<div>Plant Phenotyping is a set of methodologies for measuring and analyzing characteristic traits of a plant. While traditional plant phenotyping techniques are labor-intensive and destructive, modern imaging technologies have provided faster, non-invasive, and more cost-effective capabilities for plant phenotyping. Among different image-based phenotyping platforms, I focus on phenotyping with image data captured by Unmanned Aerial Vehicle (UAV) and ground vehicles. The crop plant used in my study is sorghum [Sorghum bicolor (L.) Moench]. In this thesis, I present multiple methods to estimate plot-level and plant-level plant traits from data collected by various platforms, including UAV and ground vehicles. I propose an image plant phenotyping system that provides end-to-end RGB data analysis for plant scientists. I describe a plant segmentation method using HSV color information. I introduce two methods to locate the center of the plants using Multiple Instance Learning (MIL) and Convolutional Neural Networks (CNN). I present three methods to segment individual leaves by shape-based approaches in both Cartesian coordinates and Polar coordinates. I propose a method to estimate leaf length and width for overhead leaf images. I describe a method to estimate leaf angle from data collected by a modified wheel-based sprayer with a sensor boom vehicle, Phenorover. Methods are tested and verified on image data collected by UAV and ground vehicle platforms in sorghum fields in West Lafayette, Indiana, USA. Estimated phenotypic traits include plant locations, the number of plants per plot, leaf area, canopy cover, Leaf Area Index (LAI), leaf count, leaf angle, leaf length, and leaf width.</div>

The organization International Aid Services (IAS) provides people in East Africawith clean water through well drilling. The wells are located in surroundingsfar away for the investors to inspect and therefore IAS wishes to be able to monitortheir wells to get a better overview if different types of improvements needto be made. To see the load on different water sources at different times of theday and during the year, and to know how many people that are visiting thewells, is of particular interest. In this paper, a method is proposed for countingpeople around the wells. The goal is to choose a suitable method for detectinghumans in images and evaluate how it performs. The area of counting humansin images is not a new topic, though it needs to be taken into account that thesituation implies some restrictions. A Raspberry Pi with an associated camerais used, which is a small embedded system that cannot handle large and complexsoftware. There is also a limited amount of data in the project. The methodproposed in this project uses a pre-trained convolutional neural network basedobject detector called the Single Shot Detector, which is adapted to suit smallerdevices and applications. The pre-trained network that it is based on is calledMobileNet, a network that is developed to be used on smaller systems. To see howgood the chosen detector performs it will be compared with some other models.Among them a detector based on the Inception network, a significantly larger networkthan the MobileNet. The base network is modified by transfer learning.Results shows that a fine-tuned and modified network can achieve better result,from a F1-score of 0.49 for a non-fine-tuned model to 0.66 for the fine-tuned one.

