This master's thesis prepared the programme which is able to follow the trajectories of the movement of people and based on this to create various statistics. In practice it is an effective marketing tool which can be used for instance for customer flow analyses, optimal evaluation of opening hours, visitor traffic analyses and for a lot of other benefits. Histograms of oriented gradients, SVM classificator and optical flow monitoring were used to solve this problem. The method of multiple hypothesis tracking was selected for the association data. The system's quality was evaluated from the video footage of the street with the large concentration of pedestrians and from the school's camera system, where the movement in the corridor was monitored and the number of people counted.

Strawberry is an important cash crop in California, and its supply accounts for 80% of the US market [2]. However, in current practice, strawberries are picked manually, which is very labor-intensive and time-consuming. In addition, the farmers need to hire an appropriate number of laborers to harvest the berries based on the estimated volume. When overestimating the yield, it will cause a waste of human resources, while underestimating the yield will cause the loss of the strawberry harvest [3]. Therefore, accurately estimating harvest volume in the field is important to farmers. This paper focuses on an image-based solution to detect strawberries in the field by using the traditional computer vision technique and deep learning method. When strawberries are in different growth stages, there are considerable differences in their color. Therefore, various color spaces are first studied in this work, and the most effective color components are used in detecting strawberries and differentiating mature and immature strawberries. In some color channels such as the R color channel from the RGB color model, Hue color channel from the HSV color model, 'a' color channel from the Lab color model, the pixels belonging to ripe strawberries are clearly distinguished from the background pixels. Thus, the color-based K-mean cluster algorithm to detect red strawberries will be exploited. Finally, it achieves a 90.5% truth-positive rate for detecting red strawberries. For detecting the unripe strawberry, this thesis first trained the Support Vector Machine classifier based on the HOG feature. After optimizing the classifier through hard negative mining, the truth-positive rate reached 81.11%. Finally, when exploring the deep learning model, two detectors based on different pre-trained models were trained using TensorFlow Object Detection API with the acceleration of Amazon Web Services' GPU instance. When detecting in a single strawberry plant image, they have achieved truth-positive rates of 89.2% and 92.3%, respectively; while in the strawberry field image with multiple plants, they have reached 85.5% and 86.3%.

The goal of this thesis is the utilization of computer vision methods, in a way that will lead to detection and identification of traffic signs in an image. The final application is to analyze video feed from a video camcorder placed in a vehicle. With focus placed on effective utilization of computer resources in order to achieve real time identification of signs in a video stream.

This study aims to modify Vision Transformer (ViT) to achieve higher accuracy. ViT is a model used in computer vision to, among other things, classify images. By applying ViT to the MNIST data set, an accuracy of approximately 98% is achieved. ViT is modified by implementing a method called Histogram of Oriented Gradients (HOG) in two different ways. The results show that the first approach with HOG gives an accuracy of 98,74% (setup 1) and the second approach gives an accuracy of 96,87% (patch size 4x4 pixels). The study shows that when HOG is applied on the entire image, a better accuracy is obtained. However, no systematic optimization has taken place, which makes it difficult to draw conclusions with certainty.

This study presents two computer vision based algorithms for automated 2D detection of construction workers and equipment from site video streams. The state-of-the-art research proposes semi-automated detection methods for tracking of construction workers and equipment. Considering the number of active equipment and workers on jobsites and their frequency of appearance in a camera's field of view, application of semi-automated techniques can be time-consuming. To address this limitation, two new algorithms based on Histograms of Oriented Gradients and Colors (HOG+C), 1) HOG+C sliding detection window technique, and 2) HOG+C deformable part-based model are proposed and their performance are compared to the state-of-the-art algorithm in computer vision community. Furthermore, a new comprehensive benchmark dataset containing over 8,000 annotated video frames including equipment and workers from different construction projects is introduced. This dataset contains a large range of pose, scale, background, illumination, and occlusion variation. The preliminary results with average performance accuracies of 100%, 92.02%, and 89.69% for workers, excavators, and dump trucks respectively, indicate the applicability of the proposed methods for automated activity analysis of workers and equipment from single video cameras. Unlike other state-of-the-art algorithms in automated resource tracking, these methods particularly detects idle resources and does not need manual or semi-automated initialization of the resource locations in 2D video frames. / Master of Science

