No description available.

The motion vector for standard MPEG motion compensation is associated to fixed blocks of size 16*16. In many situations, the moving objects are not described by these blocks. In this thesis, we hope to remove this restriction by searching and modifying the motion vectors for moving objects with non-block shape. There are three stages in our motion compression: segmentation of the moving object, modified motion compensation, and Huffman coding for the difference. The first stage is most important part in our work. The major concepts of our segmentation are based upon optical flow segmentation and modification by morphological filtering. Displacement information is important in dynamic image analysis. The method of optical flow has been well applied to compute the displacement in the field of computer vision. We apply the method of optical flow to compute the displacement information and then segment the image by the displacement vectors. This segmented image is further improved by morphology operations, opening and closing. Our modified motion compensation is focus on the segmented moving objects. Therefore, the required coding information for moving object is only the motion vector associated to the motion objects. The shapes of motion objects are obtained from prediction. Experiments have demonstrated that our coding efficiency is inferior to the standard MPEG by 32 %. This is probably we do not have our optimized Huffman coding for the difference coding after motion compensation.

Open-loop position estimation methods are commonly used in mobile robot applications. Their strength lies in the speed and simplicity with which an estimated position is determined. However, these methods can lead to inaccurate or unreliable estimates. Two methods are developed in this thesis. The first uses a single optical sensor and can accurately estimate position under ideal conditions and when wheel slip perpendicular to the axis of the wheel occurs. A second method which uses two optical sensors is developed which can accurately estimate position even when wheel slip parallel to the axis of the wheel occurs. Location of the optical sensors is investigated in order to minimize errors caused by inaccurate sensor readings. Finally, the method is implemented and tested using a potential field based navigation scheme. Estimates of position were found to be as accurate as dead-reckoning in ideal conditions and much more accurate in cases where kinematic violations occur.

In this thesis, we employ optical flow features for the detection of the rigid or non‐rigid single object on an input video. For optical flow estimation, we use the Point Line [PL] method [2] (as a local method) to estimate the motion of the image sequence which is generated from the input video stream. Although the Lukas and Kanade [LK] is a popular local method for estimation of the optical flow, it is weak in dealing with the linear symmetric images even by use of regularization [e.g. Tikhonov]. The PL method is more powerful than the LK method and can properly separate both line flow and point flow. For dealing with rapidly changing data in some part of an image (high motion problem), a gaussian pyramid with five levels (different image resolutions) is employed. In this way, the pyramid height (Level) must be chosen properly according to the maximum optical flow that we expect in each section of the image without iteration. After determining the best‐estimated optical flow vector for every pixel, the algorithm should detect an object on video with its direction to the right or left. By using techniques such as segmentation and averaging the magnitude of flow vectors the program can detect and distinguish rigid objects (e.g. a car) and non‐rigid objects (e.g. a human). Finally the algorithm makes a new video output that includes detected object with flow vectors, the pyramid levels map which has been used for optical flow estimation and a respective binary image.

Recent developments within the biomedical engineering field of using finite element methods to analyze biological structures has resulted in a need for a standardized method to validate these models. The purpose of this thesis was to develop a system to effectively and efficiently validate biological finite element models using 4D medical images. The aortic valve was chosen as the biological model for testing as any solution that could manage the complexity of the valve’s motion would likely work for simpler biological models. The proposed validation method involved 3 steps: estimating a voxel displacement field using a direct method of 3D motion estimation, converting the voxel displacement field into a nodal displacement field, and validating the results of a finite element model by comparing the nodal displacement field of the finite element model to the nodal displacement field from the medical images. The proposed validation method was implemented using synthetic 4D CT images of an aortic valve based on an existing finite element model, where the ground truth was the results of the existing finite element model. Three different direct motion estimation methods were implemented within the first step of the method and compared. The three methods were: 3D Horn-Schunck optical flow, 3D Brox optical flow, and demons method. The addition of a multilevel scheme with a variable scale constant was integrated into each of these motion estimation methods so that larger magnitudes of displacement could by captured. It was found that Horn-Schunck optical flow was best able to capture the motion of the aortic valve throughout a cardiac cycle. The proposed method of validation was able to track the aorta nodes effectively through an entire cardiac cycle and was able to track leaflet nodes through large displacements until the valve closed. Although the general trend of the motion of the aortic valve was captured by the validation method using synthetic medical images, node-to-node comparison was not entirely reliable. Comparison of the general trend was still superior to the current validation methods for biological finite element methods as it considered the motion of the entire structure.

