Mohammad Shorif Uddin

Bipolarity and Projective Invariant-Based Zebra-Crossing Detection for the Visually Impaired

A safe road-crossing system is an extreme necessity to improve the mobility of the visually impaired. It is important for a blind person to know whether a frontal area is a crossing or not. A crossing is characterized by zebra pattern i.e. by constant width periodic white stripes on a usual black road surface, which can be treated as a bipolar pattern. In this paper, a fast and stable algorithm for detecting the location of a pedestrian crossing using an image captured by a single camera is presented. This is achieved through bipolarity-based segmentation and projective invariant-based recognition. The algorithm includes three steps. First, we segment the image on the basis of bipolarity and pick the crossing candidates on the basis of area. Second, feature points are extracted on the candidate area based on Fisher criterion. Third, we use projective invariants to recognize the crossing. The experiments on a large number of street scenes with and without crossing demonstrate the effectiveness of the proposed algorithm.

Adaptive computer-based spatial-filtering method for more accurate estimation of the surface velocity of debris flow

An adaptive computer-based spatial-filtering velocimeter to measure the surface velocity of a natural debris flow with high accuracy is described that can adjust the filter parameters, specifically, the slit width of the filter, based on the surface-pattern characteristics of the flow. A computer simulation confirms the effectiveness of this technique. The surface velocity of a natural debris flow at the Mt. Yakedake Volcano, Japan, was estimated by this adaptive method, and the results were compared with those obtained by two other methods: hardware-based spatial filtering and normal computer-based spatial filtering.

Synthetic and spectroscopic characterization of Rh(I)-( S )-amino acid complexes with diphosphine and triphosphine ligands

Reaction of [Rh(η4-cod)(S)-amino-acidato] ((S)-amino acidate = (S)-O2C-CHR-NH2; cod = cycloocta-1,5-diene) with 1,2-bis(diphenylphosphino)ethane (dppe) affords the ionic [Rh(dppe)2]{(S)-O2C-CHR-NH2} (R = Me, I; Ph, II) complexes. Reactions with 1,3-bis(diphenylphosphino)propane (dppp) or 2,2,2-tris(diphenylphosphinomethyl)ethane (triphos) give the neutral [Rh(dppp){(S)-O2C-CHR-NH2}] (R = Me, III; Ph, IV) or [Rh(η2-triphos){(S)-O2C-CHR-NH2}] (R = Me, V; Ph, VI) complexes. The complexes are characterized by elemental analysis, UV–Vis-, IR-, 1H/31P{1H} NMR- and mass-spectroscopy. Two molecules of dppe coordinate to the Rh(I) symmetrically by replacing both cod and (S)-amino acidate to give I–II. Only one molecule of dppp (or triphos) coordinate to the Rh(I) asymmetrically by replacing only cod to give III–VI. Two diastereomeric Rh(I)-complexes are present in V and VI. The results further suggest that the ligands are arranged in a distorted square planar geometry around the Rh(I) centre. The use of triphos instead of dppe or dppp yields the same coordination sphere.

Detection of pedestrian crossing and measurement of crossing length - an image-based navigational aid for blind people

Pedestrian crossings are dangerous places for a visually impaired person to cross safely. This paper describes a simple method for the detection of the location of a pedestrian crossing as well as measurement of its length to enhance the safety and mobility of blind people while crossing a road. A crossing is characterized by zebra pattern i.e. by evenly spaced white stripes on a usual black road surface. Detection of the crossing location as well as measurement of its length is done using this criterion from the image captured by a single camera. The method at first checks for the existence of a crossing; if there exists a crossing then it goes to measure the crossing length. Experimental results on a large number of street scenes with and without crossings demonstrate the effectiveness of the proposed technique.