Cette thèse est centrée sur le problème de la détection d'objets saillants et de leur segmentation dans une vidéo en vue de détecter les objets les plus attractifs ou d'affecter des identités cohérentes d'objets à chaque pixel d'une séquence vidéo. Concernant la détection d'objets saillants dans vidéo, outre une revue des techniques existantes, une nouvelle approche et l'extension d'un modèle sont proposées; de plus une approche est proposée pour la segmentation d'instances d'objets vidéo. Pour la détection d'objets saillants dans une vidéo, nous proposons : (1) une approche traditionnelle pour détecter l'objet saillant dans sa totalité à l'aide de la notion de "bordures virtuelles". Un filtre guidé est appliqué sur la sortie temporelle pour intégrer les informations de bord spatial en vue d'une meilleure détection des bords de l'objet saillants. Une carte globale de saillance spatio-temporelle est obtenue en combinant la carte de saillance spatiale et la carte de saillance temporelle en fonction de l'entropie. (2) Une revue des développements récents des méthodes basées sur l'apprentissage profond est réalisée. Elle inclut les classifications des méthodes de l'état de l'art et de leurs architectures, ainsi qu'une étude expérimentale comparative de leurs performances. (3) Une extension d'un modèle de l'approche traditionnelle proposée en intégrant un procédé de détection d'objet saillant d'image basé sur l'apprentissage profond a permis d'améliorer encore les performances. Pour la segmentation des instances d'objets dans une vidéo, nous proposons une approche d'apprentissage profond dans laquelle le calcul de la confiance de déformation détermine d'abord la confiance de la carte masquée, puis une sélection sémantique est optimisée pour améliorer la carte déformée, où l'objet est réidentifié à l'aide de l'étiquettes sémantique de l'objet cible. Les approches proposées ont été évaluées sur des jeux de données complexes et de grande taille disponibles publiquement et les résultats expérimentaux montrent que les approches proposées sont plus performantes que les méthodes de l'état de l'art. / This thesis focuses on the problem of video salient object detection and video object instance segmentation which aim to detect the most attracting objects or assign consistent object IDs to each pixel in a video sequence. One approach, one overview and one extended model are proposed for video salient object detection, and one approach is proposed for video object instance segmentation. For video salient object detection, we propose: (1) one traditional approach to detect the whole salient object via the adjunction of virtual borders. A guided filter is applied on the temporal output to integrate the spatial edge information for a better detection of the salient object edges. A global spatio-temporal saliency map is obtained by combining the spatial saliency map and the temporal saliency map together according to the entropy. (2) An overview of recent developments for deep-learning based methods is provided. It includes the classifications of the state-of-the-art methods and their frameworks, and the experimental comparison of the performances of the state-of-the-art methods. (3) One extended model further improves the performance of the proposed traditional approach by integrating a deep-learning based image salient object detection method For video object instance segmentation, we propose a deep-learning approach in which the warping confidence computation firstly judges the confidence of the mask warped map, then a semantic selection is introduced to optimize the warped map, where the object is re-identified using the semantics labels of the target object. The proposed approaches have been assessed on the published large-scale and challenging datasets. The experimental results show that the proposed approaches outperform the state-of-the-art methods.

A suite of new collision avoidance systems (CAS) is presented for use in heavy vehicles whose structure and size necessarily impede driver visibility is introduced. The main goal of the project is to determine the appropriate use of each of the commercially available technologies and, where possible, produce a low cost variant suitable for use in proximity detection on large mining industry haul trucks. CAS variants produced were subjected to a field demonstration and, linked to the output from the earlier CAS 1 project, (a production high-definition in-cabin video monitor and r/f tagging system). The CAS 2 system used low cost Doppler continuous wave radar antennae coupled to the CAS 1 monitor to indicate the presence of an object moving at any speed above 3 Km/h relative to the antennae. The novelty of the CAS 3 system lies in the design of 3 interconnected, modules. The modules are 8 radar antennae (as used in CAS 2) modules located on the truck, software to interface with the end user (i.e. the drivers of the trucks) and a display unit. Modularisation enables the components to be independently tested, evaluated and replaced when in use. The radar antennae modules and the system as a whole are described together with the empirical tests conducted and results obtained. The tests, drawing on Monte-Carlo simulation techniques, demonstrate both the 'correctness' of the implementations and the effectiveness of the system. The results of the testing of the final prototype unit were highly successful both as a computer simulation level and in practical tests on light vehicles. A number of points, (as a consequence of the field test), are reviewed and their application to future projects discussed.

