For object analysis in videos such as in video surveillance systems, the preliminary segmentation step is very
important. Many segmentation methods using static camera have been proposed in the last decade, but they
all suffer in occurrance of object reflection especially on the ground, i.e. reflected regions are also segmented
as foregrounds. We present a new method which detects the border between the real object and its reflection.
Experiments show that an outstanding improvement of segmentation results are obtained by removing the
reflection part of the over-segmented objects.
Speaker change detection (SCD) is a preliminary step for many audio applications such as speaker segmentation
and recognition. Thus, its robustness is crucial to achieve a good performance in the later steps. Especially,
misses (false negatives) affect the results. For some applications, domain-specific characteristics can be used to
improve the reliability of the SCD. In broadcast news and discussions, the cooccurrence of shot boundaries and
change points provides a robust clue for speaker changes.
In this paper, two multimodal approaches are presented that utilize the results of a shot boundary detection
(SBD) step to improve the robustness of the SCD. Both approaches clearly outperform the audio-only approach
and are exclusively applicable for TV broadcast news and plenary discussions.
KEYWORDS: Chemical elements, Imaging systems, Ultrasonography, Point spread functions, Transducers, Signal to noise ratio, Electronics, Integrated circuits, 3D image processing, Signal processing
We are working on integrating front-end electronics with the ultrasound transducer array for real-time 3D ultrasound imaging systems. We achieve this integration by flip-chip bonding a two-dimensional transducer array to an integrated circuit (IC) that comprises the front-end electronics. The front-end IC includes preamplifiers, multiplexers, and pulsers. We recently demonstrated a catheter-based real-time ultrasound imaging system based on a 16x16-element capacitive micromachined ultrasonic transducer (CMUT) array. The CMUT array is flip-chip bonded to a front-end IC that includes a pulser and preamplifier for each element of the array. To simplify the back-end processing and signal routing on the IC for this initial implementation, only a single array element is active at a time (classic synthetic aperture (CSA) imaging). Compared with classic phased array imaging (CPA), where multiple elements are used on transmit and receive, CSA imaging has reduced signal-to-noise ratio and prominent grating lobes. In this work, we evaluate three array designs for the next generation front-end IC. The designs assume there are 16 receive channels and that numerous transmit pulsers are provided by the IC. The designs presented are: plus-transmit x-receive, boundary-transmit x-receive with no common elements, and full-transmit x-receive with no common elements. Each design is compared with CSA and CPA imaging. We choose to implement an IC for the full-transmit x-receive with no common elements (FT-XR-NC) design for our next-generation catheter-based imaging system.
KEYWORDS: RGB color model, Video, Image segmentation, Reflectivity, Motion models, Data modeling, Video surveillance, Cameras, Space operations, Video compression
A new segmentation approach usable for fixed or motion compensated camera is described. Instead of the often used RGB color space we operate with the invariant Gaussian color model proposed by Geusebroek and temporal information which eliminates unsteady regions surrounded by the moving objects. The Gaussian color model has never been used in video segmentation. Comparison with some state of the art methods in which both subjective and objective evaluation are applied proof the good performance of the proposed method.
KEYWORDS: RGB color model, Video, Image segmentation, Video compression, Fuzzy logic, Cameras, Video surveillance, Visualization, Quality measurement, Video processing
In the case of a static or motion compensated camera, static background segmentation methods can be applied to
segment the interesting foreground objects from the background. Although a lot of methods have been proposed,
a general assessment of the state of the art is not available. An important issue is to compare various state of
the art methods in terms of quality (accuracy) and computational complexity (time and memory consumption).
A representative set of recent techniques is chosen, implemented and compared to each other. An extensive set
of videos is used to achieve comprehensive results. Both indoor and outdoor videos with different environmental
conditions are used. While visual analysis is used for subjective assessment of the quality, pixel based measures
based on available ground truth data are used for the objective assessment. Furthermore the computational
complexity is estimated by measuring the elapsed time and memory requirements of each algorithm. The paper
summarizes the experiments and considers the assets and drawbacks of the various techniques. Moreover, it will
give hints for selecting the optimal approach for a specific environment and directions for further research in this
field.
