Over the past few decades, a variety of visual prostheses is developed to allow for the restoration of the vision for the blind. In visual prostheses, visual perception is limited to extremely low image resolution mainly due to restrictions in the fabrication of efficient microelectrode arrays. As a result, tasks such as navigation and way finding become difficult for those using implantable visual prostheses. Depth cue is a suitable alternative to intensity images to improve the quality and success of the aforementioned tasks in patients. After the processing of depth images, intensity of an object depends on its distance from the patient. Based on this principle, a method for preprocessing and downsampling of the depth images is proposed in this paper. We propose a method to enhance the contrast of the depth images and downsample the results to 6 × 12 images. This paper analyzes common downsampling methods and proposes a method based on the mode function. In the proposed method, the mode function is applied on every four successive frames to use temporal information in addition to stationary information. Quantitative and qualitative evaluations upon the LIRIS dataset are presented to compare the results of proposed method with rivals.
In this paper, first a closed-form formulation is analytically derived for the pattern of iso-disparity strip widths associated with the ground plane in disparity map images. This formulation calculates the iso-disparity strip widths based on the parameters of the stereo camera setup ( i.e. , height, tilt angle, and baseline of the cameras) used to capture the images. The proposed formulation was then statistically validated using the results achieved in the case of a bank of stereo image pairs with different stereo camera setup parameters. Validation of the proposed formulation was in the presence of the strip width imperfections that appear in reality, and were shown to be in the form of additive Gaussian noise. Using the formulation proposed for iso-disparity strip widths, the paper then introduces a novel approach for ground plane detection based on the concept of iso-disparity strips in disparity map images. To add to the robustness of the proposed procedure against strip width noise, Cumulative Moving Average (CMA) and a dynamic thresholding technique are used to find the width of the strips corresponding to the ground plane. According to experimental results for synthesized and captured datasets, while exhibiting sufficiently low false positive rates (1.38% and 5.83%), the proposed method detects the ground plane with average true positive rates of as high as 80% and 54% in 65 ms and 224 ms, respectively.
Movement pattern analysis is an effective approach to detect anomalies and behavior prediction. Existing methods depend on known scenes in which objects move along a predefined path. Moreover, most of these methods investigate 2D movement patterns. It is desirable to have automatic object movement pattern construction reflecting the knowledge of the scene. This paper proposes an automatic learning system for 3D movement patterns. The movement path of each object is considered to be a member of a cluster. In order to learn the movement patterns, the movement path is hierarchically clustered using spatial and temporal information and each movement pattern is then represented by a Gaussian distribution. Subsequently, behavior prediction is investigated using the extracted statistical movement pattern. Finally, the performance of the proposed algorithm is evaluated by simulations. Results indicate that the proposed method has a better performance when movement paths are not on a single plane.
Researchers in the field of visual prostheses need a Simulated Prosthetic Vision (SPV) setup to evaluate their image processing algorithms on people with normal vision before implanting any retinal prostheses. In this paper, an SPV developed for a visual prosthesis is introduced and the associated experimental results are reported. These experiments are designed to examine the efficacy of two down sampling methods, the mode down sampling (MDS) and the nearest neighbor method. The experiments are conducted in a corridor including some obstacles. Three levels of difficulties are considered for each of the two methods and two measures are used to compare the efficiency of the methods: Percentage of Preferred Walking Speed (PPWS), and Total Hit Count (THC). The qualitative and quantitative results reported in this paper reveal that the controlled blinking of phosphenes would present additional information to help the patients.
Disparity map images, as outputs of a stereo vision system, are known as an effective approach in applications that need depth information in their procedure. One example of such applications is extracting planes with arbitrary attributes from a scene using the concept of iso-disparity strips. The width and direction of strips depend on the plane direction and position in the 3D space. In this paper, a statistical analysis is performed to model the behavior of these strips. This statistical analysis as well as a frequency analysis reveal that for each group of iso-disparity strips, which are corresponding to a single plane in 3D, the width of strips can be represented by an average value superposed by an Additive Gaussian Noise (AGN). This means that a simple averaging technique can significantly reduce the measurement noise in applications such as ground detection using these strips. Results show that the width of iso-disparity strips can be measured with an average precision of 96% using the presented noise model.
'%3e%3cg id='e'%3e%3cg id='c' fill='none' stroke='%23fff' stroke-width='2'%3e%3cpath id='b' d='M0 1h26M1 10V5h8v4h8V5h-5M4 9h2m20 0h-5V5h8m0-5v9h8V0m-4 0v9' transform='scale(1.4)'/%3e%3cpath id='a' d='M0 7h9m1 0h9' transform='scale(2.8)'/%3e%3cuse xlink:href='%23a' y='120'/%3e%3cuse xlink:href='%23b' y='145.2'/%3e%3c/g%3e%3cg id='d'%3e%3cuse xlink:href='%23c' x='56'/%3e%3cuse xlink:href='%23c' x='112'/%3e%3cuse xlink:href='%23c' x='168'/%3e%3c/g%3e%3c/g%3e%3cuse xlink:href='%23d' x='168'/%3e%3cuse xlink:href='%23e' x='392'/%3e%3c/g%3e%3cg fill='%23da0000' transform='matrix(45 0 0 45 315 180)'%3e%3cg id='f'%3e%3cpath d='M-.548.836A.912.912 0 0 0 .329-.722 1 1 0 0 1-.548.836'/%3e%3cpath d='M.618.661A.764.764 0 0 0 .422-.74 1 1 0 0 1 .618.661M0 1l-.05-1L0-.787a.31.31 0 0 0 .118.099V-.1l-.04.993zM-.02-.85 0-.831a.144.144 0 0 0 .252-.137A.136.136 0 0 1 0-.925'/%3e%3c/g%3e%3cuse xlink:href='%23f' transform='scale(-1 1)'/%3e%3c/g%3e%3c/svg%3e)
