No description available.

In Sweden and many other northern countries, it is common for heat to be distributed to homes and industries through district heating networks. Such networks consist of pipes buried underground carrying hot water or steam with temperatures in the range of 90-150 C. Due to bad insulation or cracks, heat or water leakages might appear. A system for large-scale monitoring of district heating networks through remote thermography has been developed and is in use at the company Termisk Systemteknik AB. Infrared images are captured from an aircraft and analysed, finding and indicating the areas for which the ground temperature is higher than normal. During the analysis there are, however, many other warm areas than true water or energy leakages that are marked as detections. Objects or phenomena that can cause false alarms are those who, for some reason, are warmer than their surroundings, for example, chimneys, cars and heat leakages from buildings. During the last couple of years, the system has been used in a number of cities. Therefore, there exists a fair amount of examples of different types of detections. The purpose of the present master’s thesis is to evaluate the reduction of false alarms of the existing analysis that can be achieved with the use of a learning system, i.e. a system which can learn how to recognize different types of detections.  A labelled data set for training and testing was acquired by contact with customers. Furthermore, a number of features describing the intensity difference within the detection, its shape and propagation as well as proximity information were found, implemented and evaluated. Finally, four different classifiers and other methods for classification were evaluated. The method that obtained the best results consists of two steps. In the initial step, all detections which lie on top of a building are removed from the data set of labelled detections. The second step consists of classification using a Random forest classifier. Using this two-step method, the number of false alarms is reduced by 43% while the percentage of water and energy detections correctly classified is 99%.

Automatic tracking of an object of interest in a video sequence is a task that has been much researched. Difficulties include varying scale of the object, rotation and object appearance changing over time, thus leading to tracking failures. Different tracking methods, such as short-term tracking often fail if the object steps out of the camera’s field of view, or changes shape rapidly. Also, small inaccuracies in the tracking method can accumulate over time, which can lead to tracking drift. Long-term tracking is also problematic, partly due to updating and degradation of the object model, leading to incorrectly classified and tracked objects. This master’s thesis implements a long-term tracking framework called Tracking-Learning-Detection which can learn and adapt, using so called P/N-learning, to changing object appearance over time, thus making it more robust to tracking failures. The framework consists of three parts; a tracking module which follows the object from frame to frame, a learning module that learns new appearances of the object, and a detection module which can detect learned appearances of the object and correct the tracking module if necessary. This tracking framework is evaluated on thermal infrared videos and the results are compared to the results obtained from videos captured within the visible spectrum. Several important differences between visual and thermal infrared tracking are presented, and the effect these have on the tracking performance is evaluated. In conclusion, the results are analyzed to evaluate which differences matter the most and how they affect tracking, and a number of different ways to improve the tracking are proposed.

The goal of this thesis is to develop an algorithm to process infrared images and achieve automatic identification of moving subjects with fever. The identification is based on two main features: the distinction between the geometry of a human face and other objects in the field of view of the camera, and the temperature of the radiating object. Infrared thermography is a remote sensing technique used to measure temperatures based on emitted infrared radiation. Applications include fever screening in major public places such as airports and hospitals. Current accepted practice of screening requires people to stay in a line and temperature measurements are carried out for one person at a time. However in the case of mass screening of moving people the accuracy of the measurements is still under investigation. An algorithm constituting of image processing to threshold objects based on the temperature, template matching and hypothesis testing is proposed to achieve automatic identification of fever subjects. The algorithm was first tested on training data to obtain a threshold value (used to discriminate between face and non face shapes) corresponding to a false detection rate of 5%, which in turn corresponds to 85% probability of detection using Neyman-Pearson criterion. By testing the algorithm on several simulated and experimental images (which reflect relevant scenarios characterizing crowded places) it is observed that it can be beneficially implemented to introduce automation in the process of detecting moving subjects with fever.

The goal of this thesis is to develop an algorithm to process infrared images and achieve automatic identification of moving subjects with fever. The identification is based on two main features: the distinction between the geometry of a human face and other objects in the field of view of the camera, and the temperature of the radiating object. Infrared thermography is a remote sensing technique used to measure temperatures based on emitted infrared radiation. Applications include fever screening in major public places such as airports and hospitals. Current accepted practice of screening requires people to stay in a line and temperature measurements are carried out for one person at a time. However in the case of mass screening of moving people the accuracy of the measurements is still under investigation. An algorithm constituting of image processing to threshold objects based on the temperature, template matching and hypothesis testing is proposed to achieve automatic identification of fever subjects. The algorithm was first tested on training data to obtain a threshold value (used to discriminate between face and non face shapes) corresponding to a false detection rate of 5%, which in turn corresponds to 85% probability of detection using Neyman-Pearson criterion. By testing the algorithm on several simulated and experimental images (which reflect relevant scenarios characterizing crowded places) it is observed that it can be beneficially implemented to introduce automation in the process of detecting moving subjects with fever.

The goal of this thesis is to develop an algorithm to process infrared images and achieve automatic identification of moving subjects with fever. The identification is based on two main features: the distinction between the geometry of a human face and other objects in the field of view of the camera, and the temperature of the radiating object. Infrared thermography is a remote sensing technique used to measure temperatures based on emitted infrared radiation. Applications include fever screening in major public places such as airports and hospitals. Current accepted practice of screening requires people to stay in a line and temperature measurements are carried out for one person at a time. However in the case of mass screening of moving people the accuracy of the measurements is still under investigation. An algorithm constituting of image processing to threshold objects based on the temperature, template matching and hypothesis testing is proposed to achieve automatic identification of fever subjects. The algorithm was first tested on training data to obtain a threshold value (used to discriminate between face and non face shapes) corresponding to a false detection rate of 5%, which in turn corresponds to 85% probability of detection using Neyman-Pearson criterion. By testing the algorithm on several simulated and experimental images (which reflect relevant scenarios characterizing crowded places) it is observed that it can be beneficially implemented to introduce automation in the process of detecting moving subjects with fever.