Progress made in the development of a miniature real-time volumetric ultrasound imaging system is presented. This system is targeted for use in a 5-mm endoscopic channel and will provide real-time, 30-mm deep, volumetric images. It is being developed as a clinically useful device, to demonstrate a means of integrating the front-end electronics with the transducer array, and to demonstrate the advantages of the capacitive micromachined ultrasonic transducer (CMUT) technology for medical imaging. Presented here is the progress made towards the initial implementation of this system, which is based on a two-dimensional, 16x16 CMUT array. Each CMUT element is 250 um by 250 um and has a 5 MHz center frequency. The elements are connected to bond pads on the back side of the array with 400-um long through-wafer interconnects. The transducer array is flip-chip bonded to a custom-designed integrated circuit that comprises the front-end electronics. The result is that each transducer element is connected to a dedicated pulser and low-noise preamplifier. The pulser generates 25-V, 100-ns wide, unipolar pulses. The preamplifier has an approximate transimpedance gain of 500 kOhm and 3-dB bandwidth of 10 MHz. In the first implementation of the system, one element at a time can be selected for transmit and receive and thus synthetic aperture images can be generated. In future implementations, 16 channels will be active at a given time. These channels will connect to an FPGA-based data acquisition system for real-time image reconstruction.
Intravascular ultrasound (IVUS) imaging has become an essential imaging modality for the effective diagnosis and treatment of cardiovascular diseases during the past decade enabled by innovative applications of piezoelectric transducer technology. The limitations in the manufacture and performance of the same piezoelectric transducers have also impeded the improvement of IVUS for emerging clinically important applications such as forward viewing arrays for guiding interventions and high resolution imaging of arterial structure such as vulnerable plaque and fibrous cap, and also implementation of techniques such as harmonic imaging of the tissue and of the contrast agents. Capacitive micromachined ultrasonic transducer (CMUT) technology shows great potential for transforming IVUS not only to satisfy these clinical needs but also to open up possibilities for low-cost imaging devices integrated to therapeutic tools. We have developed manufacturing processes with a maximum process temperature of 250°C to build CMUTs on the same silicon chip with integrated electronics. Using these processes we fabricated CMUT arrays suitable for forward viewing IVUS in the 10-20MHz range. We characterized these array elements in terms of pulse-echo response, radiation pattern measurements and demonstrated its volumetric imaging capabilities on various imaging targets.
This paper presents a novel approach to human body posture recognition based on the MPEG-7 contour-based shape descriptor and the widely used projection histogram. A combination of them was used to recognize the main posture and the view of a human based on the binary object mask obtained by the segmentation process. The recognition is treated as a typical pattern recognition task and is carried out through a hierarchy of classifiers. Therefore various structures both hierachical and non-hierarchical, in combination with different classifiers, are compared to each other with respect to recognition performance and computational complexity. Based on this an optimal system design with recognition rates of 95.59% for the main posture, 77.84% for the view and 79.77% in combination is achieved.
Traditionally, the number of transmit and receive processing channels is equal to the number of transducers (N) in an ultrasound imaging system. Certain applications limit the number of processing channels such that there are fewer channels than transducer elements. For these cases, a subset of M adjacent transducers-a multi-element subarray-performs echo transmission and reception. The processing channels are multiplexed across the array as beams are acquired from each of K subarrays. Combination of all subarray apertures creates a multi-element synthetic aperture (MSA) that represents the response of the entire system. Appropriate 1D filtering is applied in the spatial domain to restore a response approximating that of full phased array imaging. Compared to full phased array (FPA) imaging, MSA imaging reduces the number of front-end processing channels by a factor of N/M. Three variations of the method were simulated for a 128-element array using 32-element subarrays. The effects of the signal bandwidth, subsampling rate, and filter length on the reconstructed 2D point-spread functions are shown. The method closely approximates the performance of FPA imaging with fewer processing channels.
An adaptive filter for smoothing images corrupted by signal dependent noise is presented. The filter is mainly developed for speckle suppression in medical B-scan ultrasonic imaging. The filter is based on mean filtering of the image using appropriately shaped and sized local kernels. Each filtering kernel, fitting to the local homogeneous region, is obtained through local statistics based region growing. Performance of the proposed scheme have been tested on a B-scan image of a standard tissue-mimicking ultrasound resolution phantom. The results indicate that the filter effectively reduces the speckle while preserving the resolvable details. The performance figures obtained through computer simulations on the phantom image are presented in a comparative way with some existing speckle suppression schemes.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.