Vehicle self-localization, the ability of a vehicle to determine its own location, is vital for many aspects of Intelligent Transportation Systems (ITS) and telematics where it is often a building block in a more complex system. Navigation systems are perhaps the most obvious example, requiring knowledge of the vehicle's location on a map to calculate a route to a desired destination. Other pervasive examples are the monitoring of vehicle fleets for tracking shipments or dispatching emergency vehicles, and in public transit systems to inform riders of time-of-arrival thereby assisting trip planning. These system often depend on Global Positioning System (GPS) technology to provide vehicle localization information; however, GPS is challenged in urban environments where satellite visibility and multipath conditions are common. Vehicle localization is made more robust to these issues through augmentation of GPS-based localization with complementary sensors, thereby improving the performance and reliability of systems that depend on localization information. This thesis investigates the augmentation of vehicle localization systems with visual context. Positioning the vehicle with respect to objects in its surrounding environment in addition to using GPS constraints the possible vehicle locations, to provide improved localization accuracy compared to a system relying solely on GPS. A modular system architecture based on Bayesian filtering is proposed in this thesis that enables existing localization systems to be augmented by visual context while maintaining their existing capabilities. It is shown in this thesis that localization errors caused by GPS signal multipath can be reduced by positioning the vehicle with respect to visually-detected intersection road markings. This error reduction is achieved when the identities of the detected road marking and the road being driven are known a priori. It is further shown how to generalize the approach to the situation when the identities of these parameters are unknown. In this situation, it is found that the addition of visual context to the vehicle localization system reduces the ambiguity of identifying the road being driven by the vehicle. The fact that knowledge of the road being driven is required by many applications of vehicle localization makes this a significant finding. A related problem is also explored in this thesis: that of using vehicle position information to augment machine vision. An approach is proposed whereby a machine vision system and a vehicle localization system can share their information with one another for mutual benefit. It is shown that, using this approach, the most uncertain of these systems benefits the most by this sharing of information. Augmenting vehicle localization with visual context is neither farfetched nor impractical given the technology available in today's vehicles. It is not uncommon for a vehicle today to come equipped with a GPS-based navigation system, and cameras for lane departure detection and parking assistance. The research in this thesis brings the capability for these existing systems to work together.

No description available.

Since the last decade the problem of surface inspection has been receiving great attention from the scientific community, the quality control and the maintenance of products are key points in several industrial applications.The railway associations spent much money to check the railway infrastructure. The railway infrastructure is a particular field in which the periodical surface inspection can help the operator to prevent critical situations. The maintenance and monitoring of this infrastructure is an important aspect for railway association.That is why the surface inspection of railway also makes importance to the railroad authority to investigate track components, identify problems and finding out the way that how to solve these problems. In railway industry, usually the problems find in railway sleepers, overhead, fastener, rail head, switching and crossing and in ballast section as well. In this thesis work, I have reviewed some research papers based on AI techniques together with NDT techniques which are able to collect data from the test object without making any damage. The research works which I have reviewed and demonstrated that by adopting the AI based system, it is almost possible to solve all the problems and this system is very much reliable and efficient for diagnose problems of this transportation domain. I have reviewed solutions provided by different companies based on AI techniques, their products and reviewed some white papers provided by some of those companies. AI based techniques likemachine vision, stereo vision, laser based techniques and neural network are used in most cases to solve the problems which are performed by the railway engineers.The problems in railway handled by the AI based techniques performed by NDT approach which is a very broad, interdisciplinary field that plays a critical role in assuring that structural components and systems perform their function in a reliable and cost effective fashion. The NDT approach ensures the uniformity, quality and serviceability of materials without causing any damage of that materials is being tested. This testing methods use some way to test product like, Visual and Optical testing, Radiography, Magnetic particle testing, Ultrasonic testing, Penetrate testing, electro mechanic testing and acoustic emission testing etc. The inspection procedure has done periodically because of better maintenance. This inspection procedure done by the railway engineers manually with the aid of AI based techniques.The main idea of thesis work is to demonstrate how the problems can be reduced of thistransportation area based on the works done by different researchers and companies. And I have also provided some ideas and comments according to those works and trying to provide some proposal to use better inspection method where it is needed.The scope of this thesis work is automatic interpretation of data from NDT, with the goal of detecting flaws accurately and efficiently. AI techniques such as neural networks, machine vision, knowledge-based systems and fuzzy logic were applied to a wide spectrum of problems in this area. Another scope is to provide an insight into possible research methods concerning railway sleeper, fastener, ballast and overhead inspection by automatic interpretation of data.In this thesis work, I have discussed about problems which are arise in railway sleepers,fastener, and overhead and ballasted track. For this reason I have reviewed some research papers related with these areas and demonstrated how their systems works and the results of those systems. After all the demonstrations were taking place of the advantages of using AI techniques in contrast with those manual systems exist previously.This work aims to summarize the findings of a large number of research papers deploying artificial intelligence (AI) techniques for the automatic interpretation of data from nondestructive testing (NDT). Problems in rail transport domain are mainly discussed in this work. The overall work of this paper goes to the inspection of railway sleepers, fastener, ballast and overhead.

