Demos of deploying combo 5 caffemodel trained for 18000 iterations and combo 15 caffemodel trained for 25000 iterations.

Background: Traffic Sign Recognition (TSR) is particularly useful for novice driversand self-driving cars. Driver Assistance Systems(DAS) involves automatic trafficsign recognition. Efficient classification of the traffic signs is required in DAS andunmanned vehicles for safe navigation. Convolutional Neural Networks(CNN) isknown for establishing promising results in the field of image classification, whichinspired us to employ this technique in our thesis. Computer vision is a process thatis used to understand the images and retrieve data from them. OpenCV is a Pythonlibrary used to detect traffic sign images in real-time. Objectives: This study deals with an experiment to build a CNN model which canclassify the traffic signs in real-time effectively using OpenCV. The model is builtwith low computational cost. The study also includes an experiment where variouscombinations of parameters are tuned to improve the model’s performance. Methods: The experimentation method involve building a CNN model based onmodified LeNet architecture with four convolutional layers, two max-pooling layersand two dense layers. The model is trained and tested with the German Traffic SignRecognition Benchmark (GTSRB) dataset. Parameter tuning with different combinationsof learning rate and epochs is done to improve the model’s performance.Later this model is used to classify the images introduced to the camera in real-time. Results: The graphs depicting the accuracy and loss of the model before and afterparameter tuning are presented. An experiment is done to classify the traffic signimage introduced to the camera by using the CNN model. High probability scoresare achieved during the process which is presented. Conclusions: The results show that the proposed model achieved 95% model accuracywith an optimum number of epochs, i.e., 30 and default optimum value oflearning rate, i.e., 0.001. High probabilities, i.e., above 75%, were achieved when themodel was tested using new real-time data.

In the last decades there has been such a fundamental development in the technologies including technologies focusing on face detection and identification supported by computer vision. Algorithm optimization has reached the point, when face detection is possible on mobile devices. At the outset, this work analy-ses common used algorithms for face detection and identification, for instance Haar features, LBP, EigenFaces and FisherFaces. Moreover, this work focuses on more up-to-date approaches of this topic, such as convolutional neural networks, or FaceNet from Google. The goal of this work is a design and its subsequent im-plementation of an automated, monitoring system designated for a lab, which is based on aforementioned algorithms. Within the design of the monitoring system, algorithms are compared with each other and their success rate and possible ap-plication in the final solution is evaluated.

An algorithm is presented to count bee numbers in images of Langsthroth hive entrances. The algorithm computes approximate bee counts by adjusting the brightness of the image, cropping a white or green area in the image, removing the background and noise from the cropped area, finding the total number of bee pixels, and dividing that number by the average number of pixels in a single bee. On 1005 images with green landing pads, the algorithm achieved an accuracy of 80 percent when compared to the human bee counting. On 776 images with white landing pads, the algorithm achieved an accuracy of 85% compared to the human bee counting.

This thesis report aims to explain the research, implementation, and testing of a monocular SLAM system in an application developed by Voysys AB called Oden, as well as the making and investigation of a new data set used to test the SLAM system. Using CUDASIFT to find and match feature points, OpenCV to compute the initial guess, and the Ceres Solver to optimize the results. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

No description available.

No description available.

Companies face a problem where employees reserve rooms and do not show up, which leadsto money and resources loss for the companies. An application capable of detecting thepresence of people in a room could solve this problem.This thesis details the process of building an Android application capable of detectingthe presence of people in a static room using motion detection. The application wasdeveloped through a five-staged process and evaluated by performing experiments whichmeasured the accuracy of the application.The finished application is installed on a Sony Xperia M4 Aqua device which is mountedhigh up on a wall in a conference room where the application takes images of the room. Theapplication is connected to a Google Drive account where the application uploads acquiredimages with an appropriate label. The application achieved an accuracy of 94.18% in anexperiment where 550 images where taken automatically by the application in differentconference rooms with and without people inside them

Made available in DSpace on 2017-07-21T14:19:31Z (GMT). No. of bitstreams: 1 dissertacao_jaqueline_franco.pdf: 5450978 bytes, checksum: ccba56653d20a1b74e0758541848145a (MD5) Previous issue date: 2017-06-29 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The condition known as purple spot in soybean seed is caused by the fungus Cercospora kikuchii and can influence both yield and quality losses in the production of soybean derivatives. Seed quality control is essential to avoid such losses, so there are conventional methods, such as visual inspections to identify contaminated seeds. However, these conventional processes are slow and imprecise, since they depend directly on the analyst. The present work had as objective to develop a computational system for the identification of soybean seeds contaminated by the fungus Cercospora kikuchii. The proposed method was developed based on the OpenCV library, using the Java programming language and the integration interface of the WEKA tool. Samples of 150 healthy seeds and 150 contaminated seeds were considered. The individual image acquisition of each seed, for purposes of classification in healthy or contaminated, was performed and was consided in the process the individual quality of each stage. The obtained result was 88% of correct classifications, using crossvalidation in the constructed neural network model and 100% correct classifications in the used images. The best results found in studies of other authors, specifically considering the fungus Cercospora kikuchii, were 66% to 83% of the correct classifications. / A presença da patologia conhecida como mancha púrpura da semente de soja é causada pelo fungo Cercospora kikuchii e pode implicar em prejuízos tanto de produtividade quanto de qualidade na produção de derivados. O controle de qualidade de sementes é essencial para evitar perdas como essas, sendo então convencionalmente realizadas inspeções visuais, para identificar as sementes contaminadas. Porém, tais processos convencionais são lentos e imprecisos, uma vez que depende diretamente do analista. O presente trabalho teve por objetivo desenvolver um sistema computacional para a identificação de sementes de soja contaminadas pelo fungo Cercospora kikuchii. O método proposto foi desenvolvido utilizando a biblioteca OpenCV, por meio da linguagem de programação Java, e utilizando a interface de integração da ferramenta WEKA. Foram consideradas amostras de 150 sementes sadias e de 150 sementes contaminadas. A obtenção individual da imagem de cada semente, para fins de classificação em sadia ou contaminada, foi realizada e foi considerada durante o processo a qualidade individual de cada etapa do processo. O resultado alcançado foi de 88% de assertividade, utilizando a validação cruzada sobre o modelo de rede neural artificial construído, e de 100% de assertividade sobre as imagens utilizadas. Os melhores resultados encontrados em trabalhos de outros autores, considerando especificamente o fungo Cercospora kikuchii, foram de 66% a 83% de assertividade.