Speckle noise reduction and segmentation of kidney regions from ultrasound image

Ultrasound imaging plays a crucial roles in medical field to estimate kidney size, position, appearance and helps to detect structural abnormalities as well as the presence of cysts, stones, cancer, congenital anomalies, swelling, blockage of urine flow etc. But presence of speckle noise and low contrast in ultrasound images, detection of kidney is a difficult as well as challenging task. In this paper we develop and implement a system, which can segment human kidney from ultrasound images, usable during surgical operations like punctures. First, we take input image and perform restoration on that image. Then we reduce speckle noise and smooth resultant image using Gabor filter. Histogram equalization is used to enhance the image quality. For this study, two segmentation techniques were chosen to be compared consist of cell segmentation and region based segmentation. For better result we use region based segmentation to extract kidney regions. Lastly we perform refinement and crop the segmented kidney region from the original image.

Detection of pedestrian crossing using bipolarity feature-an image-based technique

This paper presents a novel approach for detecting pedestrian crossings to enhance the safety and mobility of blind people while crossing a road. It is extremely important for a blind person to know whether a frontal area is a crossing or not. In a crossing, the usual black road surface is painted with constant-width periodic white bands. An image-based technique has been developed to detect the bipolar patterns of pedestrian crossings. The presence of pedestrian crossings are inferred by careful analysis of crossing width, crossing direction, number of crossing bands, as well as bandwidth trend. Experimental evaluation of the proposed approach was conducted using 100 real images with and without crossings. It was found that the proposed technique performed with 95% accuracy and with no false positive.

Measurement of the length of pedestrian crossings - a navigational aid for blind people

This paper describes a fast as well as simple method for measurement of the length of pedestrian crossings using a single camera for the purpose of a travel aid for blind people. In a crossing, the usual black road surface is painted with constant width periodic white lines. In Japan, this width is 45 cm. The crossing region as well as its length is detected using this concept. At first, the crossing direction is determined from the power spectrum using fast Fourier transform. The periodic white and black bands are detected using integration along the crossing direction and differentiation of the integral data perpendicular to the crossing direction. Then the crossing length is calculated using the number of white and black bands in the crossing region. Experiment is performed using real road scenes with pedestrian crossing. The technique is successful in measuring the length of the crossing with high accuracy if the image resolution is good and the white paintings on the crossing are fine.

Estimation of the surface velocity of debris flow with computer-based spatial filtering

A computer-based spatial-filtering velocimeter to measure the surface velocity of natural debris flow is described. This is a simple and interesting technique implemented with a spatial filter constructed as a software program that processes the video image of debris flow instead of a hardware implementation. The surface velocity of the debris flow at the Mt. Yakedake Volcano, Japan, was estimated by this computer-based spatial-filtering method, and the results were compared with those obtained by a hardware-based spatial-filtering method. Computer-based spatial filtering has the important advantage of a capability for tuning the spatial-filter parameters to the target flow.

Automatic Adaptive Facial Feature Extraction Using CDF Analysis

This paper proposes a novel adaptive algorithm to extract facial feature points automatically such as eyes corners, nostrils, nose tip, and mouth corners in frontal view faces, which is based on histogram representing CDF approach. At first, the method adopts the Viola-Jones face detector to detect the location of face and the four relevant regions such as right eye, left eye, nose, and mouth areas are cropped in a face image. Then the histogram of each cropped relevant region is computed and its CDF value is employed by varying different threshold values to create a new filtering image in an adaptive way. The connected component of interested area for each relevant filtering image is indicated our respective feature region. A simple linear search and a contour algorithm are applied to extract our desired corner points automatically. The method was tested on a large BioID face database and the experimental results have achieved average success rates of 95.56%.

Robust zebra-crossing detection using bipolarity and projective invariant

Crossing roads is a great challenge for visually impaired people. A robust technique for detection of zebra crossings is described. This is achieved through bipolaritybased segmentation and projective invariant-based recognition. The technique shows good performances under various illuminations such as sunny, cloudy and rainy situations in the day time and also evening and night environments.