Vehicle self-localization, the ability of a vehicle to determine its own location, is vital for many aspects of Intelligent Transportation Systems (ITS) and telematics where it is often a building block in a more complex system. Navigation systems are perhaps the most obvious example, requiring knowledge of the vehicle's location on a map to calculate a route to a desired destination. Other pervasive examples are the monitoring of vehicle fleets for tracking shipments or dispatching emergency vehicles, and in public transit systems to inform riders of time-of-arrival thereby assisting trip planning. These system often depend on Global Positioning System (GPS) technology to provide vehicle localization information; however, GPS is challenged in urban environments where satellite visibility and multipath conditions are common. Vehicle localization is made more robust to these issues through augmentation of GPS-based localization with complementary sensors, thereby improving the performance and reliability of systems that depend on localization information. This thesis investigates the augmentation of vehicle localization systems with visual context. Positioning the vehicle with respect to objects in its surrounding environment in addition to using GPS constraints the possible vehicle locations, to provide improved localization accuracy compared to a system relying solely on GPS. A modular system architecture based on Bayesian filtering is proposed in this thesis that enables existing localization systems to be augmented by visual context while maintaining their existing capabilities. It is shown in this thesis that localization errors caused by GPS signal multipath can be reduced by positioning the vehicle with respect to visually-detected intersection road markings. This error reduction is achieved when the identities of the detected road marking and the road being driven are known a priori. It is further shown how to generalize the approach to the situation when the identities of these parameters are unknown. In this situation, it is found that the addition of visual context to the vehicle localization system reduces the ambiguity of identifying the road being driven by the vehicle. The fact that knowledge of the road being driven is required by many applications of vehicle localization makes this a significant finding. A related problem is also explored in this thesis: that of using vehicle position information to augment machine vision. An approach is proposed whereby a machine vision system and a vehicle localization system can share their information with one another for mutual benefit. It is shown that, using this approach, the most uncertain of these systems benefits the most by this sharing of information. Augmenting vehicle localization with visual context is neither farfetched nor impractical given the technology available in today's vehicles. It is not uncommon for a vehicle today to come equipped with a GPS-based navigation system, and cameras for lane departure detection and parking assistance. The research in this thesis brings the capability for these existing systems to work together.

The finite element method (FEM) has difficulty solving certain problems where adaptive mesh is needed. Motivated by two engineering problems in live-object handling project, this research focus on a new computational method called the meshless method (MLM). This method is built upon the same theoretical framework as FEM but needs no mesh. Consequently, the computation becomes more stable and the adaptive computational scheme becomes easier to develop. In this research, we investigate practical issues related to the MLM and develop an adaptive algorithm to automatically insert additional nodes and improve computational accuracy. The study has been in the context of the two engineering problems: magnetic field computation and large deformation contact. First, we investigate the effect of two discretization methods (strong-form and weak-form) in MLM for solving linear magnetic field problems. Special techniques for handling the discontinuity boundary condition at material interfaces are proposed in both discretization methods to improve the computational accuracy. Next, we develop an adaptive computational scheme in MLM that is comprised of an error estimation algorithm, a nodal insertion scheme and a numerical integration scheme. As a more general approach, this method can automatically locate the large error region around the material interface and insert nodes accordingly to reduce the error. We further extend the adaptive method to solve nonlinear large deformation contact problems. With the ability to adaptively insert nodes during the computation, the developed method is capable of using fewer nodes for initial computation and thus, effectively improves the computational efficiency. Engineering applications of the developed methods have been demonstrated by two practical engineering problems. In the first problem, the MLM has been utilized to simulate the dynamic response of a non-contact mechanical-magnetic actuator for optimizing the design of the actuator. In the second problem, the contact between the flexible finger and the live poultry product has been analyzed by using MLM. These applications show the developed method can be applied to a broad spectrum of engineering applications where an adaptive mesh is needed.

