ALGORITHMS FOR IMPROVING SPEED AND ACCURACY OF AUTOMATED 3D RECONSTRUCTION WITH A DEPTH CAMERA MOUNTED ON AN INDUSTRIAL ROBOT

3D reconstruction technology is used in a wide variety of applications. Currently, automatically creating accurate pointclouds for large parts requires expensive hardware. We are interested in using low-cost depth cameras mounted on commonly available industrial robots to create accurate pointclouds for large parts automatically. Manufacturing applications require fast cycle times. Therefore, we are interested in speeding up the 3D reconstruction process. We present algorithmic advances in 3D reconstruction that achieve a sub-millimeter accuracy using a low-cost depth camera. Our system can be used to determine a pointcloud model of large and complex parts. Advances in camera calibration, cycle time reduction for pointcloud capturing, and uncertainty estimation are made in this work. We continuously capture pointclouds at an optimal camera location with respect to part distance during robot motion execution. The redundancy in pointclouds achieved by the moving camera significantly reduces errors in measurements without increasing cycle time. Our system produces sub-millimeter accuracy.

Car Image Classification and Recognition

Vehicle positioning and classification is a vital technology in intelligent transportation and self-driving cars. This paper describes the experimentation for the classification of vehicle images by artificial vision using Keras and TensorFlow to construct a deep neural network model, Python modules, as well as a machine learning algorithm. Image classification finds its suitability in applications ranging from medical diagnostics to autonomous vehicles. The existing architectures are computationally exhaustive, complex, and less accurate. The outcomes are used to assess the best camera location for filming, the vehicular traffic to determine the highway occupancy. An accurate, simple, and hardware-efficient architecture is required to be developed for image classification. Keywords: Convolutional Neural Networks, Image Classification, deep neural network, Keras, Tensorflow, Python, machine learning, dataset

Model-based analysis of multi-UAV path planning for surveying postdisaster building damage

Emergency responders require accurate and comprehensive data to make informed decisions. Moreover, the data should be acquired and analyzed swiftly to ensure an efficient response. One of the tasks at hand post-disaster is damage assessment within the impacted areas. In particular, building damage should be assessed to account for possible casualties, and displaced populations, to estimate long-term shelter capacities, and to assess the damage to services that depend on essential infrastructure (e.g. hospitals, schools, etc.). Remote sensing techniques, including satellite imagery, can be used to gathering such information so that the overall damage can be assessed. However, specific points of interest among the damaged buildings need higher resolution images and detailed information to assess the damage situation. These areas can be further assessed through unmanned aerial vehicles and 3D model reconstruction. This paper presents a multi-UAV coverage path planning method for the 3D reconstruction of postdisaster damaged buildings. The methodology has been implemented in NetLogo3D, a multi-agent model environment, and tested in a virtual built environment in Unity3D. The proposed method generates camera location points surrounding targeted damaged buildings. These camera location points are filtered to avoid collision and then sorted using the K-means or the Fuzzy C-means methods. After clustering camera location points and allocating these to each UAV unit, a route optimization process is conducted as a multiple traveling salesman problem. Final corrections are made to paths to avoid obstacles and give a resulting path for each UAV that balances the flight distance and time. The paper presents the details of the model and methodologies, and an examination of the texture resolution obtained from the proposed method and the conventional overhead flight with the nadir-looking method used in 3D mappings. The algorithm outperforms the conventional method in terms of the quality of the generated 3D model.

High-Accuracy Gaze Estimation for Interpolation-Based Eye-Tracking Methods

This study investigates the influence of the eye-camera location associated with the accuracy and precision of interpolation-based eye-tracking methods. Several factors can negatively influence gaze estimation methods when building a commercial or off-the-shelf eye tracker device, including the eye-camera location in uncalibrated setups. Our experiments show that the eye-camera location combined with the non-coplanarity of the eye plane deforms the eye feature distribution when the eye-camera is far from the eye’s optical axis. This paper proposes geometric transformation methods to reshape the eye feature distribution based on the virtual alignment of the eye-camera in the center of the eye’s optical axis. The data analysis uses eye-tracking data from a simulated environment and an experiment with 83 volunteer participants (55 males and 28 females). We evaluate the improvements achieved with the proposed methods using Gaussian analysis, which defines a range for high-accuracy gaze estimation between −0.5∘ and 0.5∘. Compared to traditional polynomial-based and homography-based gaze estimation methods, the proposed methods increase the number of gaze estimations in the high-accuracy range.

LOCATION OF SPEED CONTROL CAMERAS ON HIGHWAYS: A GEOSPATIAL ANALYSIS

This research proposes a methodology to identify critical sections of highways where the location of speeding control may be beneficial. The method relies on a spatial and statistical analysis of infrastructure risks, along with traffic accident frequency and severity. A relevant feature of this methodology is related to its potential to be used in areas where there are no detailed historical records about traffic crashes, which is common in Global South countries. We applied the methodology to a rural road network in Colombia, where a recent law established that technical criteria should support the location of speed cameras. The case study uses accident information from six years, and risk data from a road safety audit carried out in the area under study. Even though historical records of accidents in the area were not fully available, the methodology allowed prioritising speed camera installations in the zone and identifying the relevant variables to define camera location. The relevant variables were the geometric characteristics of the road, traffic flows, risk factors, and proximity to populated centres. The use of speed controls should be part of a road safety management system, which allows defining camera location according to robust technical criteria.

