Search

In a time where sustainability and CO2 efficiency are of ever-increasing importance, heating systems deserve special considerations. Despite well-functioning hardware, inefficiencies may arise when controller parameters are not well chosen. While monitoring systems could help to identify such issues, they lack improvement suggestions. One possible solution would be the use of digital twins; however, critical values such as the water consumption of the residents can often not be acquired for accurate models. To address this issue, coarse models can be employed to generate quantitative predictions, which can then be interpreted qualitatively to assess “better or worse” system behavior. In this paper, we present a simulation and calibration framework as well as a preprocessing module. These components can be run locally or deployed as containerized microservices and are easy to interface with existing data acquisition infrastructure. We evaluate the two main operating modes, namely automatic model calibration, using measured data, and the optimization of controller parameters. Our results show that using a coarse model of a real heating system and data augmentation through preprocessing, it is possible to achieve an acceptable fit of partially incomplete measured data, and that the calibrated model can subsequently be used to perform an optimization of the controller parameters in regard to the simulated boiler gas consumption.

Accurately calibrating camera–LiDAR systems is crucial for achieving effective data fusion, particularly in data collection vehicles. Data-driven calibration methods have gained prominence over target-based methods due to their superior adaptability to diverse environments. However, current data-driven calibration methods are susceptible to suboptimal initialization parameters, which can significantly impact the accuracy and efficiency of the calibration process. In response to these challenges, this paper proposes a novel general model for the camera–LiDAR calibration that abstracts away the technical details in existing methods, introduces an improved objective function that effectively mitigates the issue of suboptimal parameter initialization, and develops a multi-level parameter optimization algorithm that strikes a balance between accuracy and efficiency during iterative optimization. The experimental results demonstrate that the proposed method effectively mitigates the effects of suboptimal initial calibration parameters, achieving highly accurate and efficient calibration results. The suggested technique exhibits versatility and adaptability to accommodate various sensor configurations, making it a notable advancement in the field of camera–LiDAR calibration, with potential applications in diverse fields including autonomous driving, robotics, and computer vision.

Risley-prism-based image sensors can expand the imaging field of view through beam control. The larger the top angle of the prism, the higher the magnification of the field of view, but at the same time, it aggravates the problem of imaging aberrations, which also puts higher requirements on the aberration correction method for the Risley-prism-based image sensor. To improve the speed, accuracy, and stability of the aberration correction process, an automatic calibration method for the Risley-prism-based image sensor is proposed based on a two-axis turntable. The image datasets of the calibration plate with different prism rotation angles and object distances are acquired using a two-axis turntable. Then, the images of the calibration plate are pre-processed using the bicubic interpolation algorithm. The calibration parameters are finally calculated, and parameter optimization is performed. The experimental results verify the feasibility of this automated calibration method. The reprojection error of the calibration is within 0.26 pixels when the distance of the imaging sensor is 3.6 m from the object, and the fine aberration correction results are observed.

This paper describes an affordable robotic mobile 3D mapping system. It is built with Livox Mid–40 lidar with a conic field of view extended by a custom rotating planar reflector. This 3D sensor is compared with the more expensive Velodyne VLP 16 lidar. It is shown that the proposed sensor reaches satisfactory accuracy and range. Furthermore, it is able to preserve the metric accuracy and non–repetitive scanning pattern of the unmodified sensor. Due to preserving the non–repetitive scan pattern, our system is capable of covering the entire field of view of 38.4 × 360 degrees, which is an added value of conducted research. We show the calibration method, mechanical design, and synchronization details that are necessary to replicate our system. This work extends the applicability of solid–state lidars since the field of view can be reshaped with minimal loss of measurement properties. The solution was part of a system that was evaluated during the 3rd European Robotics Hackathon in the Zwentendorf Nuclear Power Plant. The experimental part of the paper demonstrates that our affordable robotic mobile 3D mapping system is capable of providing 3D maps of a nuclear facility that are comparable to the more expensive solution.

The space around the Earth is filled with man-made objects, which orbit the planet at altitudes ranging from hundreds to tens of thousands of kilometers. Keeping an eye on all objects in Earth’s orbit, useful and not useful, operational or not, is known as Space Surveillance. Due to cost considerations, the space surveillance solutions beyond the Low Earth Orbit region are mainly based on optical instruments. This paper presents a solution for real-time automatic detection and ranging of space objects of altitudes ranging from below the Medium Earth Orbit up to 40,000 km, based on two low cost observation systems built using commercial cameras and marginally professional telescopes, placed 37 km apart, operating as a large baseline stereovision system. The telescopes are pointed towards any visible region of the sky, and the system is able to automatically calibrate the orientation parameters using automatic matching of reference stars from an online catalog, with a very high tolerance for the initial guess of the sky region and camera orientation. The difference between the left and right image of a synchronized stereo pair is used for automatic detection of the satellite pixels, using an original difference computation algorithm that is capable of high sensitivity and a low false positive rate. The use of stereovision provides a strong means of removing false positives, and avoids the need for prior knowledge of the orbits observed, the system being able to detect at the same time all types of objects that fall within the measurement range and are visible on the image.

