Figure 6 - uploaded by Jan Paul Siebert
Content may be subject to copyright.
Source publication
The goal of the Active Stereo Probe (ASP) project is the on-line recovery of 3D surfaces from stereo images captured using a dynamic binocular robot vision system. In this paper, we present results of 3D surface recovery using scale-space automatic stereo-matching. These results have been considerably enhanced by bathing the scene in textured light...
Context in source publication
Context 1
... 3D surface model of the scene is obtained by matching the texture projected stereogramme using MSSM and back-projecting the matched image points into three-dimensions using camera parameter information provided by a previous stage of static calibration. Such a surface model is shown in figure 6 after it has been vertex shaded, Gouraud shaded and rendered (surface "draped") with the left image from the normally illuminated stereogramme. A contour model obtained from the recovered 3D surface information is shown in figure 7. The area corresponding to the surface model and the contour map is indicated by the white rectangle in the left image of the texture projected stereogramme ( figure 5). ...
Similar publications
This study presents a novel navigation method designed to support a real-time, efficient, accurate indoor localisation for mobile robot system. It is applicable for inertial measurement units (IMU) consisting of gyroscopes, accelerometers, and magnetic besides stereo vision (SV). The current indoor mobile robot localisation technology adopts tradit...
A road multi‐object detection algorithm is one of the core algorithms for intelligent road cleaning robots relying on machine vision. Most existing object detection algorithms analyse all image regions and finally calculate the category and location of each object. However, it is not necessary to analyse all areas of the image when detecting object...
This paper sets out to overview the progress of a binocular robot vision project titled the “Active Stereo Probe” (ASP) and present the novel aspects of an active controllable illumination system to be integrated with a robot vision head now under development.
Citations
... EXECUTION TIMES, IN SECONDS, FOR MSSM IN 1993[7] ...
Integrating a stereo-photogrammetric robot head into a real-time system requires software solutions that rapidly resolve the stereo correspondence problem. The stereo-matcher presented in this paper uses therefore code parallelisation and was tested on three different processors with x87 and AVX. The results show that a 5mega pixels colour image can be matched in 5,55 seconds or as monochrome in 3,3 seconds.
... The roles of anthropometry and forensic science have intertwined beginning with Bertillon in the 1800s [2,3] and anthropometry was one of the identification methods used in [4][5][6]. Although more sophisticated vision based methods of image comparison are being developed [7,8], it remains to be seen what can be achieved by utilizing ratios between key facial landmarks on single 2D images. Even if reliable automatic methods for face image comparison can be developed, the need for manual intervention in terms of landmark placement are likely to be required where low-quality images have to be analysed, such as generated by many currently installed CCTV systems. ...
... Although not utilised in this study, the creation of 3D images has its place and is important to the field of facial recognition to address the fundamental problem of rotation variation amongst images. A great deal of effort by researchers has been spent on creating a 3D facial image [7,8,37,38], but 3D images are not without their problems as well. Discouraging results were seen when comparing a 2D image with that of a 3D laser scan image by comparing the locations of the X and Y coordinates of a maximum of seven landmarks [39]. ...
... The set of comparisons was small and combined with the fact that only seven landmarks were used could have influenced the poor outcome. In reality, it may not be feasible to take a 3D image scan of a possible suspect as the subject will probably not agree, but using photographs taken of the suspect at several different angles to create a 3D image of the suspect would be possible [7,8]. ...
An abundunce of surveillance cameras highlights the necessity of identifying individuals recorded. Images captured are often unintelligible and are unable to provide irrefutable identifications by sight, and therefore a more systematic method for identification is required to address this problem. An existing database of video and photograhic images was examined, which had previously been used in a psychological research project; material consisted of 80 video (Sample 1) and 119 photograhic (Sample 2) images, though taken with different cameras. A set of 38 anthropometric landmarks were placed by hand capturing 59 ratios of inter-landmark distances to conduct within sample and between sample comparisons using normalised correlation calculations; mean absolute value between ratios, Euclidean distance and Cosine θ distance between ratios. The statistics of the two samples were examined to determine which calculation best ascertained if there were any detectable correlation differences between faces that fall under the same conditions. A comparison of each face in Sample 1 was then compared against the database of faces in Sample 2. We present pilot results showing that the Cosine θ distance equation using Z-normalised values achieved the largest separation between True Positive and True Negative faces. Having applied the Cosine θ distance equation we were then able to determine that if a match value returned is greater than 0.7, it is likely that the best match will be a True Positive allowing a decrease of database images to be verified by a human. However, a much larger sample of images requires to be tested to verify these outcomes.
This paper reports on the development of C3D, a computer-based product for constructing 3-D surface models of real world 3-D objects, e.g. a model of a human face, from stereo image pairs. C3D is a GUI-based computer program that converts the implicit 3-D information contained within the stereo image pair into an explicit 3-D surface model in a standard CAD file format. Hence, C3D extracts automatically the 3-D information from a stereo pair of images which have been frame-grabbed (digitised) into a computer and then builds a 3-D surface model. This surface model can then be edited using standard CAD packages or manipulated within virtual reality environments in the usual way.
Almost every part of the earth's surface and even man-made structures are subject to variations of size, shape and position with time. The period of these changes differs from case to case depending on the individual characteristics of the deformable body. The determination and sometimes interpretation of these movements is the objective of deformation surveys. Photogrammetric methods are suitable for monitoring displacements, because a photograph represents a remote, complete and instantaneous record of an object. An instantaneous record of particular situation which may be changing in time, together with a complete coverage, is most appropriate for a phenomenon such as a moving object. Here, rotary kiln in Abyek cement factory has been chosen for study. The main purpose of monitoring these kilns is to determine the displacement of the centre of the kiln in the place of rollers. On the other hand, we want to monitor the displacement of the kiln in order to avoid dangers due to horizontal and vertical movements. Close-Range photogrammetric technique was chosen to carry out this research. The results according to the ground coordinate of the check points, accuracy derived from variance-covariance matrix and computing the displacements for four points instead of one point, are acceptable and mm accuracy for determining the coordinates shows that this method is suitable for monitoring studies, especially for specific cases like this case which popular geodetic methods are not applicable due to high temperature of the kiln area.
Photogrammetric measurement for the diagnosis and treatment of human conditions and for bio-medical research is a form of close-range photogrammetry with its own distinctive challenges and constraints. Reports of fully digital systems are somewhat limited so far, being restricted primarily to face and body measurement and to motion recording, but clear patterns are apparent in the approaches being adopted.The effectiveness of photogrammetric measurement in gait analyses and some other body measurements involving targets, has stimulated commercial development of a number of comprehensive digital systems. They are characterised by the use of multiple cameras, LED or reflective targets, fast image processing based on target detection, links to other recording systems, and by the provision of comprehensive medical information.Surface shape measurements by state-of-the-art photogrammetric systems have been aimed primarily at the face, back and torso. But in contrast to target-based measurement systems, they are characterised not by commercial systems, but by individually tailored hardware and software systems based on low-cost, low-resolution cameras, the casting of a texturising light pattern, image processing to detect features within the pattern, and area-based rather than feature-based matching methods for automated stereoscopic correlation. In common with motion measurement, effective and informative output is crucial for these applications.Medical photogrammetry does not end with these applications, but distinctive trends in the use of digital methodology are not apparent among other measurement tasks. On the other hand, digital image processing has contributed usefully to optical measurement techniques which are not strictly photogrammetric but which are useful for external measurement on the human body.
