ITC/USA 2014 Conference Proceedings / The Fiftieth Annual International Telemetering Conference and Technical Exhibition / October 20-23, 2014 / Town and Country Resort & Convention Center, San Diego, CA / This paper presents an effective multi-layer background modeling method to detect moving objects by exploiting the advantage of novel distinctive features and hierarchical structure of the Codebook (CB) model. In the block-based structure, the mean-color feature within a block often does not contain sufficient texture information, causing incorrect classification especially in large block size layers. Thus, the Binary Ordered Dithering (BOD) feature becomes an important supplement to the mean RGB feature In summary, the uniqueness of this approach is the incorporation of the halftoning scheme with the codebook model for superior performance over the existing methods.

From the viewpoint of applications, conventional cameras are usually limited in their fields of view. The omni-directional camera has a full range in all directions, which gains the complete field of view. In the past, a moving object can be detected, only when the camera is static or moving with a known speed. If those methods are employed to mobile robots or vehicles, it will be difficult to determine the motion of moving objects observed by the camera. In this paper, we assume the omni-directional camera is mounted on a moving platform, which travels with a planar motion. The region of floor in the omni-directional image and the brightness constraint equation are applied to estimate the ego-motion. The depth information is acquired from the floor image to solve the problem that cannot be obtained by single camera systems. Using the estimated ego-motion, the optical flow caused by the floor motion can be computed. Therefore, comparing its direction with the direction of the optical flow on the image leads to detection of a moving object. Due to the depth information, even if the camera is in the condition that combining translational and rotational motions, a moving object can still be accurately identified.

In this study, primary steps of a visual surveillance system are presented: moving object detection and tracking of these moving objects. Background subtraction has been performed to detect the moving objects in the video, which has been taken from a static camera. Four methods, frame differencing, running (moving) average, eigenbackground subtraction and mixture of Gaussians, have been used in the background subtraction process. After background subtraction, using some additional operations, such as morphological operations and connected component analysis, the objects to be tracked have been acquired. While tracking the moving objects, active contour models (snakes) has been used as one of the approaches. In addition to this method / Kalman tracker and mean-shift tracker are other approaches which have been utilized. A new approach has been proposed for the problem of tracking multiple targets. We have implemented this method for single and multiple camera configurations. Multiple cameras have been used to augment the measurements. Homography matrix has been calculated to find the correspondence between cameras. Then, measurements and tracks have been associated by the new tracking method.

Video surveillance has long been in use to monitor security sensitive areas such as banks, department stores, crowded public places and borders. The rise in computer speed, availability of cheap large-capacity storage devices and high speed network infrastructure enabled the way for cheaper, multi sensor video surveillance systems. In this thesis, the problem of tracking multiple targets with multiple cameras has been discussed. Cameras have been located so that they have overlapping fields of vision. A dynamic background-modeling algorithm is described for segmenting moving objects from the background, which is capable of adapting to dynamic scene changes and periodic motion, such as illumination change and swaying of trees. After segmentation of foreground scene, the objects to be tracked have been acquired by morphological operations and connected component analysis. For the purpose of tracking the moving objects, an active contour model (snakes) is one of the approaches, in addition to a Kalman tracker. As the main tracking algorithm, a rule based tracker has been developed first for a single camera, and then extended to multiple cameras. Results of used and proposed methods are given in detail.