De nos jours les algorithmes de vision par ordinateur abondent dans les applications de vidéo-surveillance, de reconstruction 3D, de véhicules autonomes, d'imagerie médicale, etc… La détection et la mise en correspondance d'objets dans les images constitue une étape clé dans ces algorithmes.Les méthodes les plus communes pour la mise en correspondance d'objets ou d'images sont basées sur des descripteurs locaux, avec tout d'abord la détection de points d'intérêt, puis l'extraction de caractéristiques de voisinages des points d'intérêt, et enfin la construction des descripteurs d'image.Dans cette thèse, nous présentons des contributions au domaine de la mise en correspondance d'images par l'utilisation de demi filtres tournants. Nous suivons ici trois approches : la première présente un nouveau descripteur à faible débit et une stratégie de mise en correspondance intégrés à une plateforme vidéo. Deuxièmement, nous construisons un nouveau descripteur local en intégrant la réponse de demi filtres tournant dans un histogramme de gradient orienté (HOG) ; enfin nous proposons une nouvelle approche pour la construction d'un descripteur utilisant des statistiques du second ordre. Toutes ces trois approches apportent des résultats intéressants et prometteurs.Mots-clés : Demi filtres tournants, descripteur local d'image, mise en correspondance, histogramme de gradient orienté (HOG), Différence de gaussiennes. / Nowadays computer vision algorithms can be found abundantly in applications relatedto video surveillance, 3D reconstruction, autonomous vehicles, medical imaging etc. Image/object matching and detection forms an integral step in many of these algorithms.The most common methods for Image/object matching and detection are based on localimage descriptors, where interest points in the image are initially detected, followed byextracting the image features from the neighbourhood of the interest point and finally,constructing the image descriptor. In this thesis, contributions to the field of the imagefeature matching using rotating half filters are presented. Here we follow three approaches:first, by presenting a new low bit-rate descriptor and a cascade matching strategy whichare integrated on a video platform. Secondly, we construct a new local image patch descriptorby embedding the response of rotating half filters in the Histogram of Orientedgradient (HoG) framework and finally by proposing a new approach for descriptor constructionby using second order image statistics. All the three approaches provides aninteresting and promising results by outperforming the state of art descriptors.Key-words: Rotating half filters, local image descriptor, image matching, Histogram of Orientated Gradients (HoG), Difference of Gaussian (DoG).

Magister Scientiae - MSc (Computer Science) / A machine translation system that can convert South African Sign Language (SASL) video to audio or text and vice versa would be bene cial to people who use SASL to communicate. Five fundamental parameters are associated with sign language gestures, these are: hand location; hand orientation; hand shape; hand movement and facial expressions. The aim of this research is to recognise facial expressions and to compare both feature descriptors and machine learning techniques. This research used the Design Science Research (DSR) methodology. A DSR artefact was built which consisted of two phases. The rst phase compared local binary patterns (LBP), compound local binary patterns (CLBP) and histogram of oriented gradients (HOG) using support vector machines (SVM). The second phase compared the SVM to arti cial neural networks (ANN) and random forests (RF) using the most promising feature descriptor|HOG|from the rst phase. The performance was evaluated in terms of accuracy, robustness to classes, robustness to subjects and ability to generalise on both the Binghamton University 3D facial expression (BU-3DFE) and Cohn Kanade (CK) datasets. The evaluation rst phase showed HOG to be the best feature descriptor followed by CLBP and LBP. The second showed ANN to be the best choice of machine learning technique closely followed by the SVM and RF.

This thesis deals with methods for the detection of people and tracking objects in video sequences. An application for detection and tracking of players in video recordings of sport activities, e.g. hockey or basketball matches, is proposed and implemented. The designed application uses the combination of histograms of oriented gradients and classification based on SVM (Support Vector Machines) for detecting players in the picture. Moreover, a particle filter is used for tracking detected players. The whole system was fully tested and the results are shown in the graphs and tables with verbal descriptions.

This thesis deals with an automatic counting of cylinders placed on the back of a truck using images taken by a camera mounted above the car. To achieve this goal, an SVM classifier based on HOG image descriptors has been trained to detect the cylinders. Further, a tracking method based on optical flow estimation has been designed to track the cylinders through image sequences. The result of the thesis is an application that counts bottles with precision 93,08 % placed on the truck and visualizes results of the detection.

This paper is focused on object learning and recognizing in the image and in the image stream. More specifically on learning and recognizing humans or theirs parts in case they are partly occluded, with possible usage on robotic platforms. This task is based on features called Histogram of Oriented Gradients (HOG) which can work quite well with different poses the human can be in. The human is split into several parts and those parts are detected individually. Then a system of voting is introduced in which detected parts votes for the final positions of found people. For training the detector a linear SVM is used. Then the Kalman filter is used for stabilization of the detector in case of detecting from image stream.