Future frame prediction is a difficult but useful problem to solve in deep learning. The technology can be used to predict future occurrences in a video, anticipate anomalies, and aid autonomous devices in smart decision making. Although there is potential with frame prediction technology, there is still progress that needs to be made with it. As the predicted frame becomes farther away from the last input frame, the image becomes blurry and distorted. This indicates that the model is more uncertain about the motion occurring in the image frame. To reduce model uncertainty shown in predictions, optical flow information from each video was extracted and combined with the video frames. An optical flow-based approach is uncommon in frame prediction and has not been implemented with a fully Convolutional Neural Network (CNN) based architecture. In this work, the change in image quality evaluation metrics and overall image quality is analyzed across 4 different datasets between a state-of-the-art frame prediction model and a modified model that combines optical flow information. The results demonstrate that adding optical flow information improves the model Mean Squared Error (MSE) by 4.11% and its Structural Similarity Index Metric (SSIM) by 0.41% for the Moving MNIST dataset. Optical flow improved the SSIM value of Taxi BJ, KTH, and KITTI by 0.02%, 0.011%, and 1.297% respectively. While there was a consistent improvement in performance, the models still need more improvement in terms of the quality of images predicted in the distant future. / Master of Science / Future frame prediction is a technology that allows computers to predict what future video frames will look like. This can be used to predict future occurrences in a video, anticipate anomalies, and aid autonomous devices in smart decision making. Although there is potential with frame prediction technology, there is still progress that needs to be made with it. As the predicted frame becomes farther away from the last input frame, the image becomes blurry and distorted. This indicates that the model is more uncertain about the motion occurring in the image frame. To reduce model uncertainty shown in predictions, optical flow information from each video was extracted and combined with the video frames. Optical flow is the change in direction and magnitude of a moving object in a video. This type of information is helpful for making frame predictions because it gives the model additional information on how objects are moving to base its predictions on. In this work, the change in image quality evaluation metrics and overall image quality is analyzed across 4 different datasets between a state-of-the-art frame prediction model and a modified model that combines optical flow information. The results demonstrate that adding optical flow information improves the model Mean Squared Error (MSE) by 4.11% and its Structural Similarity Index Metric (SSIM) by 0.41% for the Moving MNIST dataset. Optical flow improved the SSIM value of Taxi BJ, KTH, and KITTI by 0.02%, 0.011%, and 1.297% respectively. While there was a consistent improvement in performance, the models still need more improvement in terms of the quality of images predicted in the distant future.

Rotary disc mowers are capable of much higher throughput than traditional mowers, and as a result have much higher power demands. With the recent increasing popularity of rotary mowers and the ever-increasing size of high-capacity forage and haying equipment, manufacturers are offering larger mowers with higher power demands. A disc mower cutterbar requires a significant amount of the total implement power, and little research has been performed relating to the study of power requirements and material movement. The objectives of this research were to develop a means of measuring cutterbar power requirements and material flow, and to perform a statistical design of the mower in operation. Using these results, it may be possible to offer insight into changes that could be considered in the design of rotary mower cutterbars.<p> Two types of experiments were performed on a prototype disc mower. Both experiments were performed in both alfalfa and light grass, at three different ground speeds, and at three different disc rotational velocities. The first experiment consisted of measuring the power requirements and specific energy of three individual discs on the prototype cutterbar. The rotational direction of the three adjacent discs investigated produce converging and diverging cutting zones. Measurements were made by means of instrumented drive hubs, each with individual onboard data acquisition systems. Average power measurements recorded by each instrumented hub were found to be approximately 2.45 and 3.31 kW for alfalfa and grass, respectively. Likewise, average specific energy measurements for alfalfa and grass ranged from 1.83 to 5.74 kWh/t, respectively. The second experiment involved the optical flow field calculation from high-speed videos captured of the cutterbar in operation. A phase-based optical flow algorithm was applied to videos captured to study material flow across the cutterbar.<p> An analytical model and two regression models were developed to describe and predict the cutterbar specific energy at the converging and diverging zones. The analytical model was based on the cutting and transport processes as performed by the rotating discs, as well as the zero-load power. The model included the results of the averaged material flow vector angles. The regression models were fitted to the experimental specific energy results as a function of the different combinations of effects in the experimental design. All three models, which were produced for both the converging and diverging cutting zones, were found with coefficient of determination values between 0.79 and 0.96.