In general, stereovision can be defined as a two part problem. The first is the correspondence problem. This involves determining the image point in each image of a set of images that correspond to the same physical point P. We will call this set of image points, N. The second problem is the reconstruction problem. Once a set of image points, N, that correspond to point P has been determined, N is then used to extract three dimensional information about point P. This master's thesis presents three novel solutions to the reconstruction problem. Two of the techniques presented are for detecting the location of a 3-D point and one for detecting a line expressed in a three dimensional coordinate system. These techniques are tested and validated using a unique 3-D finger detection algorithm. The techniques presented are unique because of their simplicity and because they do not require the cameras to be placed in specific locations, orientations or have specific alignments. On the contrary, it will be shown that the techniques presented in this thesis allow the two cameras used to assume almost any relative pose provided that the object of interest is within their field of view. The relative pose of the cameras at a given instant in time, along with basic equations from the perspective image model are used to form a system of equations that when solved, reveal the 3-D coordinates of a particular fixed point of interest or the three dimensional equation of a fixed line of interest. Finally, it will be shown that a single moving camera can successfully perform the same line and point detection accomplished by two cameras by altering the pose of the camera. The results presented in this work are beneficial to any typical stereovision application because of the computational ease in comparison to other point and line reconstruction techniques. But more importantly, this work allows for a single moving camera to perceive three-dimensional position information, which effectively removes the two camera constraint for a stereo vision system. When used with other monocular cues such as texture or color, the work presented in this thesis could be as accurate as binocular stereo vision at interpreting three dimensional information. Thus, this work could potentially increase the three dimensional perception of a robot that normally uses one camera, such as an eye-in-hand robot or a snake like robot.

Vision is the most celebrated human sense. Eighty percent of the information humans receive is obtained through vision. Machines capable of capturing images are now ubiquitous, but until recently, they have been unable to recognize objects in the images they capture. In effect, machines have been blind. This paper explores the revolutionary new capability of a camera to recognize whether a human is present in an image and take detailed measurements of the person’s dimensions. It explains how the hardware and software of the camera work to provide this remarkable capability in just 200 milliseconds per image. To demonstrate these capabilities, a home security application has been built called Security with Visual Understanding (SVU). SVU is a hardware/software solution that detects a human and then performs biometric authentication by comparing the dimensions of the seen person against a database of known people. If the person is unrecognized, an alarm is sounded, and a picture of the intruder is sent via SMS text message to the home owner. Analysis is performed to measure the tolerance of the SVU algorithm for differentiating between two people based on their body dimensions. / text

An autonomous machine vision guided plant sensing and monitoring system was designed and constructed to continuously monitor plant related features: color (red-green-blue, hue-saturation-luminance, and color brightness), morphology (top projected canopy area), textural (entropy, energy, contrast, and homogeneity), Normalized Difference Vegetative Index (NDVI) (as well as other similar indices from the color and NIR channels), and thermal (plant and canopy temperature). Several experiments with repeated water stress cycles, using the machine vision system, was conducted to evaluate the machine vision system's performance to determine the timeliness of induced plant water stress detection. The study aimed at identifying significant features separating the control and treatment from an induced water stress experiment and also identifying, amongst the plant canopy, the location of the emerging water stress with the found significant features. Plant cell severity had been ranked based on the cell's accumulated feature count and converted to a color coded graphical canopy image for the remote operator to evaluate. The overall feature analysis showed that the morphological feature, Top Projected Canopy Area, was found to be a good marker for the initial growth period while the vegetation indices (ENDVI, NDVIBlue, and NDVIRed) were more capable at capturing the repeated stress occurrences during the various stages of the lettuce crop. Furthermore, the crop's canopy temperature was shown to be a significant and dominant marker to timely detect the water stress occurrences. The graphical display for the remote user showed the severity of summed features to equal the detection of the human vision. Capabilities and limitations of the developed system and stress detection methodology were documented with recommendations for future improvements for the crop monitoring/production system. An example web based decision support platform was created for data collection, storage, analysis, and display of the data/imagery collected for a remote operator.

Current methods of determining spinal cord recovery in mice, post-directed injury, are qualitative measures. This is due to the small size and quickness of mice. This thesis presents a design for a gait acquisition and analysis system able to capture the footfalls of a mouse, extract position and timing data, and report quantitative gait metrics to the operator. These metrics can then be used to evaluate the recovery of the mouse. This work presents the design evolution of the system, from initial sensor design concepts through prototyping and testing to the final implementation. The system utilizes a machine vision camera, a well-designed walkway enclosure, and image processing techniques to capture and analyze paw strikes. Quantitative results gained from live animal experiments are presented, and it is shown how the measurements can be used to determine healthy, injured, and recovered gait.

The health and productive output of dairy cows can be closely correlated to individual cow feed intake. Being able to monitor feed intake on a daily basis is beneficial dairy farm management. Each cow can be addressed individually with minimal time required from those working with the animals. This is essential as time management is closely tied to resource management in a dairy operation. Anything that can save time and resources and increase profitability and herd health is a paramount advantage in dairy farming. This study examined the use of machine vision structured light illumination three-dimensional scanning of cow feed to determine the volume and weight of feed in a bin before and after feeding dairy cow. Calibration and control tests were conducted to determine the effectiveness and capability of implementing such a machine vision feed scanning system. Such a system is ideal as it does not obstruct workflow or cow feeding behavior. This is an improvement over existing systems as the system in this research study can be implemented into existing farm operations with minimal effort and costs.