Real-time face view correction for front-facing cameras

Face views are particularly important in person-to-person communication. Differenes between the camera location and the face orientation can result in undesirable facial appearances of the participants during video conferencing. This phenomenon is particularly noticeable when using devices where the front-facing camera is placed in unconventional locations such as below the display or within the keyboard. In this paper, we take a video stream from a single RGB camera as input, and generate a video stream that emulates the view from a virtual camera at a designated location. The most challenging issue in this problem is that the corrected view often needs out-of-plane head rotations. To address this challenge, we reconstruct the 3D face shape and re-render it into synthesized frames according to the virtual camera location. To output the corrected video stream with natural appearance in real time, we propose several novel techniques including accurate eyebrow reconstruction, high-quality blending between the corrected face image and background, and template-based 3D reconstruction of glasses. Our system works well for different lighting conditions and skin tones, and can handle users wearing glasses. Extensive experiments and user studies demonstrate that our method provides high-quality results.

New Image Recognition Technique for Intuitive Understanding in Class of the Dynamic Response of High-Rise Buildings

In the last years, more and more studies have highlighted the advantages of complementing traditional master classes with additional activities that improve students’ learning experience. This combination of teaching techniques is specially advised in the field of structural engineering, where intuition of the structural response it is of vital importance to understand the studied concepts. This paper deals with the introduction of a new (and more encouraging) educational tool to introduce students intuitively to the dynamic response of structures excited with an educational shaking table. Most of the educational structural health monitoring systems use sensors to determine the dynamic response of the structure. The proposed tool is based on a radically different approach, as it is based on low-cost image-recognition techniques. In fact, it only requires the use of an amateur camera, a black background, and a computer. In this study, the effects of both the camera location and the image quality are also evaluated. Finally, to validate the applicability of the proposed methodology, the dynamic response of small-scale buildings with different typologies is analyzed. In addition, a series of surveys were conducted in order to evaluate the activity based on student´s satisfaction and the actual acquisition and strengthening of knowledge.

New Image Recognition Technique for Intuitive Understanding in Class of the Dynamic Response of High-Rise Buildings

In the last years, more and more studies highlight the advantages of complementing traditional master classes with additional activities that improve students´ learning experience. This combination of teaching techniques is specially advised in the field of structural engineering, where intuition of the structural response it is of vital importance to understand the studied concepts. This paper deals with the introduction of a new (and more encouraging) educational tool to introduce intuitively students in the dynamic response of structures excited with an educational shaking table. Most of the educational structural health monitoring systems use sensors to determine the dynamic response of the structure. The proposed tool is based on a radically different approach, as it is based on low-cost image-recognition techniques. In fact, it only requires the use an amateur camera, a black background and a computer. In this study, the effects of both the camera location and the image quality are also evaluated. Finally, to validate the applicability of the proposed methodology, the dynamic response of small-scale buildings with different typologies is analyzed. In addition, a series of surveys were conducted in order to evaluate the activity based on student´s satisfaction and the actual acquisition and strengthening of knowledge.

Experiences from a Virtual Mapathon for collaborative Georeferencing of historical terrestrial Images in Alpine regions

<p>Historical terrestrial images for identification, documentation, and especially the quantification of change in the alpine landscape are a largely unused source. Metric exploitation requires estimating the unknown camera parameters (camera location, angular attitude, and focal length) by photogrammetric resection. This is a challenging task, especially the identification of ground control points in mountainous terrain is time consuming and requires experience. Furthermore, due to the limited field of view of single images only small areas are captured. Hence, despite their possibility to provide quantitative information from more than one hundred years ago, integrating information from these historical images into subsequent analysis is often avoided.</p><p>Enabling their usage requires suitable software as well as users willing to engage in the challenge of image orientation. To facilitate this, a virtual Mapathon was organized, inviting participants to collaboratively orient historical images of the Val Martell (Italy) in the Ortler Alps. The participants from varying geoscience backgrounds (e.g. Botany, Climatology, Geomorphology, Glaciology, Hydrology) had little experience in photogrammetry prior to the Mapathon. Nevertheless, within one day nearly 100 images were oriented by 20 participants. The Mapathon was organized as a video conference using a web-based 3D image orientation software linked to an image database. Sessions with the whole group and in small teams alternated. Working in small teams stimulated internal discussions, promoting the understanding and success of each participant. Feedback received from the participants shows that the Mapathon helped overcoming the initial problem of getting started. Furthermore, the gained knowledge allows the participants to work with historical terrestrial images on their own in the future. </p><p>The set of oriented historical images created within the Mapathon further underlines the potential of historical terrestrial images. Due to  the availability of numerous oriented images, the limited fields of view of individual images can be combined, allowing the documentation of changes for larger areas. With the calculation of the viewshed for each image, the image database can not only be queried by metadata, but more importantly by location and spatial coverage. Especially the possibility to search for images capturing a certain region of interest will encourage scientists to include historical terrestrial images into their analysis.</p>

Application of OpenPose and deep learning for intelligent surveillance reconnaissance system

In this study, defense surveillance reconnaissance systems were implemented through deep learning networks such as OpenPose and deep neural networks (DNN), convolutional neural networks (CNN), and long short-term memory (LSTM). This study proposes a target recognition method which differs from the existing surveillance reconnaissance systems. This method consists in distinguishing between ordinary people and targets by classifying motions in the images being filmed. Thus, the skeleton data of the target in the image are extracted using OpenPose. Then, keypoints included in the extracted skeleton data are entered into DNN, CNN, and LSTM to classify the motion. The classified motions are selected as motions learned in the military, such as overall security. When the system classifies motions and recognizes targets, it identifies them on the map and tracks them. The tracking algorithm calculates the movement direction of the target by calculating the change in the values of keypoints extracted through OpenPose by frames. Finally, it uses the depth information obtained from the camera to display targets on the map based on the camera location. All these computations are based on the use of the skeleton data rather than the entire image, thus reducing the overall computation.