<div>Unmanned Aerial Vehicle (UAV) technology is being increasingly used in a wide variety of applications ranging from remote sensing, to delivery, to security. As the number of UAVs increases, there is a growing need for UAV to UAV detection and tracking systems for both collision avoidance and coordination. Among possible solutions, autonamous “see-and-avoid” systems based on low-cost high-resolution video cameras offer the important advantages of light-weight and low power sensors. However, in order to be effective, camera based “see-and-avoid” systems will require sensitive, robust, and computationally efficient algorithms for UAV to UAV detect and tracking (U2U-D&T) from a moving camera.</div><div><br></div><div>In this thesis, we propose a general architecture for a highly accurate and computationally efficient U2U-D&T algorithms for detecting UAVs from a camera mounted on a moving UAV platform. The thesis contains three studies of U2U-D&T algorithms.<br></div><div><br></div><div>In the first study, we present a new approach to detect and track other UAVs from a single camera in our own UAV. Given the sequence of video frames, we estimate the background motion via perspective transformation model and then identify distinctive points in the background subtracted image to detect moving objects. We find spatio-temporal characteristics of each moving object through optical flow matching and then classify our targets which have very different motion compared with background. We also perform tracking based on Kalman filter to enforce the temporal consistency on our detection. The algorithm is tested on real videos from UAVs and results show that it is effective to detect and track small UAVs with limited computing resources.<br></div><div><br></div><div>In the second study, we present a new approach to detect and track UAVs from a single camera mounted on a different UAV. Initially, we estimate background motions via a perspective transformation model and then identify moving object candidates in the background subtracted image through deep learning classifier trained on manually labeled datasets. For each moving object candidates, we find spatio-temporal traits through optical flow matching and then prune them based on their motion patterns compared with the background. Kalman filter is applied on pruned moving objects to improve temporal consistency among the candidate detections. The algorithm was validated on video datasets taken from a UAV. Results demonstrate that our algorithm can effectively detect and track small UAVs with limited computing resources. </div><div><br></div><div>The system in the third study is based on a computationally efficient pipeline consisting of moving object detection from a motion stabilized image, classification with a hybrid neural network, followed by Kalmann tracking. The algorithm is validated using video data collected from multiple fixed-wing UAVs that is manually ground-truthed and publicly available. Results indicate that the proposed algorithm can be implemented on practical hardware and robustly achieves highly accurate detection and tracking of even distant and faint UAVs.<br></div>

Successful and high precision localization is an important feature for autonomous vehicles in an urban environment. GPS solutions are not good on their own and laser, sonar and radar are often used as complementary sensors. Localization with these sensors requires the use of techniques grouped under the acronym SLAM (Simultaneous Localization And Mapping). These techniques work by comparing the current sensor inputs to either an incrementally built or known map, also adding the information to the map.Most of the SLAM techniques assume the environment to be static, which means that dynamics and clutter in the environment might cause SLAM to fail. To ob-tain a more robust algorithm, the dynamics need to be dealt with. This study seeks a solution where measurements from different points in time can be used in pairwise comparisons to detect non-static content in the mapped area. Parked cars could for example be detected at a parking lot by using measurements from several different days.The method successfully detects most non-static objects in the different test datasets from the sensor. The algorithm can be used in conjunction with Pose-SLAM to get a better localization estimate and a map for later use. This map is good for localization with SLAM or other techniques since only static objects are left in it.

A DSP-based system is developed in this thesis for tracking ¡§an arbitrary-shaped object¡¨. It uses CCD camera to capture images, and detects in the video sequence. When we want to track a target that we interest, we can make the target in the view of camera. If the target move, the system will lock it and extract its contour by using active contour model. After extracting contour, the system will start to track target and shows the locked image on the LCD screen. The tracking system includes three sub-systems : ¡§Moving Object Detection¡¨, ¡§Active Contour Model¡¨, and ¡§Contour Matching¡¨. From the results of experiment, it can meet the expectation and gain good performance and robustness.

With the development of wireless communications and mobile computing technologies, the applications of moving objects have been developed in many topics, for example, traffic monitoring, mobile E-Commerce, Navigation System, and Geographic Information System. The feature of the moving objects is that objects change their locations continuously. Conventional spatial databases can not support to store the moving objects efficiently, because the databases must be updated frequently. Therefore, it is important to index moving objects for efficiently answering queries about moving objects. Among the spatial indexing methods for predicting current and future data, the approach of parametric spatial access methods has been applied largely, since it needs little memory space to preserve parametric rectangles, and it still provides good performance, so it is adopted generally. The methods of this approach include the TPR-tree, the TPR*-tree, the Bx-tree, and the Bxr-tree. Among those methods, the Bxr-tree improves CPU performance of TPR-tree by expanding query region first, and improves I/O performance of the Bxr-tree by expanding the data blocks additionally. However, the query process of the B$^x_r$-tree is too rough such that it costs too much CPU and I/O time to check the useless data. Therefore, in this thesis, we propose a new data structure and a new query processing method named Adjustable Expanded Index (AEI), to improve the disadvantages of the Bxr-tree. In our method, we let each block records the maximum and minimum speeds of each of eight directions, instead of only the maximum speed of each of four directions in the Bxr-tree method. Based on the data structure, the query region can be expanded in each of eight directions individually, instead of being expanded in each of four directions once in the Bxr-tree method. Moreover, in our AEI method, the data blocks can be expanded according to the direction toward the query region, instead of being expanded in four directions in the Bxr-tree method. In this way, the query process of AEI checks less number of data blocks because it considers the minimum speed of each of eight directions. Furthermore, the objects are divided into four groups in AEI according to their directions, while the Bxr-tree method does not. Only the objects moving to query region will be checked in the query process of AEI. Therefore, we can reduce more number of retrieved data blocks and the number of I/O operations in our method than the Bxr-tree. From our simulation, we show that the query process of the AEI method is more efficient than that of the Bxr-tree in term of the average numbers of retrieved data blocks and I/O operations.

