As climate change concerns grow, the reduction of energy consumption is seen as one of many potential solutions. In the US, a considerable amount of energy is wasted in commercial buildings due to sub-optimal heating, ventilation and air conditioning that operate with no knowledge of the occupancy level in various rooms and open areas. In this thesis, I develop an approach to passive occupancy estimation that does not require occupants to carry any type of beacon, but instead uses an overhead camera with fisheye lens (360 by 180 degree field of view). The difficulty with fisheye images is that occupants may appear not only in the upright position, but also upside-down, horizontally and diagonally, and thus algorithms developed for typical side-mounted, standard-lens cameras tend to fail. As the top-performing people detection algorithms today use deep learning, a logical step would be to develop and train a new neural-network model. However, there exist no large fisheye-image datasets with person annotations to facilitate training a new model. Therefore, I developed two people-counting methods that leverage YOLO (version 3), a state-of-the-art object detection method trained on standard datasets. In one approach, YOLO is applied to 24 rotated and highly-overlapping windows, and the results are post-processed to produce a people count. In the other approach, regions of interest are first extracted via background subtraction and only windows that include such regions are supplied to YOLO and post-processed. I carried out extensive experimental evaluation of both algorithms and showed their superior performance compared to a benchmark method.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第21206号 / 情博第659号 / 新制||情||114(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)講師 延原 章平, 教授 美濃 導彦, 教授 松田 哲也 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

The Southeast Asian island of Borneo boasts an incredible diversity of terrestrial mammals which is threatened by habitat loss. Understanding the abundance and distribution of these species is essential for conservation and management. We assessed the occurrence of terrestrial mammals within two commercial forest reserves in Sabah, Malaysian Borneo. In particular, we investigated the habitat associations of the Sunda stink-badger, whose patchy distribution is not well understood. To improve detection probability and precision of model parameters, we deployed 2 camera-traps at sample stations. Our results showed that Sunda stink-badgers are likely dietary and habitat generalists, that may benefit from forest disturbance. Additionally, we found that unguligrade species were associated with high detection probability when data from one camera trap was considered and inclusion of a second camera further increased the detectability of ungulates compared to all other species. We suggest that future studies consider physical characteristics of focal species to maximize effectiveness of camera effort and ensure that data collection is efficient and meets project needs.

Mesocarnivores occupy critical functional roles in regulating ecosystems and maintaining biodiversity. In the Canadian Rocky Mountains, mustelid species depend heavily on carrion as an important dietary contribution, particularly in winter when resources are scarce. In diverse mesocarnivore communities such as this, sympatric species must balance energetic resource acquisitions through scavenging with avoidance of costly competition dynamics, in a manner that optimizes energetic gain through risk aversion. We examined the nature of spatial-temporal interactions between wolverine (Gulo gulo), American marten (Martes Americana), and short-tailed weasel (Mustela erminea) in the Willmore Wilderness Park in western Alberta. Data were collected from camera traps (n = 59) baited with a simulated scavenging opportunity during winter months between 2006 to 2008. The spatial-temporal dimensions of intraguild competition were evaluated using a multi-model approach. Zero-inflated negative binomial (ZINB) or zero-inflated Poisson (ZIP) regression models were used to identify the competitive and environmental factors that affected (1) species presence/absence and (2) how intensely a species would spatiotemporally optimize a carrion site. A time-to-event analysis was used to quantify the directionality of fine-scale (hourly) reactionary behavioural responses of species to potential sources of competition. An extension of this group of models, the Cox proportional hazard (CPH) model was used to further reveal the relative influence of external environmental variables (i.e. diel period, landcover, and snow depth) on temporal spacing. Pairing CPH and ZINB/ZIP models enables us to recognize the relative contribution of fine-scale spatial and temporal behavioural responses to competitors in shaping coexistence strategies. Our results suggest that facultative scavengers adopt different coexistence mechanisms based on the interspecific competitor and environmental conditions they encounter at carrion sites. We found that carrion use was impacted for all species by competition and snow depth. Marten scavenging behaviours were additionally impacted by habitat character. We also found evidence of fine-scale temporal attraction between marten and wolverine, thought to indicate a shared net-energetic gain at scavenging sites. Our results suggest that mesocarnivore scavengers are likely to adopt spatiotemporal mechanisms to facilitate carrion resource partitioning and adapt to conditions specific to carcass placement in a spatially complex environment. Given their vital ecological roles, it is important that we recognize the ability of individual mustelid species to exploit scavenging opportunities and identify the external factors that influence coexistence. Understanding the factors that drive access to these ephemeral resources will provide valuable information for anticipating impacts of climate change on facultative scavengers in the boreal forests of western Canada. / Graduate / 2022-08-23