One of the central problems in computer vision is the automatic recognition of object classes. In particular, the detection of the class of human faces is a problem that generates special interest due to the large number of applications that require face detection as a first step. In this thesis we approach the problem of face detection as a joint detection and segmentation problem, in order to precisely localize faces with pixel accurate masks. Even though this is our primary goal, in finding a solution we have tried to create a general framework as independent as possible of the type of object being searched. For that purpose, the technique relies on a hierarchical region-based image model, the Binary Partition Tree, where objects are obtained by the union of regions in an image partition. In this work, this model is optimized for the face detection and segmentation tasks. Different merging and stopping criteria are proposed and compared through a large set of experiments. In the proposed system the intra-class variability of faces is managed within a learning framework. The face class is characterized using a set of descriptors measured on the tree nodes, and a set of one-class classifiers. The system is formed by two strong classifiers. First, a cascade of binary classifiers simplifies the search space, and afterwards, an ensemble of more complex classifiers performs the final classification of the tree nodes. The system is extensively tested on different face data sets, producing accurate segmentations and proving to be quite robust to variations in scale, position, orientation, lighting conditions and background complexity. We show that the technique proposed for faces can be easily adapted to detect other object classes. Since the construction of the image model does not depend on any object class, different objects can be detected and segmented using the appropriate object model on the same image model. New object models can be easily built by selecting and training a suitable set of descriptors and classifiers. Finally, a tracking mechanism is proposed. It combines the efficiency of the mean-shift algorithm with the use of regions to track and segment faces through a video sequence, where both the face and the camera may move. The method is extended to deal with other deformable objects, using a region-based graph-cut method for the final object segmentation at each frame. Experiments show that both mean-shift based trackers produce accurate segmentations even in difficult scenarios such as those with similar object and background colors and fast camera and object movements. Lloc i / Un dels problemes més importants en l'àrea de visió artificial és el reconeixement automàtic de classes d'objectes. En particular, la detecció de la classe de cares humanes és un problema que genera especial interès degut al gran nombre d'aplicacions que requereixen com a primer pas detectar les cares a l'escena. A aquesta tesis s'analitza el problema de detecció de cares com un problema conjunt de detecció i segmentació, per tal de localitzar de manera precisa les cares a l'escena amb màscares que arribin a precisions d'un píxel. Malgrat l'objectiu principal de la tesi és aquest, en el procés de trobar una solució s'ha intentat crear un marc de treball general i tan independent com fos possible del tipus d'objecte que s'està buscant. Amb aquest propòsit, la tècnica proposada fa ús d'un model jeràrquic d'imatge basat en regions, l'arbre binari de particions (BPT: Binary Partition Tree), en el qual els objectes s'obtenen com a unió de regions que provenen d'una partició de la imatge. En aquest treball, s'ha optimitzat el model per a les tasques de detecció i segmentació de cares. Per això, es proposen diferents criteris de fusió i de parada, els quals es comparen en un conjunt ampli d'experiments. En el sistema proposat, la variabilitat dins de la classe cara s'estudia dins d'un marc de treball d'aprenentatge automàtic. La classe cara es caracteritza fent servir un conjunt de descriptors, que es mesuren en els nodes de l'arbre, així com un conjunt de classificadors d'una única classe. El sistema està format per dos classificadors forts. Primer s'utilitza una cascada de classificadors binaris que realitzen una simplificació de l'espai de cerca i, posteriorment, s'aplica un conjunt de classificadors més complexes que produeixen la classificació final dels nodes de l'arbre. El sistema es testeja de manera exhaustiva sobre diferents bases de dades de cares, sobre les quals s'obtenen segmentacions precises provant així la robustesa del sistema en front a variacions d'escala, posició, orientació, condicions d'il·luminació i complexitat del fons de l'escena. A aquesta tesi es mostra també que la tècnica proposada per cares pot ser fàcilment adaptable a la detecció i segmentació d'altres classes d'objectes. Donat que la construcció del model d'imatge no depèn de la classe d'objecte que es pretén buscar, es pot detectar i segmentar diferents classes d'objectes fent servir, sobre el mateix model d'imatge, el model d'objecte apropiat. Nous models d'objecte poden ser fàcilment construïts mitjançant la selecció i l'entrenament d'un conjunt adient de descriptors i classificadors. Finalment, es proposa un mecanisme de seguiment. Aquest mecanisme combina l'eficiència de l'algorisme mean-shift amb l'ús de regions per fer el seguiment i segmentar les cares al llarg d'una seqüència de vídeo a la qual tant la càmera com la cara es poden moure. Aquest mètode s'estén al cas de seguiment d'altres objectes deformables, utilitzant una versió basada en regions de la tècnica de graph-cut per obtenir la segmentació final de l'objecte a cada imatge. Els experiments realitzats mostren que les dues versions del sistema de seguiment basat en l'algorisme mean-shift produeixen segmentacions acurades, fins i tot en entorns complicats com ara quan l'objecte i el fons de l'escena presenten colors similars o quan es produeix un moviment ràpid, ja sigui de la càmera o de l'objecte.