Στη παρούσα Διπλωματική εργασία μελετήθηκε, προσομοιώθηκε, σχεδιάστηκε και υλοποιήθηκε ένα σύστημα εντοπισμού θέσης κινούμενου αντικειμένου στον τρισδιάστατο χώρο με την χρήση υπερήχων. Για τον εντοπισμό του αντικειμένου κατασκευάστηκε ένα σύστημα δεκτών και ένας πομπός υπερήχων, ο οποίος τοποθετείται στο κινούμενο αντικείμενο εκπέμποντας ένα σήμα χαμηλής αυτοσυσχέτισης με τη βοήθεια ενός μικροεπεξεργαστή. Επίσης αναπτύχθηκε λογισμικό με εύχρηστη διεπαφή, το οποίο χρησιμοποιώντας μοντέρνες θεωρίες ψηφιακής επεξεργασίας ηχητικών σημάτων, δίνει την δυνατότητα στον χρήστη να μελετήσει τις ιδιότητες των σημάτων και να αντιληφθεί την κίνηση του πομπού σε πραγματικό χρόνο. Ένα τέτοιο σύστημα θα μπορούσε να είναι μία ασύρματη πένα η οποία θα λειτουργούσε ως 3D ποντίκι υπολογιστή. Επίσης θα μπορούσε να χρησιμοποιηθεί σε ενσωματωμένα συστήματα με σκοπό τον έλεγχο, την πλοήγηση ή ακόμα και στην επικοινωνία συνεργατικών ρομπότ. / In this Diploma Thesis was studied, simulated, designed and implemented an ultrasonic 3d positioning system of a moving object. In order to track the moving object, one base station and an ultrasonic transmitter were implemented. The latter was embedded in the object and produced a low autocorrelation ultrasonic signal by a microprocessor. Furthermore we developed software with a friendly user interface, which by using modern theories of digital signal processing, enables deep study of signal properties and the real-time monitoring of the trajectory of the moving object. Such a system could be a wireless pen used as a 3D computer mouse and it could be applied successfully in control and navigation embedded systems and even in communication of cooperative robots.

O crescimento do uso de sistemas de posicionamento global (GPS) e outros sistemas de localização espacial tornaram possível o rastreamento de objetos móveis, produzindo um grande volume de um novo tipo de dado, chamado trajetórias de objetos móveis. Existe, entretanto, uma forte lacuna entre a quantidade de dados extraídos destes dispositivos, dotados de sistemas GPS, e a descoberta de conhecimento que se pode inferir com estes dados. Um tipo de descoberta de conhecimento em dados de trajetórias de objetos móveis é a classificação. A classificação de trajetórias é um tema de pesquisa relativamente novo, e poucos métodos tem sido propostos até o presente momento. A maioria destes métodos foi desenvolvido para uma aplicação específica. Poucos propuseram um método mais geral, aplicável a vários domínios ou conjuntos de dados. Este trabalho apresenta um novo método de classificação que transforma as trajetórias em séries temporais, de forma a obter características mais discriminativas para a classificação. Experimentos com dados reais mostraram que o método proposto é melhor do que abordagens existentes. / The growing use of global positioning systems (GPS) and other location systems made the tracking of moving objects possible, producing a large volume of a new kind of data, called trajectories of moving objects. However, there is a large gap between the amount of data generated by these devices and the knowledge that can be inferred from these data. One type of knowledge discovery in trajectories of moving objects is classification. Trajectory classification is a relatively new research subject, and a few methods have been proposed so far. Most of these methods were developed for a specific application. Only a few have proposed a general method, applicable to multiple domains or datasets. This work presents a new classification method that transforms the trajectories into time series, in order to obtain more discriminative features for classification. Experiments with real trajectory data revealed that the proposed approach is more effective than existing approaches.