This paper describes a non-invasive, automatic, and robust method for calibrating a scalable RGB-D sensor network based on retroreflective ArUco markers and the iterative closest point (ICP) scheme. We demonstrate the system by calibrating a sensor network comprised of six sensor nodes positioned in a relatively large industrial robot cell with an approximate size of 10 m × 10 m × 4 m . Here, the automatic calibration achieved an average Euclidean error of 3 c m at distances up to 9.45 m . To achieve robustness, we apply several innovative techniques: Firstly, we mitigate the ambiguity problem that occurs when detecting a marker at long range or low resolution by comparing the camera projection with depth data. Secondly, we use retroreflective fiducial markers in the RGB-D calibration for improved accuracy and detectability. Finally, the repeating ICP refinement uses an exact region of interest such that we employ the precise depth measurements of the retroreflective surfaces only. The complete calibration software and a recorded dataset are publically available and open source.

As the number of objects in Earth’s atmosphere and in low Earth orbit is continuously increasing; accurate surveillance of these objects has become important. This paper presents a generic, low cost sky surveillance system based on stereovision. Two cameras are placed 37 km apart and synchronized by a GPS-controlled external signal. The intrinsic camera parameters are calibrated before setup in the observation position, the translation vectors are determined from the GPS coordinates and the rotation matrices are continuously estimated using an original automatic calibration methodology based on following known stars. The moving objects in the sky are recognized as line segments in the long exposure images, using an automatic detection and classification algorithm based on image processing. The stereo correspondence is based on the epipolar geometry and is performed automatically using the image detection results. The resulting experimental system is able to automatically detect moving objects such as planes, meteors and Low Earth Orbit satellites, and measure their 3D position in an Earth-bound coordinate system.

This paper proposes a method that automatically calibrates four cameras of an around view monitor (AVM) system in a natural driving situation. The proposed method estimates orientation angles of four cameras composing the AVM system, and assumes that their locations and intrinsic parameters are known in advance. This method utilizes lane markings because they exist in almost all on-road situations and appear across images of adjacent cameras. It starts by detecting lane markings from images captured by four cameras of the AVM system in a cost-effective manner. False lane markings are rejected by analyzing the statistical properties of the detected lane markings. Once the correct lane markings are sufficiently gathered, this method first calibrates the front and rear cameras, and then calibrates the left and right cameras with the help of the calibration results of the front and rear cameras. This two-step approach is essential because side cameras cannot be fully calibrated by themselves, due to insufficient lane marking information. After this initial calibration, this method collects corresponding lane markings appearing across images of adjacent cameras and simultaneously refines the initial calibration results of four cameras to obtain seamless AVM images. In the case of a long image sequence, this method conducts the camera calibration multiple times, and then selects the medoid as the final result to reduce computational resources and dependency on a specific place. In the experiment, the proposed method was quantitatively and qualitatively evaluated in various real driving situations and showed promising results.

Proximity sensors are broadly used in mobile robots for obstacle detection. The traditional calibration process of this kind of sensor could be a time-consuming task because it is usually done by identification in a manual and repetitive way. The resulting obstacles detection models are usually nonlinear functions that can be different for each proximity sensor attached to the robot. In addition, the model is highly dependent on the type of sensor (e.g., ultrasonic or infrared), on changes in light intensity, and on the properties of the obstacle such as shape, colour, and surface texture, among others. That is why in some situations it could be useful to gather all the measurements provided by different kinds of sensor in order to build a unique model that estimates the distances to the obstacles around the robot. This paper presents a novel approach to get an obstacles detection model based on the fusion of sensors data and automatic calibration by using artificial neural networks.

Since it is impossible for surveillance personnel to keep monitoring videos from a multiple camera-based surveillance system, an efficient technique is needed to help recognize important situations by retrieving the metadata of an object-of-interest. In a multiple camera-based surveillance system, an object detected in a camera has a different shape in another camera, which is a critical issue of wide-range, real-time surveillance systems. In order to address the problem, this paper presents an object retrieval method by extracting the normalized metadata of an object-of-interest from multiple, heterogeneous cameras. The proposed metadata generation algorithm consists of three steps: (i) generation of a three-dimensional (3D) human model; (ii) human object-based automatic scene calibration; and (iii) metadata generation. More specifically, an appropriately-generated 3D human model provides the foot-to-head direction information that is used as the input of the automatic calibration of each camera. The normalized object information is used to retrieve an object-of-interest in a wide-range, multiple-camera surveillance system in the form of metadata. Experimental results show that the 3D human model matches the ground truth, and automatic calibration-based normalization of metadata enables a successful retrieval and tracking of a human object in the multiple-camera video surveillance system.