The method for creating my art is a matter of experimental process, manipulation of photographic elements, and time spent. I am a photographer in a digital age that does not use a camera. My moment of creativity occurs without the snap of a shutter, but relies on my understanding and control of the chemical components of photography. My work deconstructs the notion of duplication commonly found in photography. The procedure can be repeated but the results are variable. The process of creating my work often results in a multitude of prints, but the pieces that I select as art capture a number of instinctive characteristics which convey an emotion or message to me. When I present my photographs I offer the viewer an experience--an opportunity to see the work through my mind's eye as it makes sense to me. It is within this open dialogue that the work is complete: part process, part intuitive participation.

No / The purpose of the research was to examine the practical feasibility of developing a hyperspectral camera from a Zeiss fundus camera and to illustrate its use in imaging diabetic retinopathy and glaucoma patients. The original light source of the camera was replaced with an external lamp filtered by a fast tunable liquid-crystal filter. The filtered light was then brought into the camera through an optical fiber. The original film camera was replaced by a digital camera. Images were obtained in normals and patients (primary open angle glaucoma, diabetic retinopathy) recruited at the Manchester Royal Eye Hospital. A series of eight images were captured across 495- to 720-nm wavelengths, and recording time was less than 1.6s. The light level at the cornea was below the ANSI limits, and patients judged the measurement to be very comfortable. Images were of high quality and were used to generate a pixel-to-pixel oxygenation map of the optic nerve head. Frame alignment is necessary for frame-to-frame comparison but can be achieved through simple methods. We have developed a hyperspectral camera with high spatial and spectral resolution across the whole visible spectrum that can be adapted from a standard fundus camera. The hyperspectral technique allows wavelength-specific visualization of retinal lesions that may be subvisible using a white light source camera. This hyperspectral technique may facilitate localization of retinal and disc pathology and consequently facilitate the diagnosis and management of retinal disease.

In manufacturing, monitoring machine health is an important step when implementing Industry 4.0 and ensures effective machining operations and minimal downtime. Monitoring the health of cutting tools during a machining process helps contain the faults associated with gradual tool wear, because they can be tracked and responded to as wear worsens. Left unchecked, tool failures can lead to more severe problems, such as dimensional and surface issues with machined workpieces and lower overall productivity during the machining process. This research explores the use of a machine vision setup used internally by the McMaster Manufacturing Research Institute (MMRI) in their three lathe machines. This machine vision setup provides a direct indication of the tool's maximum flank wear (VBmax), which, according to ISO 3685:1993(E), is set to be 300 µm. Also investigated was the use of image processing and analysis methods to determine the flank wear without removing the tool from the machine. This new, in-machine vision setup is intended to replace the use of an external optical microscope, which requires extended downtime between cutting passes. As a result of this replacement, the experimentation downtime was decreased by around 98.6%, leading to the experiment time to decrease from 5 weeks or more to just a couple of days. In addition, the difference in measurement between a commonly used optical microscope and in-machine vision setup was found to be ±3µm. / Thesis / Master of Science (MSc)

No description available.

No description available.

No description available.