Conference Paper

Permanent URI for this collectionhttps://hdl.handle.net/10361/7308

Browse

Now showing 1 - 7 of 7

Automatic measurement of rail line expansion joint gaps
(© 2014 Institute of Electrical and Electronics Engineers Inc., 2015-03) Islam, Samiul; Khan, Rubayat Ahmed; Biswas, Rubel; Department of Computer Science and Engineering
Expansion joint gaps are the gaps which are deliberately left between the rail ends to allow for expansion of the rails in hot weather. Over gapping of these end to end gaps often result in derailments. Therefore in order to prevent dangerous situations and ensuring safety rail lines are periodically inspected. Rail inspection in many countries especially in third world countries, like Bangladesh, is performed manually by a trained human operator who periodically walks along the track searching for visual anomalies. Such manual inspection is lengthy, laborious and subjective. This paper presents a machine vision-based technique to automatically measure the length of rail line expansion joint gaps using morphological processing. This approach has confirmed to successfully detect scenarios of different condition with an accuracy of 89%, thus proving its robustness.
Automatic detection of defective rail anchors
(2014-11) Khan, Rubayat Ahmed; Islam, Samiul; Biswas, Rubel; Department of Computer Science and Engineering
Rail line anchors/fasteners are the metallic components that attach each line with the sleepers. These are essential rail components as absence of these often result in derailments. Therefore in order to prevent dangerous situations and ensuring safety rail lines are periodically inspected. Rail inspection in many countries especially in third world countries, like Bangladesh, is performed manually by a trained human operator who periodically walks along the track searching for visual anomalies. This manual inspection is lengthy, laborious and subjective. This paper presents a machine vision-based technique to automatically detect the presence of rail line anchors/fasteners using Shi - Tomasi and Harris - Stephen feature detection algorithms. This approach has confirmed to successfully detect scenarios with both grounded and missing anchors invoked in the experiment, with an accuracy of 83.55%, thus proving its robustness.
LVQ and HOG based speed limit traffic signs detection and categorization
(© 2014 IEEE Computer Society, 2014) Biswas, Rubel; Tora, Moumita Roy; Bhuiyan, Farazul Haque; Department of Computer Science and Engineering
The proper identification of the traffic signs can ensure driving safety and can play a very important role in reducing the number of road accidents significantly. This paper represents a uniform way to detect the speed limit traffic signs and to confirm it by recognizing the sign's speed number. In this system, firstly the red color objects are segmented from an image using LVQ. Secondly, detected circular part is extracted from the color segmented image using bounding box and then Histogram Oriented Gradient (HOG) is used to collect the feature of the extracted part of circular object and finally SVM classifier is applied to train the HOG features of each speed no. into their corresponding classes. In general, the system detects the prohibitory traffic sign in the first place, specifies whether the detected sign is a speed limit sign, and then determines the allowed speed in case the detected sign is a speed limit sign. The SVM classifier was trained with 200 images which were collected in different light conditions. To check the robustness of this system, it was tested against 381 images which contain 361 Speed Limit traffic sign and 30 Non- Speed Limit signs. It was found that the accuracy of recognition was 92.75% which indicates clearly the high robustness targeted by this system.
Detection and classification of speed limit traffic signs
(© 2014 Institute of Electrical and Electronics Engineers Inc., 2014-10) Biswas, Rubel; Fleyeh, Hasan; Mostakim, Moin; Department of Computer Science and Engineering
This paper presents a novel traffic sign recognition system which can aid in the development of Intelligent Speed Adaptation. This system is based on extracting the speed limit sign from the traffic scene by Circular Hough Transform (CHT) with the aid of colour and non-colour information of the traffic sign. The digits of the speed limit sign are then extracted and classified using SVM classifier which is trained for this purpose. In general, the system detects the prohibitory traffic sign in the first place, specifies whether the detected sign is a speed limit sign, and then determines the allowed speed in case the detected sign is a speed limit sign. The SVM classifier was trained with 270 images which were collected in different light conditions. To check the robustness of this system, it was tested against 210 images which contain 213 speed limit traffic sign and 288 Non- Speed limit signs. It was found that the accuracy of recognition was 98% which indicates clearly the high robustness targeted by this system.
Night mode prohibitory traffic signs detection
(© 2013 Institute of Electrical and Electronics Engineers Inc., 2013) Biswas, Rubel; Khan, Arif; Khan, Mumit; Alom, Md. Zahangir
Prohibitory traffic signs play an important role in guiding, warning and regulating traffic system. As driving over the speed limit is often the major cause of accidents, detecting this group of prohibitory signs may reduce this danger. This paper presents an approach to detecting speed limit signs at night mode which is based on Multi-Scale Retinex Color Restoration and Hough Transform. Experiment to check the strength of this approach shows that approximately 96.6% of the prohibitory traffic signs invoked for this test were successfully detected. This test was carried out at dark mode images from different country.
Night mode face recognition using adaptively weighted sub-pattern PCA
(© 2012 IEEE, 2012) Alom, Md. Zahangir; Khan, Arif; Biswas, Rubel; Khan, Mumit; Department of Computer Science and Engineering
The face recognition problem is made difficult by the great variability in head rotation and tilt, lighting intensity and angle, facial expression, aging, partial occlusion (e.g. Wearing Hats, scarves, glasses etc.), etc. Principal components from the face space are used for face recognition to reduce dimensionality of database images. However, this paper discusses on adaptively weighted sub-pattern PCA (Aw-SpPCA) based face recognition system for dark images that have captured at night. It is really difficult to capture good quality picture at night for lacking of light source with traditional acquisition devices like camera or mobile phone. The computational photographic concepts have been applied to enhance the quality of the capture images at night automatically. Multi-scale retinex color restorations (MSRCR) technique has been applied for overcome this problem. Moreover, for recognition phase of this propose method, unlike PCA based on a whole image pattern, Aw-SpPCA operates directly on its sub patterns partitioned from an original whole pattern and separately extracts features from them. Aw-SpPCA can adaptively compute the contributions of each part and then endows them to a classification task in order to enhance the robustness to both expression and illumination variations. Experimental results show that the proposed method is competitive.
Automatic slice growing method based 3D reconstruction of liver with its vessels
(© 2014 Institute of Electrical and Electronics Engineers Inc., 2014) Alom, Md. Zahangir; Mostakim, Moin; Biswas, Rubel; Chakrabarty, Amitabha; Department of Computer Science and Engineering
In the recent years, reconstructing 3D liver and its vessels from abdominal CT volume images becomes an inevitable and necessary research field. In this paper, a method of 3D reconstruction of liver with its vessels has been implemented, which involves volume preprocessing, de-noising, segmentation, contouring, and combination of different modalities. An advanced liver segmentation algorithms have been proposed: The first one is a 2.5D method that utilizes automatic Slice Growing Method (SGM) to segment liver part of each slice of a data set. It takes advantage of curvature control of level set segmentation method to distinguish liver and adjacent organs. It is proved that the result of this proposed method is much better than simple 3D level set method in liver segmentation. In the case of liver vessel segmentation, we have proposed an improved smoothing method dedicate to 3D vascular volume which results from region growing segmentation method. The cooperation of region growing method and proposed smoothing method has been demonstrated the possibility of efficient vessel segmentation with very accurate results. And the results indicate that our method is suitable for anatomical studying and surgical planning.

Browse

Recent Submissions