Guanqun Bao

Polyp detection and radius measurement in small intestine using video capsule endoscopy

Video Capsule Endoscopy (VCE) was invented in the year 2000 and rapidly became one of the most popular noninvasive non-surgical inspection techniques in the diagnosis of gastrointestinal (GI) tract, especially in small intestine. A critical issue of capsule endoscopic examination is to determine the location and size of polyps. A critical problem associated with capsule endoscopic examination is to localize and correctly estimate the size of polyps for proper clinical treatment. In this paper we present a global statistical method which could automatically detect the polyps in VCE frames and determine their radii. The proposed method gathers the statistical information from available RGB channels. The statistical information is then fed to a support vector machine (SVM) to determine the existence and radii of polyps. The experimental result of this approach shows its improvement of accuracy when compared with other methods in the literature.

A video-based speed estimation technique for localizing the wireless capsule endoscope inside gastrointestinal tract

Wireless Capsule Endoscopy (WCE) is progressively emerging as one of the most popular non-invasive imaging tools for gastrointestinal (GI) tract inspection. As a critical component of capsule endoscopic examination, physicians need to know the precise position of the endoscopic capsule in order to identify the position of intestinal disease. For the WCE, the position of the capsule is defined as the linear distance it is away from certain fixed anatomical landmarks. In order to measure the distance the capsule has traveled, a precise knowledge of how fast the capsule moves is urgently needed. In this paper, we present a novel computer vision based speed estimation technique that is able to extract the speed of the endoscopic capsule by analyzing the displacements between consecutive frames. The proposed approach is validated using a virtual testbed as well as the real endoscopic images. Results show that the proposed method is able to precisely estimate the speed of the endoscopic capsule with 93% accuracy on average, which enhances the localization accuracy of the WCE to less than 2.49 cm.

Hybrid Localization of Microrobotic Endoscopic Capsule Inside Small Intestine by Data Fusion of Vision and RF Sensors

Wireless capsule endoscope (WCE) offers a noninvasive investigation of the entire small intestine, which other conventional wired endoscopic instruments can barely reach. As a critical component of the capsule endoscopic examination, physicians need to keep track of the 3D trajectory that the capsule has traveled inside the lower abdomen to identify the positions of the intestinal abnormalities after they are found by the video source. However, existing commercially available radio frequency (RF)-based localization systems can only provide inaccurate and discontinuous position estimation of the WCE due to nonhomogeneity of body tissues and highly complicated distribution of the intestinal tube. In this paper, we present a hybrid localization technique, which takes advantage of data fusion of multiple sensors inside the WCE, to enhance the positioning accuracy and construct the 3-D trajectory of the WCE. The proposed hybrid technique extracts motion information of the WCE from the image sequences captured by the capsules embedded visual sensor and combines it with the RF signal emitted by the wireless capsule, to simultaneously localize the WCE and mapping the path traveled by the WCE. Experimental results show that the proposed hybrid algorithm is able to reduce the average localization error from 6.8 cm to <;2.3 cm of the existing RF localization systems and a 3-D map can be precisely constructed to represent the position of the WCE inside small intestine.

Automated pavement distress inspection based on 2D and 3D information

During the last few decades, many efforts have been made to produce automatic inspection systems to meet the specific requirements in assessing distress on the road surfaces using video cameras and image processing algorithms. However, due to the noisy images from pavement surfaces, limited success was accomplished. One major issue with pure video based systems is their inability to discriminate dark areas not caused by pavement distress such as tire marks, oil spills, shadows, and recent fillings. To overcome the limitation of the conventional imaging based methods, a probabilistic relaxation technique based on 3-dimensional (3D) information is proposed in this paper. The primary goal of this technique is to integrate conventional image processing techniques with stereovision technology to obtain an accurate topological structure of the road defects. Simulation results show the proposed system is effective and robust on a variety of pavement surfaces.

The Performance of Simulated Annealing Algorithms for Wi-Fi Localization Using Google Indoor Map

Wi-Fi localization is currently the most promising approach to build indoor localization systems. Especially after the recent release of Google Indoor Map for the Android system smart phones, many companies such like Skyhook and TCS etc. have flourished into the business of developing accurate Wi-Fi based indoor localization techniques due to their numerous applications. In this paper, we proposed an accurate Wi-Fi based indoor localization algorithm with the help of Google Indoor Map. The initial position of the mobile station (MS) is estimated according to the received signal strength (RSS) from the calibrated Wi-Fi access points (APs). Then, the position of the MS is allocated by using the simulated annealing (SA) algorithm to search for a better solution. During the searching process, the SA takes the indoor map structure into consideration and updates the cost function weights accordingly. This procedure makes sure the final estimation reaches to a better convergence. Extensive experimental results confirm that our solution is able to provide a much better result compared with other existing indoor localization techniques.

