Point cloud completion in challenging indoor scenarios with human motion

Combining and completing point cloud data from two or more sensors with arbitrarily relative perspectives in a dynamic, cluttered, and complex environment is challenging, especially when the two sensors have significant perspective differences while the large overlap ratio and feature-rich scene cannot be guaranteed. We create a novel approach targeting this challenging scenario by registering two camera captures in a time series with unknown perspectives and human movements to easily use our system in a real-life scene. In our approach, we first reduce the six unknowns of 3D point cloud completion to three by aligning the ground planes found by our previous perspective-independent 3D ground plane estimation algorithm. Subsequently, we use a histogram-based approach to identify and extract all the humans from each frame generating a three-dimensional (3D) human walking sequence in a time series. To enhance accuracy and performance, we convert 3D human walking sequences to lines by calculating the center of mass (CoM) point of each human body and connecting them. Finally, we match the walking paths in different data trials by minimizing the Fréchet distance between two walking paths and using 2D iterative closest point (ICP) to find the remaining three unknowns in the overall transformation matrix for the final alignment. Using this approach, we can successfully register the corresponding walking path of the human between the two cameras' captures and estimate the transformation matrix between the two sensors.

Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera

Face masks can effectively prevent the spread of viruses. It is necessary to determine the wearing condition of masks in various locations, such as traffic stations, hospitals, and other places with a risk of infection. Therefore, achieving fast and accurate identification in different application scenarios is an urgent problem to be solved. Contactless mask recognition can avoid the waste of human resources and the risk of exposure. We propose a novel method for face mask recognition, which is demonstrated using the spatial and frequency features from the 3D information. A ToF camera with a simple system and robust data are used to capture the depth images. The facial contour of the depth image is extracted accurately by the designed method, which can reduce the dimension of the depth data to improve the recognition speed. Additionally, the classification process is further divided into two parts. The wearing condition of the mask is first identified by features extracted from the facial contour. The types of masks are then classified by new features extracted from the spatial and frequency curves. With appropriate thresholds and a voting method, the total recall accuracy of the proposed algorithm can achieve 96.21%. Especially, the recall accuracy for images without mask can reach 99.21%.

A novel auricular prosthesis which incorporates a cartilage conduction hearing aid based on 3D data processing technique: a preclinical evaluation

PURPOSE

To achieve the challenging goal of simultaneously improving aesthetics and auditory function in the treatment of microtia, we developed an auricular prosthesis incorporating a cartilage conduction hearing aid (APiCHA), which covers a cartilage conduction hearing aid (CC-HA). We evaluated the acoustic characteristics generated by the method of combining these two components using an artificial mastoid and investigated the possibility of clinical translation.

METHODS

The first step in creating an APiCHA is to take molds of both the affected and normal auricles and invert the 3D data of the normal auricle to create data for the auricular prostheses. Grooves were then made inside the prosthetic data to fit the affected ear and a CC-HA, and the APiCHA was made of silicone. The acoustic characteristics were measured using an artificial mastoid, and the results were compared between CC-HA alone and with APiCHA.

RESULTS

Compared with CC-HA alone, the gain was approximately 2 dB lower at high frequencies from 1 k Hz and higher, and approximately 2 dB higher at approximately 900 Hz when CC-HA was used with APiCHA. For the other frequencies, the acoustic characteristics were almost the same.

CONCLUSION

The changes in acoustic characteristics caused by the combined use of APiCHA and CC-HA were minimal and did not pose a clinical problem. The combined use of APiCHA and CC-HA can be considered as a non-invasive and clinically applicable treatment option to achieve both aesthetic and auditory improvements for microtia.

Passing through Open/Closed Doors: A Solution for 3D Scanning Robots

In this article, a traversing door methodology for building scanning mobile platforms is proposed. The problem of passing through open/closed doors entails several actions that can be implemented by processing 3D information provided by dense 3D laser scanners. Our robotized platform, denominated as MoPAD (Mobile Platform for Autonomous Digitization), has been designed to collect dense 3D data and generate basic architectural models of the interiors of buildings. Moreover, the system identifies the doors of the room, recognises their respective states (open, closed or semi-closed) and completes the aforementioned 3D model, which is later integrated into the robot global planning system. This document is mainly focused on describing how the robot navigates towards the exit door and passes to a contiguous room. The steps of approaching, door-handle recognition/positioning and handle-robot arm interaction (in the case of a closed door) are shown in detail. This approach has been tested using our MoPAD platform on the floors of buildings composed of several rooms in the case of open doors. For closed doors, the solution has been formulated, modeled and successfully tested in the Gazebo robot simulation tool by using a 4DOF robot arm on board MoPAD. The excellent results yielded in both cases lead us to believe that our solution could be implemented/adapted to other platforms and robot arms.

Automatic construction of 3D basic-semantic models of inhabited interiors using laser scanners and RFID sensors

This paper is focused on the automatic construction of 3D basic-semantic models of inhabited interiors using laser scanners with the help of RFID technologies. This is an innovative approach, in whose field scarce publications exist. The general strategy consists of carrying out a selective and sequential segmentation from the cloud of points by means of different algorithms which depend on the information that the RFID tags provide. The identification of basic elements of the scene, such as walls, floor, ceiling, windows, doors, tables, chairs and cabinets, and the positioning of their corresponding models can then be calculated. The fusion of both technologies thus allows a simplified 3D semantic indoor model to be obtained. This method has been tested in real scenes under difficult clutter and occlusion conditions, and has yielded promising results.