color images are employed to detect food types and food existence regions using Mask R-CNN. The post-meal color image is spatially transformed to match the food region locations between the pre- and post-meal color images. The same transformation is also performed on the post-meal depth image. The pixel values of the post-meal depth image are compensated to reflect 3D position changes caused by the image transformation. In both the pre- and post-meal depth images, a space volume for each food region is calculated by dividing the space between the food surfaces and the camera into multiple tetrahedra. The food intake amounts are estimated as the difference in space volumes calculated from the pre- and post-meal depth images. From the simulation results, we verify that the proposed method estimates the food intake amount with an error of up to 2.2%.

This paper proposes an indoor positioning method based on Bluetooth Low Energy signals by Convolution Neural Network-Long Short-Term Memory (CNN-LSTM). The proposed method determines a receiver location based on distances from adjacent transmitters. The CNN-LSTM model estimates the distance from each transmitter using continuous signal strengths. To train and validate the model, the signal strengths are collected in several locations within various indoor environments. The positioning technique is adaptively selected based on the highest signal strength to avoid the interfering problem due to an excessively strong signal. If the signal strength exceeds a certain threshold, the location is determined using the proximity technique, which utilizes only the strongest signal instead of triangulation. In the experimental results, the proposed method demonstrated an average error of about 2.90 m, which is 34.2% better than a triangulation-based positioning method that does not utilize neural networks.

In this article, we propose a depth data coding method by plane modeling. The plane modeling is a prediction method based on a plane estimation from depth pixels in a block. The plane modeling improves the intra-picture prediction for depth data comparing with intra modes of conventional coding standards. The plane modeling coefficients, which are the information about the estimated plane, are required to be provided during the depth data coding. The plane modeling coefficients are predicted from neighboring depth pixels. A prediction error of the plane modeling coefficients is calculated through the plane modeling for the selected pixels. If the prediction error is below a certain threshold, then the plane modeling coefficients are applied to the plane modeling for the block. From the simulation results, we verify that the proposed method achieves up to 6.76% bit rate saving in the same coding distortion condition compared to VVC test model.

In this paper, we propose a proximity-based adaptive positioning algorithm to address the challenge of positioning errors in indoor localization based on RSSI (received signal strength indicator). When positioning by trilateration, if a receiver is close to one AP, the signals of other APs become rapidly unstable, so positioning accuracy is reduced. Therefore, this paper proposes an algorithm to identify the proximity state with AP and adaptively determine the positioning technique based on this state. The proposed algorithm consists of three steps: RSSI error correction, adaptive location estimation, and post-processing. The RSSI error correction step corrects unstable RSSI. The adaptive location estimation step utilizes a modified proximity technique when identified as close to an AP, employing trilateration otherwise. Finally, in the post-processing step, an efficient filtering algorithm is applied. For the static state experiment, the accuracy of the proposed algorithm is found to be improved by about 28% compared to the method measured using only the trilateration technique applying the RSSI error correction step and post-processing step. The proposed algorithm improved the positioning accuracy of the entire area by improving accuracy in regions with weak signals without additional devices.