Pavement Distress Detection and Severity Analysis

Automatic recognition of road distresses has been an important research area since it reduces economic loses before cracks and potholes become too severe. Existing systems for automated pavement defect detection commonly require special devices such as lights, lasers, etc, which dramatically increase the cost and limit the system to certain applications. Therefore, in this paper, a low cost automatic pavement distress evaluation approach is proposed. This method can provide real-time pavement distress detection as well as evaluation results based on the color images captured from a camera installed on a survey vehicle. The entire process consists of two main parts: pavement surface extraction followed by pavement distress detection and classification. In the first part, a novel color segmentation method based on a feed forward neural network is applied to separate the road surface from the background. In the second part, a thresholding technique based on probabilistic relaxation is utilized to separate distresses from the road surface. Then, by inputting the geometrical parameters obtained from the detected distresses into a neural network based pavement distress classifier, the defects can be classified into different types. Simulation results are given to show that the proposed method is both effective and reliable on a variety of pavement images.

Motion estimation of the endoscopy capsule using region-based Kernel SVM classifier

Wireless Capsule Endoscopy (WCE) allows physicians to examine the entire digestive system without any surgical operation. Although it provides a noninvasive imaging approach to access the gastrointestinal (GI) tract, the biggest drawback of this technology is its incapability of localizing the capsule when an abnormality is found by the video source. Existing localization methods based on radio frequency (RF) and magnetic field suffer a great error due to the non-homogeneity of the human body and uncertain movement of the endoscopic capsule. In this paper, we developed a novel image classification technique to analyze the motion of the capsule. The proposed method segments the endoscopic images into sub-regions and classified them using Kernel Support Vector Machine (K-SVM). Our method performs better than the traditional pixel based classification methods since the quantized feature vector is able to better represent the image due to its natural resistant characteristic against the noises. Besides, the Kernel function is able to map the low dimensional feature vectors to higher dimensional space to form a non-linear decision hyper-plane. Experimental results show that the proposed method is able to reach a high accuracy of 92%.

Pavement distress detection and classification using feature mapping

The detection of cracks and other degradations on pavement surfaces was traditionally done by human experts using visual inspection while driving along the surveyed road. To overcome the limitations of the manual scheme, an automatic crack detection and classification system is proposed in this paper to both speed up and reduce the subjectivity of the process. After the pavement images are captured by a digital camera, regions corresponding to cracks are detected over the acquired images by local segmentation and then represented by a matrix of square tiles. Since the crack pattern can be represented by the distribution of the crack tiles, standard deviations for both vertical and horizontal histograms are calculated to map the cracks onto a 2D feature space, where four crack types, namely, longitudinal, transversal, block, and alligator cracks can be identified. The experimental results, obtained by testing real pavement images over local asphalt roads, present the effectiveness of our algorithm for automating the process of identifying road distresses from images.

Measurement of motion detection of Wireless Capsule Endoscope inside large intestine

Wireless Capsule Endoscope (WCE) provides a noninvasive way to inspect the entire Gastrointestinal (GI) tract, including large intestine, where intestinal diseases most likely occur. As a critical component of capsule endoscopic examination, physicians need to know the precise position of the endoscopic capsule in order to identify the position of detected intestinal diseases. Knowing how the capsule moves inside the large intestine would greatly complement the existing wireless localization systems by providing the motion information. Since the most recently released WCE can take up to 6 frames per second, its possible to estimate the movement of the capsule by processing the successive image sequence. In this paper, a computer vision based approach without utilizing any external device is proposed to estimate the motion of WCE inside the large intestine. The proposed approach estimate the displacement and rotation of the capsule by calculating entropy and mutual information between frames using Fibonacci method. The obtained results of this approach show its stability and better performance over other existing approaches of motion measurements. Meanwhile, findings of this paper lay a foundation for motion pattern of WCEs inside the large intestine, which will benefit other medical applications.

A Novel Cyber Physical System for 3-D Imaging of the Small Intestine In Vivo

Small intestine is the longest organ in the gastrointestinal tract where much of the digestion and the food absorption take place. Wireless video capsule endoscope (VCE) is the first device taking 2-D pictures from the lesions and the abnormalities in the entire length of the small intestine. Since precise localization and mapping inside the small intestine is a very challenging problem, we cannot measure the distance traveled by the VCE to associate lesions and abnormalities to locations inside the small intestine, and we cannot use the 2-D pictures to reconstruct the 3-D image of interior of the entire small intestine in vivo. This paper presents the architectural concept of a novel cyber physical system (CPS), which can utilize the 2-D pictures of the small intestine taken by the VCE to reconstruct the 3-D image of the small intestine in vivo. Hybrid localization and mapping techniques with millimetric accuracy for inside the small intestine is presented as an enabling technology to facilitate the reconstruction of 3-D images from the 2-D pictures. The proposed CPS architecture provides for large-scale virtual experimentations inside the human body without intruding the body with a sizable equipment using reasonable clinical experiments for validation. The 3-D imaging of the small intestine in vivo allows a lesion to be pinpointed for follow-up diagnosis and/or treatment and the abnormalities may be observed from different angles in 3-D images for more thorough examination.