Visual target tracking problem consists of two topics: Obtaining targets from camera measurements and target tracking. Even though it has been studied for more than 30 years, there are still some problems not completely solved. Especially in the case of multiple targets, association of measurements to targets, creation of new targets and deletion of old ones are among those. What is more, it is very important to deal with the occlusion and crossing targets problems suitably. We believe that a slightly modified version of multiple hypothesis tracking can successfully deal with most of the aforementioned problems with sufficient success. Distance, track size, track color, gate size and track history are used as parameters to evaluate the hypotheses generated for measurement to track association problem whereas size and color are used as parameters for occlusion problem. The overall tracker has been fine tuned over some scenarios and it has been observed that it performs well over the testing scenarios as well. Furthermore the performance of the tracker is analyzed according to those parameters in both association and occlusion handling situations.

There is an increasing trend towards object detection from aerial and satellite images. Most of the widely used object detection algorithms are based on local features. In such an approach, first, the local features are detected and described in an image, then a representation of the images are formed using these local features for supervised learning and these representations are used during classification . In this thesis, Harris and SIFT algorithms are used as local feature detector and SIFT approach is used as a local feature descriptor. Using these tools, Bag of Visual Words algorithm is examined in order to represent an image by the help of histograms of visual words. Finally, SVM classifier is trained by using positive and negative samples from a training set. In addition to the classical bag of visual words approach, two novel extensions are also proposed. As the first case, the visual words are weighted proportional to their importance of belonging to positive samples. The important features are basically the features occurring more in the object and less in the background. Secondly, a principal component analysis after forming the histograms is processed in order to remove the undesired redundancy and noise in the data, reduce the dimension of the data to yield better classifying performance. Based on the test results, it could be argued that the proposed approach is capable to detecting a number of geo-spatial objects, such as airplane or ships, for a reasonable performance.

Moving object detection techniques can be divided into two categories based on the type of the camera which is either static or active. Methods of static cameras can detect moving objects according to the variable regions on the video frame. However, the same method is not suitable for active cameras. The task of moving object detection for active cameras generally needs more complex algorithms and unique solutions. The aim of this thesis work is real time detection and tracking of moving objects with an active camera. For this purpose, feature based algorithms are implemented due to the computational efficiency of these kinds of algorithms and SURF (Speeded Up Robust Features) is mainly used for these algorithms. An algorithm is developed in C++ environment and OpenCV library is frequently used. The developed algorithm is capable of detecting and tracking moving objects by using a PTZ (Pan-Tilt-Zoom) camera at a frame rate of approximately 5 fps and with a resolution of 640x480.

In this thesis, a video tracking method is proposed that is based on both computer vision and estimation theory. For this purpose, the overall study is partitioned into four related subproblems. The first part is moving object detection / for moving object detection, two different background modeling methods are developed. The second part is feature extraction and estimation of optical flow between video frames. As the feature extraction method, a well-known corner detector algorithm is employed and this extraction is applied only at the moving regions in the scene. For the feature points, the optical flow vectors are calculated by using an improved version of Kanade Lucas Tracker. The resulting optical flow field between consecutive frames is used directly in proposed tracking method. In the third part, a particle filter structure is build to provide tracking process. However, the particle filter is improved by adding optical flow data to the state equation as a correction term. In the last part of the study, the performance of the proposed approach is compared against standard implementations particle filter based trackers. Based on the simulation results in this study, it could be argued that insertion of vision-based optical flow estimation to tracking formulation improves the overall performance.

There is a rising interest in geospatial object detection due to not only the complexity of manual processing of such huge amount of data provided by high resolution satellite imagery but also for military application needs. A fundamental and yet state-of-the art approach for object detection is based on methods that utilize the global appearance. In such a holistic approach, the information of the object class is aimed to be modeled as a whole in the learning phase. And during the classification, a decision is taken at each window of the test image. In this thesis, two different discriminative methods are investigated for airplane detection from satellite images. In the first method, Haar-like features are used as weak classifiers for the airplane class representation. Then the AdaBoost learning algorithm is used to select the critical visual features that represent the airplanes best. Finally, a cascade of classifiers is constructed in order to speed-up the classifier. In the second method, a computationally efficient appearance-based algorithm for airplane detection is presented. An operator exploiting the edge information via gray level differences between the target and its background is constructed with Haar-like polygon regions using the shape information of the airplane as an invariant. The airplanes matching the operator are supposed to yield higher responses around the centroid of the object. Fast evaluation of the operator is achieved by means of integral image. The proposed algorithm has promising results in terms of accuracy in detecting aircraft type geospatial objects from satellite imagery.