Submitted by Angela Maria de Oliveira (amolivei@uepg.br) on 2018-06-19T17:15:59Z No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) PEDRO HENRIQUE SOARES DE ALMEIDA.pdf: 8669671 bytes, checksum: bf6252d5566d0b626215c08edce94dca (MD5) / Made available in DSpace on 2018-06-19T17:15:59Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) PEDRO HENRIQUE SOARES DE ALMEIDA.pdf: 8669671 bytes, checksum: bf6252d5566d0b626215c08edce94dca (MD5) Previous issue date: 2018-05-15 / O mosaico de imagens é o alinhamento de múltiplas imagens em composições maiores que representam partes de uma cena 3D. Diversos algoritmos de mosaico de imagens foram propostos nas últimas duas décadas. Ao mesmo tempo, o advento contínuo de novos métodos de mosaico torna muito difícil escolher um algoritmo apropriado para uma finalidade específica. Este trabalho teve por objetivo avaliar métodos de mosaico baseados em característica de baixo nível utilizando imagens agrícolas obtidas por meio de Aeronave Remotamente Pilotada (RPA). Algoritmos detectores de característica de baixo nível podem ser invariantes à escala e rotação, dentre outras transformações que comumente ocorrem em imagens agrícolas obtidas por meio de RPA. O detector de cantos de Harris, detector de cantos FAST, detector de característica SIFT e detector SURF foram avaliados de acordo com o desempenho computacional e a qualidade do mosaico gerado. Para avaliar o desempenho, foram levados em consideração fatores como a média de características detectadas por imagem, o número de imagens utilizadas para compor o mosaico e o tempo de processamento (tempo de usuário ou user time). Para avaliar a qualidade, os mosaicos gerados pelos métodos foram utilizados para estimar a severidade da ferrugem asiática da soja e uma comparação com o software comercial Pix4Dmapper foi realizada. Em relação à qualidade, não houve diferença significativa e todos os métodos demonstraram estar no mesmo patamar. O detector SURF, dentre todos os métodos, obteve o pior desempenho utilizando, em média, apenas 33,1% das imagens de entrada para compor os mosaicos. O detector de cantos de Harris mostrou-se como a solução mais rápida, chegando a ser 7,27% mais rápido para compor o mosaico. Porém, em seu último mosaico gerado, o aproveitamento das imagens de entrada foi pobre: apenas 52%. O detector de cantos FAST obteve o melhor aproveitamento das imagens de entrada, porém, descontinuidades significativas de objetos ocorreram em seu último mosaico gerado. Além disso, obteve um tempo de processamento consideravelmente superior ao dos demais métodos, chegando a ser 6,42 vezes mais lento para compor o mosaico. O detector de característica SIFT obteve o segundo melhor tempo de processamento e o segundo melhor aproveitamento das imagens de entrada, sem apresentar problemas de descontinuidades de objetos. Portanto, mostrou-se como o método mais adequado para imagens agrícolas obtidas por meio de RPA. / Image mosaicing is the alignment of multiple images into larger compositions which represent portions of a 3D scene. A number of image mosaicing algorithms have been proposed over the last two decades. At the same time, the continuous advent of new mosaicing methods in recent years makes it really difficult to choose an appropriate mosaicing algorithm for a specific purpose. This study aimed to evaluate low level feature-based mosaicing methods using agricultural images obtained by Remotely Piloted Aircraft (RPA). Low-level feature detecting algorithms can be invariant to scale and rotation, among other transformations that commonly occur in agricultural images obtained by RPA. Harris corner detector, FAST corner detector, SIFT feature detector and SURF detector were evaluated according to the computational performance and the quality of the generated mosaic. To evaluate computational performance, were taken into account factors such as the detected features average per image, the number of images used to compose the mosaic and the processing time (user time). To evaluate quality, the mosaics generated by each method were used to estimate the Asian soybean rust severity and a comparison with the commercial software Pix4Dmapper was performed. Regarding quality, there was no significant difference and all methods proved to be on the same level. SURF detector, among all methods, got the worst performance using, on average, only 33.1% of the input images to compose the mosaics. Harris corner detector proved to be the fastest solution, becoming 7.27% faster to compose the mosaic. However, in its final mosaic, the use of the input images was poor: only 52%. FAST corner detector had the best utilization of the input images, however, significant discontinuities of objects occurred in its final mosaic. In addition, it had a considerably longer processing time than the other methods, becoming 6.42 times slower to compose the mosaic. SIFT feature detector had the second best processing time and the second best utilization of the input images, without presenting object discontinuities problems. Therefore, presented itself as the most suitable method for agricultural images obtained by RPA.