Rotary disc mowers are capable of much higher throughput than traditional mowers, and as a result have much higher power demands. With the recent increasing popularity of rotary mowers and the ever-increasing size of high-capacity forage and haying equipment, manufacturers are offering larger mowers with higher power demands. A disc mower cutterbar requires a significant amount of the total implement power, and little research has been performed relating to the study of power requirements and material movement. The objectives of this research were to develop a means of measuring cutterbar power requirements and material flow, and to perform a statistical design of the mower in operation. Using these results, it may be possible to offer insight into changes that could be considered in the design of rotary mower cutterbars.<p> Two types of experiments were performed on a prototype disc mower. Both experiments were performed in both alfalfa and light grass, at three different ground speeds, and at three different disc rotational velocities. The first experiment consisted of measuring the power requirements and specific energy of three individual discs on the prototype cutterbar. The rotational direction of the three adjacent discs investigated produce converging and diverging cutting zones. Measurements were made by means of instrumented drive hubs, each with individual onboard data acquisition systems. Average power measurements recorded by each instrumented hub were found to be approximately 2.45 and 3.31 kW for alfalfa and grass, respectively. Likewise, average specific energy measurements for alfalfa and grass ranged from 1.83 to 5.74 kWh/t, respectively. The second experiment involved the optical flow field calculation from high-speed videos captured of the cutterbar in operation. A phase-based optical flow algorithm was applied to videos captured to study material flow across the cutterbar.<p> An analytical model and two regression models were developed to describe and predict the cutterbar specific energy at the converging and diverging zones. The analytical model was based on the cutting and transport processes as performed by the rotating discs, as well as the zero-load power. The model included the results of the averaged material flow vector angles. The regression models were fitted to the experimental specific energy results as a function of the different combinations of effects in the experimental design. All three models, which were produced for both the converging and diverging cutting zones, were found with coefficient of determination values between 0.79 and 0.96.

Optical flow indicates a computing method which utilizes the brightness variation of image motion in further image disposition, without the prior understanding of field, environment, or related object. It also reflects the image variation to compute the variation of optical flow field due to the motion of time and distance. The Essay content follows the optical flow as its basis theory consideration to find the direction of image motion. It utilizes the auto-focus principle to search the corrective focus basis, to proceed the identify analysis through the target object. To obtain the visual tracking result after the auto-focus of image definition, moving direction when achieve the target object. The application method is easily to determine the movement or stationary target in the certain field.

Displacement information is important in dynamic image analysis. The method of optical flow has been well applied to compute the displacement in the field of computer vision. We apply the method of optical flow to compute the displacement information for video compression. We can predict the optical flow between picture 2 and picture 3 by the optical flow between picture 1 and picture 2 by using the principle of inertia. Using the predicted optical flow between picture 2 and picture 3, we can recover a rough version of picture 3. This version can be taken as a reference picture for encoding picture 3. This reference will decrease the compensation information in the following stage, and then improve the compression ratio of MPEG . We modified the traditional optical flow of Horn & Schunck to a regional optical flow by segmentation. Then, the displacement information could be reduced. The picture is recovered by the optical flow in a modified way because some objects couldn¡¦t move in the same direction and velocity. We propose two methods in optical flow prediction. One is the complete information: shape and value. The other is shape only with value recomputed and extra encoded. Experiments demonstrate a better compression ratio of 1% for our motion compensation than the regular motion compensation.