High resolution imaging of wide fields has been a prerogative of space telescopes for decades. Multi-conjugate adaptive optics (MCAO) is a key technology for the future of ground-based astronomy, especially as we approach the era of ELTs, where the large apertures will provide diffraction limits that will significantly surpass even the James Webb Space Telescope. NFIRAOS will be the first light MCAO system for the Thirty Meter Telescope and to support its development I have worked on HeNOS, its test bench integrated in Victoria at NRC Herzberg. I have aligned the optics, tested the electronic hardware, calibrated the subsystems (cameras, deformable mirrors, light sources, etc.) and characterized the system parameters. Development and support for future MCAO instruments also involves data analysis, a critical process in delivering the expected performance of any scientific instrument. To develop a strategy for optimal stellar photometry with MCAO, I have observed the Galactic globular cluster NGC 1851 with GeMS, the MCAO system on the 8-meter Gemini South telescope. From near-infrared images of this target in two bands, I have found the optimal parameters to employ in the profile-fitting photometry and calibration. As testimony to the precision of the results, I have obtained the deepest near-infrared photometry of a crowded field from the ground and used it to determine the age of the cluster with a method recently proposed that exploits the bend in the lower main sequence. The precise color-magnitude diagram also allows us to clearly observe the double subgiant branch for the first time from the ground, caused by the multiple stellar populations in the cluster. As the only facility MCAO system, GeMS is an important instrument that serves to illuminate the challenges of obtaining accurate photometry using such a system. By coupling the knowledge acquired from an instrument already on-sky with experiments in the lab on a prototype of a future system, I have addressed new challenges in photometry and astrometry, like the promising technique of point spread function reconstruction. This thesis informs the development of appropriate data processing techniques and observing strategies to ensure the ELTs deliver their full scientific promise over extended fields of view. / Graduate

The goal of this thesis is to develop an algorithm to process infrared images and achieve automatic identification of moving subjects with fever. The identification is based on two main features: the distinction between the geometry of a human face and other objects in the field of view of the camera, and the temperature of the radiating object. Infrared thermography is a remote sensing technique used to measure temperatures based on emitted infrared radiation. Applications include fever screening in major public places such as airports and hospitals. Current accepted practice of screening requires people to stay in a line and temperature measurements are carried out for one person at a time. However in the case of mass screening of moving people the accuracy of the measurements is still under investigation. An algorithm constituting of image processing to threshold objects based on the temperature, template matching and hypothesis testing is proposed to achieve automatic identification of fever subjects. The algorithm was first tested on training data to obtain a threshold value (used to discriminate between face and non face shapes) corresponding to a false detection rate of 5%, which in turn corresponds to 85% probability of detection using Neyman-Pearson criterion. By testing the algorithm on several simulated and experimental images (which reflect relevant scenarios characterizing crowded places) it is observed that it can be beneficially implemented to introduce automation in the process of detecting moving subjects with fever.

Stereo vision is one of the most active research areas in computer vision. While hundreds of stereo reconstruction algorithms have been developed, little work has been done on the evaluation of such algorithms and almost none on evaluation on Near-Infrared (NIR) images. Of almost a hundred examined, we selected a set of 15 stereo algorithms, mostly with real-time performance, which were then categorized and evaluated on several NIR image datasets, including single stereo pair and stream datasets. The accuracy and run time of each algorithm are measured and compared, giving an insight into which categories of algorithms perform best on NIR images and which algorithms may be candidates for real-time applications. Our comparison indicates that adaptive support-weight and belief propagation algorithms have the highest accuracy of all fast methods, but also longer run times (2-3 seconds). On the other hand, faster algorithms (that achieve 30 or more fps on a single thread) usually perform an order of magnitude worse when measuring the per-centage of incorrectly computed pixels.

In the master thesis about object detection(OD) using deep convolutional neural network(DCNN), the area of OD is being tested when being applied to infrared images(IR). In this thesis the, goal is to use both long wave infrared(LWIR) images and short wave infrared(SWIR) images taken from an airplane in order to train a DCNN to detect runways, Precision Approach Path Indicator(PAPI) lights, and approaching lights. The purpose for detecting these objects in IR images is because IR light transmits better than visible light under certain weather conditions, for example, fog. This system could then help the pilot detect the runway in bad weather. The RetinaNet model architecture was used and modified in different ways to find the best performing model. The models contain parameters that are found during the training process but some parameters, called hyperparameters, need to be determined in advance. A way to automatically find good values of these hyperparameters was also tested. In hyperparameter optimization, the Bayesian optimization method proved to create a model with equally good performance as the best performance acieved by the author using manual hyperparameter tuning. The OD system was implemented using Keras with Tensorflow backend and received a high perfomance (mAP=0.9245) on the test data. The system manages to detect the wanted objects in the images but is expected to perform worse in a general situation since the training data and test data are very similar. In order to further develop this system and to improve performance under general conditions more data is needed from other airfields and under different weather conditions.